| 1 |
Author(s):
Lavanya Ramchandra Patil.
Page No :
|
Data-Driven Athlete Performance Analysis and Talent Identification Using Sports Analytics
Abstract
This paper presents a data-driven approach for analyzing athlete performance and identifying high-potential talent using sports analytics. A dataset of 1,200 athletes was analyzed using statistical and exploratory techniques. Key performance indicators such as Skill Assessment Score, Cognitive Score, and Olympic Potential Score were examined along with physiological factors like sleep duration, fatigue level, and heart rate. The results highlight strong relationships between recovery and performance. The study demonstrates how data analytics can support decision-making in sports organizations by improving training efficiency and talent identification.
| 2 |
Author(s):
KATTA SAITEJA .
Page No : 1-2
|
STUDENT ATTENDANCE APP – STUBOOK
Abstract
The Student Attendance App is a smart and efficient digital solution designed to simplify and automate the process of attendance management in educational institutions. Traditional attendance systems are often time-consuming, prone to errors, and difficult to maintain. This application addresses these challenges by providing a centralized platform where attendance can be recorded, stored, and monitored in real time.
| 3 |
Author(s):
M RAVIKARAN .
Page No : 1-3
|
A Study on Consumer Buying Behavior Towards Online Shopping.
Abstract
Shopping online has become a key part of how people shop today because of fast
technology growth and more internet access. This study looks at how consumers
behave when buying things online and what factors affect their choices. It focuses
on important points like ease of use, prices, variety of products, trust, and customer
happiness. The research also discusses the problems shoppers face and gives ideas
to make the online shopping experience better. The results show that convenience
and appealing deals are very important in shaping how consumers act.
| 4 |
Author(s):
Lakshmanan S ,Dr Kandavel R .
Page No : 1-3
|
A Study On Inventory And Distribution Management In The Logistics Sector
Abstract
Managing inventory and distribution plays a crucial role in logistics, making sure that goods move and are stored efficiently. This research looks at how good inventory control and distribution methods help improve operations and keep customers happy. Inventory management keeps stock levels just right, lowers storage costs, and stops shortages from happening, while distribution management makes sure deliveries are on time through effective transport and coordination.
The study also points out how modern technologies like warehouse and transportation management systems can boost accuracy and performance. It further explores the main challenges that logistics companies face, such as unpredictable demand and increasing operational costs. From this analysis, the study finds that well-organized inventory and distribution systems are key to achieving cost savings, enhancing service quality, and gaining an edge in the logistics industry.
Managing inventory and distribution plays a crucial role in logistics, making sure that goods move and are stored efficiently. This research looks at how good inventory control and distribution methods help improve operations and keep customers happy. Inventory management keeps stock levels just right, lowers storage costs, and stops shortages from happening, while distribution management makes sure deliveries are on time through effective transport and coordination.
The study also points out how modern technologies like warehouse and transportation management systems can boost accuracy and performance. It further explores the main challenges that logistics companies face, such as unpredictable demand and increasing operational costs. From this analysis, the study finds that well-organized inventory and distribution systems are key to achieving cost savings, enhancing service quality, and gaining an edge in the logistics industry.
Managing inventory and distribution plays a crucial role in logistics, making sure that goods move and are stored efficiently. This research looks at how good inventory control and distribution methods help improve operations and keep customers happy. Inventory management keeps stock levels just right, lowers storage costs, and stops shortages from happening, while distribution management makes sure deliveries are on time through effective transport and coordination.
The study also points out how modern technologies like warehouse and transportation management systems can boost accuracy and performance. It further explores the main challenges that logistics companies face, such as unpredictable demand and increasing operational costs. From this analysis, the study finds that well-organized inventory and distribution systems are key to achieving cost savings, enhancing service quality, and gaining an edge in the logistics industry.
Managing inventory and distribution plays a crucial role in logistics, making sure that goods move and are stored efficiently. This research looks at how good inventory control and distribution methods help improve operations and keep customers happy. Inventory management keeps stock levels just right, lowers storage costs, and stops shortages from happening, while distribution management makes sure deliveries are on time through effective transport and coordination.
The study also points out how modern technologies like warehouse and transportation management systems can boost accuracy and performance. It further explores the main challenges that logistics companies face, such as unpredictable demand and increasing operational costs. From this analysis, the study finds that well-organized inventory and distribution systems are key to achieving cost savings, enhancing service quality, and gaining an edge in the logistics industry.
| 5 |
Author(s):
Nandhitha & Suyam Praba.
Page No : 1-3
|
LEVERAGING BUSINESS INTELLIGENCE AND DATA VISUALIZATION FOR STRATEGIC DECISION MAKING : AN EMPHERICAL STUDY AT INNOVEXIS
Abstract
In today’s competitive and data-intensive business environment, organizations are increasingly shifting towards data-driven decision-making. This study explores the practical application of Business Intelligence (BI) and data visualization techniques using three real-time datasets—IPL (sports analytics), OLA rider dataset (mobility services), and Emirates Group dataset (aviation industry). The research is based on hands-on data processing activities carried out during an MBA internship, including data cleaning, transformation, modeling, and dashboard development using tools such as Power BI, Power Query, and Pivot Tables. The study highlights how structured data processing and visualization techniques help uncover patterns, trends, and operational insights across different industries.
Keywords: Business Intelligence, Data Visualization, Power BI, Data Cleaning, Dashboarding, Decision Making
| 6 |
Author(s):
M SRIKANTH , Dr. S. S. Onyx Nathanael Nirmal Raj.
Page No : 1-3
|
A Study of Financial Management in Apex Laboratories pvt ltd
Abstract
This study focuses on the financial management practices of Apex Laboratories Pvt. Ltd.. Financial management is an important function in any organization as it helps in planning, controlling, and utilizing financial resources effectively. The study aims to understand how the company manages its funds, financial planning, budgeting, and financial decision-making processes.
The study also highlights the role of the finance department in maintaining financial stability and supporting the overall growth of the company. By analyzing financial activities and management practices, the study explains the importance of efficient financial management in improving profitability and ensuring the smooth functioning of the organization.
| 7 |
Author(s):
Thillai Gowri R.
Page No : 1-3
|
CROWDSOURCED CIVIC ISSUE REPORTING AND RESOLUTION SYSTEM
Abstract
Urban governance in the twenty-first century faces mounting pressure from rapid population growth, aging infrastructure, and widening expectations between government services and commercial responsiveness. The Crowdsourced Civic Issue Reporting and Resolution System is a multi-tier digital platform designed to bridge the communication gap between citizens and municipal authorities by enabling real-time, geotagged reporting of civic infrastructure issues such as potholes, waste accumulation, broken streetlights, water leakages, and drainage blockages.
The system employs a Three-Tier Architecture comprising a cross-platform mobile and web frontend, a microservices-based application logic layer, and a PostgreSQL/PostGIS data management layer. Citizens submit complaints via photograph, GPS location, and icon-based category selection requiring under thirty seconds of user effort. An automated Assignment Algorithm routes each complaint to the correct ward office based on geospatial point-in-polygon matching. Field workers receive task assignments with navigation guidance and are required to submit georeferenced resolution photographs, creating an end-to-end accountability chain.
The administrative dashboard provides real-time heat maps, multi-dimensional complaint filtering, SLA-based escalation workflows, and periodic performance analytics. The system incorporates Privacy by Design principles, OAuth 2.0 authentication, AES-256 data encryption at rest, and TLS 1.3 communication security to protect citizen data in compliance with India's Digital Personal Data Protection Act.
Evaluation through unit, integration, load, usability, and penetration testing demonstrates that the system achieves sub-three-second response times under peak concurrent load and maintains a 99.9% uptime target. The project demonstrates that open-source technology stacks can deliver enterprise-grade civic platforms at operational costs accessible to resource-constrained municipal bodies, contributing to the advancement of data-driven, citizen-centred urban governance.
| 8 |
Author(s):
Ashutosh kumar.
Page No : 1-3
|
A REVIEW ON DIFFERENT TYPES OF ANALYTICAL METHODS
Abstract
Selection of suitable analytical method play an essential role in the discovery, development and manufacturing of pharmaceuticals. Every year, number of drugs entered into the market; hence it is mandatory to select suitable analytical methods for such drugs. After the development, it becomes necessary to validate the new analytical method. Method development is the process which proves that the analytical method is acceptable for use. Validation should be done as per regulatory guidelines such as ICH guidelines. This article was pre-pared with an aim to review different analytical method available for analysis of the drugs.
| 9 |
Author(s):
Stavan Parmar & Aeny Patel.
Page No : 1-3
|
A Study on Balance Between Employee Morale & Productivity
Abstract
This study focuses on understanding the connection between employee morale and productivity in the Information Technology (IT) sector. The research is based on responses collected from employees working in different IT organizations through a structured questionnaire. Important aspects such as work environment, leadership style, motivation, employee engagement, and work-life balance were considered to understand their influence.
The findings suggest that employees who feel positive and satisfied at work are more likely to perform better and contribute effectively to organizational goals. However, the level of impact differs depending on workplace conditions and individual experiences. The study highlights the importance of maintaining a healthy balance between employee well-being and job performance. It also suggests that organizations should focus on creating supportive and flexible work environments to achieve better results in the long run.
| 10 |
Author(s):
M Pranav Kumar.
Page No : 1-3
|
TIME-SERIES MOMENTUM IN CRYPTOCURRENCY MARKETS: A PRE AND POST SPOT BITCOIN ETF ANALYSIS
Abstract
This paper investigates the effectiveness of Time-Series Momentum (TSMOM) as a quantitative trading strategy in cryptocurrency markets, focusing on the structural shift introduced by the first spot Bitcoin ETF launch on January 11, 2024. Using daily price data from January 2018 to March 2026 across six assets: BTC-USD, ETH-USD, IBIT, FBTC, GLD, and SPY, we implement a volatility-scaled TSMOM strategy with monthly rebalancing consistent with Moskowitz, Ooi, and Pedersen (2012). The TSMOM portfolio generated annualized returns of 18.03% pre-ETF and 28.58% post-ETF, with Sharpe ratio improving from 0.82 to 1.22. A two-sample t-test yields p = 0.5835, indicating no statistically significant difference at the 5% level. Backtesting shows TSMOM underperformed Buy-and-Hold by 7.67% in the pre-ETF bull market but outperformed by 20.95% post-ETF. These findings suggest TSMOM adds most value in uncertain, regime-switching conditions following institutional entry through spot ETFs.
| 11 |
Author(s):
Tanveer khan.
Page No : 1-3
|
Fake News Detection
Abstract
The widespread proliferation of misinformation across digital platforms has emerged as a critical challenge to the integrity of public discourse. This paper presents a machine-learning-based Fake News Detection System that classifies news articles as genuine or fabricated using a Random Forest Classifier. Text data undergoes a preprocessing pipeline encompassing tokenization, stop-word removal, and punctuation elimination, followed by feature extraction via Term Frequency-Inverse Document Frequency (TF-IDF) vectorization. An ensemble of decision trees votes collectively to produce the final binary classification label. The model is serialized with Python’s pickle module and deployed through an interactive Streamlit web interface enabling real-time user queries. Experimental evaluation on the Kaggle Fake and Real News benchmark achieves an overall accuracy of 94.5%, with balanced precision and recall across both classes, confirming the viability of ensemble learning for combating online misinformation at scale.
Keywords—fake news detection; random forest; TF-IDF; natural language processing; Streamlit; misinformation; ensemble learning.
| 12 |
Author(s):
Shraddha Suresh Kale.
Page No : 1-3
|
Sentiment Analysis of Women’s Crime News Tweets Using NLP Techniques
Abstract
Crimes against women remain a significant social issue, and social media platforms like Twitter provide real-time insights into public opinion and emotional responses. This research focuses on analyzing sentiments expressed in tweets related to women’s crime news using Natural Language Processing (NLP) techniques. The dataset is collected from Kaggle and includes tweets related to harassment, domestic violence, and gender-based crimes. The data is preprocessed using techniques such as tokenization, stop word removal, and text cleaning. A rule-based sentiment analysis approach is applied to classify tweets into positive, negative, and neutral categories. The results indicate that the majority of tweets express negative sentiment, reflecting public concern, fear, and anger regarding women’s safety. This study highlights the importance of sentiment analysis in understanding public perception and supports policymakers and organizations in improving safety measures.
| 13 |
Author(s):
Dhanushraj G.
Page No : 1-3
|
EazyStore: Design and Implementation of a Secure Full-Stack E-Commerce Web Application
Abstract
The rapid growth of online commerce demands e-commerce platforms that are secure, scalable, and user-friendly. This paper presents EazyStore, a full-stack web application built using Spring Boot and React, integrating JWT-based authentication, BCrypt password hashing, role-based access control, and Stripe payment processing. The system supports user registration, product browsing, cart management, secure checkout, and admin order handling. A modular RESTful API architecture ensures scalability and maintainability. Experimental validation confirms secure authentication and successful end-to-end transactions. EazyStore serves as a practical reference for modern secure web application development.
| 14 |
Author(s):
Sumeet Chaudhari.
Page No : 1-3
|
A User-Centric and Scalable Tour and Travel Web Application for Digital Business Growth
Abstract
Many small businesses face difficulty in moving to digital platforms. The travel and tourism
industry is one of the areas which could benefit from utilizing digital transformation to improve
both customer reach as well as the efficiency of providing services. This research paper outlines
both the design and development of a new user centered and scalable web application for tour and
travel companies. This system will allow small business owners to handle all aspects of their
business including managing customer's inquiries and bookings via a single web based interface.
The application has been built using HTML, CSS, and JavaScript on the front end and has Firebase
for managing authentication (signing up) and databases, while EmailJS has also been implemented
to provide email confirmation of bookings and inquiries. With the newly developed application,
users have the capability to sign up, sign in, browse through travel packages, and make reservations
respectively in a fast and efficient manner. The reservations are stored in an encrypted format and
can be retrieved in real time by business owners.
This research paper provides a concise and functional application for small business owners that
have a formalized structure supporting the digitalization of their operations. As a result, the user
experience is enhanced, manual operations are reduced and overall business efficiency is markedly
increased. This proposed solution is also scalable and contains the capability of additional
modifications such as payment systems and administrative dashboards to be added in the future.
| 15 |
Author(s):
Keyur Padmane .
Page No : 1-3
|
Students Emotion Analysis And Prediction Using Raspberry Pi
Abstract
Student Emotions Analysis and Prediction using Raspberry Pi is an innovative embedded system designed to monitor and forecast students’ emotional states in real-time educational settings. By integrating affordable hardware like the Raspberry Pi with computer vision techniques, the system captures facial expressions to identify emotions such as happiness, stress, boredom, or frustration, enabling proactive interventions to enhance learning outcomes
| 16 |
Author(s):
Varun Shashikant Naik.
Page No : 1-3
|
Survey on Automated Interview Systems Based on AI Technologies
Abstract
AI-based mock interview systems integrate multiple technologies—natural language processing, speech analytics, and computer vision—to create realistic and adaptive training environments for job seekers. These systems simulate various interview types, including behavioral, situational, and technical formats, offering structured, unbiased, and repeatable practice. By analyzing verbal, vocal, and visual cues, they provide holistic feedback that enhances communication clarity, confidence, and readiness. Recent advancements in multimodal analytics and remote hiring trends have accelerated their development and adoption. This survey examines the technological foundations, data management challenges, fairness and transparency concerns, and emerging directions for personalized AI coaching. It highlights ongoing efforts to make these systems more supportive, accurate, and ethically responsible.
Keywords — AI-based Mock Interviews, Natural Language Processing, Speech Analytics, Computer Vision, Human-AI Interaction, Fairness, Personalization, Interview Simulation, Multimodal Systems, Automated Feedback.
| 17 |
Author(s):
Aditya Patil.
Page No : 1-3
|
VISUAL ML
Abstract
VisualML is an interactive web application designed to simplify the learning of Machine Learning concepts. The platform integrates visual simulations, quizzes, and user performance tracking to enhance understanding and engagement.
Users can explore different ML topics such as Regression, Classification, Clustering, and Neural Networks through intuitive interfaces and dynamic visualizations. The system also provides quizzes with instant feedback to evaluate user understanding.
The project is deployed using Firebase, enabling real-time authentication and hosting. The combination of visualization and interactivity makes VisualML an effective tool for beginners in Machine Learning.
Key Words: Machine Learning, Web Application, Gamification, Firebase, Education, Interactive Learning.
| 18 |
Author(s):
S Hari Prasad.
Page No : 1-4
|
The Study Of Digital Marketing And It’s Impact On Consumer Satisfaction
Abstract
In today’s digital age, marketing has transitioned from conventional techniques to online
platforms, making digital marketing a vital asset for businesses. This study aims to explore
the effect of digital marketing on consumer satisfaction. It investigates how various factors,
such as accessibility, tailored communication, and prompt interactions through digital
channels, enhance the overall customer experience. Additionally, the study addresses
challenges like data privacy concerns and the prevalence of misleading information online,
which can undermine consumer trust. Despite these challenges, the research indicates that
digital marketing has a significant positive influence on customer satisfaction. When
implemented effectively, it enables businesses to foster stronger relationships with
consumers, boost engagement, and promote long-term loyalty.
| 19 |
Author(s):
T Sriram.
Page No : 1-4
|
THE IMPACT OF TOURISM ON LOCAL ECONOMIC DEVELOPMENT
Abstract
This research examines the diverse effects of tourism on local economic
development, emphasising both its advantages and drawbacks. Tourism acts as a
major catalyst for economic expansion, supporting job creation, revenue
streams, and improvements to infrastructure in many areas. The arrival of
tourists boosts local businesses—ranging from hospitality and retail to
transportation and entertainment—thereby increasing employment and
encouraging entrepreneurship. For numerous communities, tourism is a crucial
economic support, especially in regions with few alternative industries. Yet, the
connection between tourism and local economic growth is complicated and
brings certain challenges. The seasonal nature of tourism may result in
economic fluctuations, with periods of high activity offering temporary jobs and
quieter times leading to job losses. Furthermore, an overdependence on tourism
can leave local economies exposed to external disruptions, such as recessions or
worldwide crises, as seen during the COVID-19 pandemic. Tourism can also
contribute to environmental harm, as greater visitor numbers and resource use
put pressure on local ecosystems. Therefore, adopting sustainable practices is
essential to lessen negative impacts while protecting natural and cultural
resources. Involving local communities in tourism planning and development
ensures that the benefits are distributed fairly. This research highlights the need
for sustainable tourism approaches that harmonise economic advancement with
environmental protection and community welfare. By understanding the
complex relationship between tourism and local economic development,
stakeholders can design strategies that optimise positive outcomes and address
obstacles, building resilient and sustainable communities in a rapidly evolving
world. Ultimately, grasping these factors is key to leveraging tourism for
constructive economic growth.
| 20 |
Author(s):
Karthik.
Page No : 1-4
|
A STUDY ON CHALLENGES FACED BY FIRST – TIME ENTREPRENEURS IN ESTABLISHING NEW BUSINESS VENTURES.
Abstract
Entrepreneurship plays an important role in economic development by creating employment opportunities and encouraging innovation. However, individuals who start a business for the first time often face several difficulties in the early stages of their business journey. The main objective of this study is to identify the common challenges experienced by first-time entrepreneurs and understand the factors that affect their ability to start and manage a business. The study is based on primary data collected through a structured questionnaire. The responses were gathered from individuals who are interested in starting a business. The findings indicate that financial problems, lack of experience, and strong market competition are some of the major challenges faced by first-time entrepreneurs. The study highlights the importance of proper guidance, training, and financial support to help new entrepreneurs overcome these difficulties.
| 21 |
Author(s):
Lakshmana.P.
Page No : 1-4
|
IMPACT OF ARTIFICIAL INTELLIGENCE IN MARKETING STRATEGIES
Abstract
Artificial Intelligence (AI) is transforming modern marketing strategies by enabling businesses to deliver personalized, data-driven, and efficient customer experiences. This study aims to analyze the impact of AI technologies such as machine learning, predictive analytics, and chatbots on marketing practices. The research follows a descriptive methodology using secondary data sources including journals, industry reports, and case studies. The findings indicate that AI enhances customer engagement, improves decision-making, and increases return on investment (ROI) through targeted campaigns and automation. However, challenges such as data privacy concerns and implementation costs remain significant. The study concludes that AI is a powerful tool for modern marketers, but its successful adoption depends on ethical usage and strategic integration into business processes
| 22 |
Author(s):
Vaidoorya .
Page No : 1-4
|
A study on work place stress, organizational commitment and employee productivity
Abstract
Employee productivity is influenced by several factors which may be internal or external to the organization. These factors can have either a positive or negative effect on employee performance depending on the nature of the organization and its working conditions. In a typical workplace, both physical and behavioural factors play an important role in shaping employees’ abilities, attitudes, and productivity. Therefore, a healthy work environment is essential for improving employee engagement, performance, and overall organizational effectiveness. The workplace environment has become a critical factor in determining employee productivity, especially in today’s highly competitive business environment. Organizations are increasingly recognizing that employees are valuable assets whose performance directly affects organizational sustainability. Since employees spend a significant portion of their time at work, the conditions of the workplace can influence their mental, emotional, and physical wellbeing. A positive work environment improves concentration, motivation, and behaviour, which ultimately enhances productivity. Conversely, an unfavourable work environment may create stress, reduce morale, and negatively affect performance. The work environment includes everything surrounding employees while they perform their duties. It consists of both physical and psychological components that influence employees’ work attitudes and productivity levels. Physical workplace factors such as office layout, cleanliness, ventilation, lighting, noise levels, temperature, equipment design, and safety measures significantly affect employee comfort and efficiency. A well-designed and safe workplace promotes better interaction, teamwork, and employee satisfaction, which leads to improved productivity. On the other hand, poor workplace design and unsafe conditions may cause stress, discomfort, and underutilization of employee capabilities. Employee efficiency plays a crucial role in the success and long-term sustainability of any organization. The work environment is an important factor that can significantly influence employee productivity both positively and negatively. Progressive organizations recognize the value of their employees and therefore focus on creating a supportive and healthy work environment, as employees spend a major part of their time performing job-related activities. However, an unfavourable work environment may lead to job stress and reduced performance. The findings indicate a positive relationship between workplace environment and employee commitment. The study concludes that improving workplace conditions can enhance employee commitment and performance. These findings provide useful insights for academic institutions to improve their work environment and support effective employee performance
| 23 |
Author(s):
Praveen Kumar P.
Page No : 1-4
|
A STUDY ON WORKING CAPITAL MANAGEMENT OF MAINI MATERIALS MOVEMENT PVT LTD AT BANGALORE
Abstract
This study focuses on analysing the working capital management practices of Maini Materials Movement Pvt Ltd, Bangalore. Working capital plays a crucial role in ensuring the smooth functioning of day-to-day business operations and maintaining liquidity and profitability. The research evaluates how efficiently the company manages its current assets and current liabilities over a period of five years. The study is based on secondary data collected from financial statements and annual reports. Various tools such as ratio analysis and trend analysis are used to assess the financial performance and working capital efficiency of the organization. The findings highlight the relationship between liquidity and profitability and emphasize the importance of maintaining an optimal level of working capital. Both excessive and inadequate working capital can negatively affect business performance. The study concludes that effective working capital management enhances operational efficiency, reduces financial risk, and improves profitability. It also provides suggestions for improving cash flow, inventory control, and credit management practices. This research is useful for financial managers, investors, and academicians in understanding the importance of working capital in industrial organizations.
| 24 |
Author(s):
Reshma Madan Bhakta.
Page No : 1-4
|
INFLUENCE OF SELF-POSITION MERCHANDISE IN INDIA’S FMCG SECTOR A Comprehensive Research Study
Abstract
Self-position merchandise represents a critical yet understudied dimension of retail strategy in the Indian FMCG (Fast-Moving Consumer Goods) sector. This research paper examines the influence of product positioning, shelf placement, and consumer-driven merchandising strategies on purchasing decisions, brand visibility, and market competitiveness within India's dynamic retail environment. Through a comprehensive analysis of empirical data, case studies, and theoretical frameworks, this study demonstrates that strategic self-position merchandising directly correlates with increased market share, consumer engagement, and retail efficiency.
| 25 |
Author(s):
G.VIGNESHWARAN.
Page No : 1-4
|
Governance of Employees in Cooperative Societies: A Study on Appointment, Recruitment Bureau, Common Cadre and Disciplinary Control in Tamil Nadu
Abstract
This paper examines the governance of employees in Cooperative Societies with special reference to the Tamil Nadu Co-operative Societies Act, 1983 and the relevant rules. It focuses on the appointment of paid officers and servants, the role of recruitment bureaus, the common cadre system, and the disciplinary powers of the Registrar. The study explains how proper recruitment and service conditions help improve efficiency and accountability. It also highlighted the importance of suspension and removal provisions in maintaining discipline. Overall, the paper shows that effective employee management is essential for the smooth functioning and development of Cooperative institutions.
| 26 |
Author(s):
Rakshaben Virani.
Page No : 1-4
|
A CASE STUDY ON TALENT ACQUISITION IN RETAIL AND E COMMERCE INDUSTRY
Abstract
This study focuses on analyzing talent acquisition practices in the retail and e-commerce industry, with special emphasis on the role of digital tools and social media in recruitment. The rapid growth of the industry, driven by technological advancements and changing consumer behavior, has increased the demand for skilled professionals across various domains such as IT, logistics, marketing, and customer service.
The research adopts a descriptive and analytical approach using both primary and secondary data. Primary data is collected through structured questionnaires with HR professionals and employees, while secondary data is gathered from journals, reports, and case studies.
The study examines recruitment strategies, effectiveness of hiring channels, impact of technology, and challenges such as high employee turnover and skill shortages. The findings highlight that digital platforms, employer branding, and AI-based recruitment tools significantly improve hiring efficiency and candidate quality. However, issues like talent scarcity and retention continue to affect organizational performance.
The study concludes with recommendations to enhance recruitment practices through technology adoption, skill-based hiring, and improved employer branding.
| 27 |
Author(s):
SUJAN P, SWAROOP P,S REVANTH, TEERTHAK.
Page No : 1-4
|
AI driven multimodal interactive humanoid for childcare with compendious analysis with machine learning
Abstract
The AI driven multimodal interactive humanoid for
childcare with compendious analysis using machine learning is
an innovative Smart Parenting Care Robot designed to ensure
child safety, health, and productivity. Combining hardware and
intelligent software, it features a central processor, DC/servo
motors for movement and meal delivery, a camera for monitoring,
and sensors to track heart rate and temperature. Advanced AI
analyzes visual data to detect excessive screen time, issuing voice
alerts, while speech recognition enables educational interactions.
Emergency sensors notify parents via mobile alerts during falls
or health irregularities, ensuring timely response. The robot
automates essential arenting tasks like meal delivery, and real
time health monitoring, reducing parental stress and promoting
a structured, engaging environment for children. Scalable and in
teractive, it bridges technology and caregiving, making it ideal for
modern parenting. This comprehensive solution supports child
development and safety even in a parent’s absence, integrating
real-time monitoring, learning support, and emergency response
into one smart system.
| 28 |
Author(s):
SAFIKUL SK, Research Scholar, YBN University, Ranchi; Dr. Gauri Shankar Yadav, Assistant Professor, Department of Arts, Humanities and Social Sciences, Sikkim Global Technical University. .
Page No : 1-4
|
The Social and Economic Status of Indian Muslim Women in the Contemporary Context: Intersectionality, Structural Inequalities, and Pathways to Empowerment
Abstract
The social and economic status of Indian Muslim women remains a crucial concern within the broader discourse of gender justice, minority rights, and inclusive development. Situated at the intersection of gender, religion, class, and region, Muslim women experience layered marginalization that shapes their access to education, employment, healthcare, and political participation. While constitutional guarantees and policy interventions have attempted to address these disparities, structural inequalities persist. Drawing on recent empirical studies (2020–2025), government reports, and theoretical frameworks such as intersectionality and feminist institutionalism, this paper critically examines the contemporary condition of Indian Muslim women. The study argues that although incremental improvements have occurred in education and visibility, economic participation and substantive empowerment remain constrained by systemic discrimination, informalization of labor, and socio-cultural norms. The paper concludes with a comprehensive policy framework aimed at achieving inclusive and equitable empowerment.
| 29 |
Author(s):
N.Rajesh Babu.
Page No : 1-4
|
IOT-ENABLED REAL TIME MONITORING AND CONTROL OF INDUCTION MOTOR
Abstract
Induction motors have become the most used motors in industrial applications in recent years. However, despite their high reliability, operating conditions can expose induction motors to various fault conditions. Implementing condition monitoring is crucial to prevent unexpected motor shutdowns and enhance the motor's productivity and lifespan. One effective approach to monitoring is leveraging the Internet of Things (IoT), which enables real-time data collection, data visualization
through graphs, and the development of web services and connections. The objective of this research is to monitor real time data and detect electrical faults in a three-phase induction motor. The monitored electrical parameters include voltage,
current, and temperature. The system will identify faults such as overcurrent, overvoltage, undervoltage, undercurrent, and overtemperature. Once a fault is detected, the system will isolate the motor to prevent further damage. Additionally, the system will utilize the Internet of Things to measure and display electrical parameters, including voltage, current, and temperature, along with their corresponding graphs, through a mobile application. Data transmission between the system and the mobile application will occur between 7-8 a.m. and 9-10
p.m. The mobile application will access a history log, allowing users to review past data. Furthermore, the application will compile information about motor faults that occurred on specific days and times, which will be displayed in the error logs.
| 30 |
Author(s):
Mansi Bansod, Chaitali Shirpurkar, Mrudula Shete, Anushka Kuthemathe, Mrs. Y.A.Nafde.
Page No : 1-4
|
Design of Reconfigurable Antenna for Wireless Application
Abstract
The design of reconfigurable antennas has gained significant importance in modern wireless communication systems due to the increasing demand for multi-band, multi-standard, and adaptive functionalities. This paper presents the design and analysis of a reconfigurable antenna suitable for wireless applications. The proposed antenna is capable of dynamically altering its operating frequency, radiation pattern, or polarization using switching elements such as PIN diodes or MEMS switches. A compact microstrip patch structure is employed to ensure low profile, lightweight, and ease of fabrication. The antenna is designed and simulated using advanced electromagnetic simulation tools, and its performance is evaluated in terms of return loss, bandwidth, gain, and radiation characteristics. The results demonstrate that the antenna effectively operates over multiple frequency bands, making it suitable for applications such as Wi-Fi, Bluetooth, and mobile communication systems. The proposed design enhances spectrum efficiency and provides flexibility, making it a promising solution for next-generation wireless devices.
| 31 |
Author(s):
A. Vamsi Krishna.
Page No : 1-4
|
Smart grid integrated wireless EV charging system using machine learning
Abstract
The rapid growth of electric vehicles (EVs) demands intelligent, efficient, and sustainable charging infrastructure integrated with smart grid technologies. This project presents a Smart Grid Integrated EV Charging System with Machine Learning and Power Flow Analysis, designed to enable wireless EV charging, real-time power monitoring, and intelligent decision-making. The proposed system uses wireless power transmission coils for contactless charging, where IR sensors detect vehicle presence and activate relays to initiate charging. Electrical parameters such as voltage and current are continuously monitored using sensors and transmitted to a Python-based platform for analysis. A Random Forest machine learning algorithm is employed to analyse sensor data and predict charging behaviour, efficiency, and abnormal conditions. The system also integrates IoT functionality using NodeMCU, allowing real-time data upload to cloud platforms for remote monitoring. A solar-powered charging station charges a battery to support green energy utilisation, while a robotic vehicle chassis represents the EV, controlled via Bluetooth. LED indicators display charging status and system states. The proposed solution demonstrates an intelligent, scalable, and eco-friendly EV charging system suitable for future smart grid applications
| 32 |
Author(s):
Vaishnavi Desai.
Page No : 1-4
|
A Real-Time Streaming Hybrid Ensemble SOAR Framework Using Kafka Streaming for Autonomous Cyber Anomaly Detection
Abstract
Modern networks generate large volumes of security logs, making it difficult for analysts to detect and respond to threats in time. In this work, we design and evaluate a real-time streaming SOAR framework that combines a Kafka-based ingestion pipeline with a hybrid ensemble consisting of XG Boost, Random Forest, and an Isolation Forest model. The system processes events as they arrive, assigns risk levels through a weighted consensus score, and triggers automated responses when high- severity activity is detected. Although our evaluation uses simulated enterprise traffic, the architecture reflects real deployment constraints and is implemented in a containerized setup to measure latency and through- put. Experimental results show that the ensemble achieves high detection accuracy while maintaining sub-second processing latency under moder- ate load. We also include ablation studies to understand the contribution of each model. The findings highlight the potential of lightweight ensemble techniques and streaming pipelines for building practical, automated cyber defense systems.
| 33 |
Author(s):
Sahaya Gladwin JS.
Page No : 1-4
|
Attendify: Smart Attendance System
Abstract
Attendance monitoring is an essential process in educational institutions, but traditional attendance methods
such as manual roll calls, registers, RFID, and biometric systems are time-consuming and prone to errors. This paper
proposes Attendify, a contactless attendance monitoring system that uses face recognition technology to automate the
attendance process. The system captures student faces using a camera and identifies them through deep learning-based
facial recognition models. Once a student is recognized, attendance is automatically recorded with a timestamp and
stored in a centralized database. The system also provides attendance reports and notifications to staff and parents to
ensure transparency. By eliminating manual effort and proxy attendance, the system improves accuracy, efficiency, and
classroom management.
| 34 |
Author(s):
Namanshoo Pardikar.
Page No : 1-4
|
Habit dicussion forum with file sharing
Abstract
n today’s dynamic and fast-paced world, individuals are constantly striving to improve their lifestyle and develop positive habits. However, maintaining consistency and motivation while building new habits often becomes difficult without external support and encouragement.
| 35 |
Author(s):
Sumedh Gajbhiye.
Page No : 1-4
|
The Challenge of Code-Switching: Sentiment Analysis in Multilingual Social Media Data
Abstract
This an important study as it tackles the issue of parsing huge amounts of informal, unstructured user-generated content on X and Instagram. The proposed work designs a solid pipeline for polarity classification by using supervised machine learning framework using Sentiment140 and Hinglish_Sentiment datasets. The project includes novel preprocessing and cleaning methods for social media-specific, shorthand slangs, and text that is limited by a certain number of characters. Early results show that sentiment detection can be done with a high degree of accuracy, confirmed our belief that this type of automated analysis is precise and scalable; an essential component in real-time market research, public policy tracking and helping clients navigate community mood.
| 36 |
Author(s):
Tanaya Bure.
Page No : 1-4
|
AI Based Smart Resume Builder
Abstract
The goal of resume screening is to identify the top applicants for a position and to inform users of their resume score and areas for improvement. The literature on existing approaches has been analysed, and it has been discovered that the traditional systems like manual screening may result in false assumptions and the wasting of human potential, but they lack robustness in terms of processing, accuracy and efficiency. To acquire accurate results, software must use machine learning and natural language processing techniques to match and rate the candidates in real-time by ranking their resumes. The input would be the applicant’s resumes and output would be a ranked candidate’s resumes and output would be a ranked candidate’s resume list on the admin side and suggestions on the user side. Instantaneous real-time output results are acquired by employing natural language processing techniques. In the proposed system authors used Cosine similarity, TF-IDF and Mong Techniques of NLP for string matching. According to experimental finding, this system has a text parsing accuracy of 85% and a ranking accuracy of 92%.
| 37 |
Author(s):
Dnyaneshwar Gumalwad.
Page No : 1-4
|
Crowdsourced Civic Issue Reporting and Resolution System
Abstract
Urban municipalities across rapidly growing cities face persistent challenges in managing civic infrastructure complaints efficiently. Conventional grievance mechanisms — telephone helplines, physical offices, and paper-based registers — are characterised by opacity, delayed response cycles, and a near-total absence of citizen feedback, leaving defects such as potholes, waterlogging, broken streetlights, and uncollected waste unresolved for extended periods. This paper presents CivicFix, a crowdsourced civic issue reporting and resolution system developed under Smart India Hackathon 2025 (Problem Statement SIH25031) for the Government of Jharkhand. The platform empowers citizens to submit geo-tagged, media-rich complaints through a Progressive Web Application (PWA) supporting multilingual voice input via the Web Speech API. A Convolutional Neural Network (CNN) engine automatically categorises incoming reports, which are routed through a four-tier administrative hierarchy — Super Admin, City Admin, Ward Admin, and Field Worker — governed by a Service Level Agreement (SLA) auto-escalation engine. Real-time status notifications are delivered through Socket.io, Twilio SMS, and email, while every administrative action is immutably recorded on a blockchain audit trail to ensure tamper-proof accountability. The system is built on a cloud-native stack comprising Next.js 14, Node.js/Express, MongoDB Atlas, Redis, and Cloudinary, deployed across Vercel and Railway. Pilot evaluation conducted across two ward offices demonstrated a 66.7 percent reduction in average issue resolution time (17.4 days to 5.8 days), a 2.3-fold increase in complaint submission volume, a 95.8 percent drop in administrative assignment latency (46 hours to 1.9 hours), and a mean citizen satisfaction score of 4.1 out of 5.0. These results confirm CivicFix as a scalable, accountable, and citizen-centric model for transforming urban governance in developing cities.
| 38 |
Author(s):
Tambe Supriya Ravindra.
Page No : 1-5
|
A Review on Application of Machine Learning in Fused Deposition Modeling
Abstract
Fused deposition modeling (FDM) is a example of additive manufac¬turing (AM) which uses joining of materials in a layer by layer based methodology to manufacture a component, FDM can build complicated part geometries and intri¬cacies in least time when compared to traditional manufacturing methods. It doesn’t require any fixed process plan, special looting and involve very little human intervention. FDM parts offer superb heat and chemical resisting behavior and shows excellent strength-to-weight ratios. Despite of all these advantages, FDM parts are facing inconsistency in part properties, reliability and accuracy. To meet the consislent quality standard and process reliability real time monitoring of FDM process is requisite. Research trend shows that machine learning (ML) aided models are proficient computational technology which enable AM processes to achieve the high quality standard, product consistency and optimized process response. In this direction, integration of machine learning (ML) and FDM process is relatively less explored. Though the researches are limited in number, a review based study on the application of ML in FDM process is lacking which can help the researchers to decide their areas of research. Authors got motivated to bridge this gap by pre-senting a state of art showing the applicability of ML methods in FDM process.
| 39 |
Author(s):
Gopal.C , Venkatesan. S , Venkateswaran .B Department of Information Technology, M.A.M. College of Engineering and Technology, Trichy, India R. Revathy, Assistant Professor, Department of Information Technology, M.A.M. College of Engineering and Technology, Trichy, India.
Page No : 1-5
|
SMART WATER MANAGEMENT SYSTEM IN IOT
Abstract
A Water quality monitoring system can aid in preserving the environment, ensuring the security of nearby water sources, and fostering economic growth in rural areas. As a result, this will help to develop a system here that employs Internet of Things and Machine Learning to monitor the quality of water. This paper discusses the characteristics of water to let us know whether it is fit for human consumption or not. The sensors dipped in water samples acquired from wells, lakes, rivers, ponds, or other places are used to inform the development of an effective model made up of TDS, pH and turbidity sensors. The data will be delivered from the sensors as soon as they are received to the IDE, where it will then be sent to the cloud server. The model effectively accounts for test tables, where 1 indicates the water is fit for drinking and 0 indicates the water is not. The values were classified differently using Machine Learning models like SVM, RF and XG Boost method. Training data is pre-processed before being fetched from the cloud. Over that data, machine learning models like Support Vector Machine, Random Forest & Extreme Gradient Boost has been implemented. The maximum accuracy of 95.12% was observed using XG Boost. After testing, we will be able to determine whether the water is fit for drinking using the binary indicators of 1 and 0, where 1 indicates the water is fit for drinking and 0 indicates the water is not .
| 40 |
Author(s):
Sanjai R.
Page No : 1-5
|
Customer Perception Towards Digital Marketing: Role of Personalization and Al
Abstract
In the modern business environment, digital marketing has become a powerful tool for influencing customer perception and buying behaviour. The integration of Artificial Intelligence (AI) and personalization has significantly transformed how businesses interact with customers. This study focuses on understanding customer perception towards digital marketing strategies. The research highlights how personalized marketing and AI-driven tools enhance customer engagement, satisfaction, and decision-making. Based on primary data collected from 150 respondents, the study reveals that customers prefer relevant, customized content and value digital platforms for convenience and interaction. However, challenges such as irrelevant targeting and misinformation still affect perception. The study concludes that effective use of AI_and_personalization_can_improve_customer_trust_and_brand_loyalty.
| 41 |
Author(s):
Aravinthsami S.
Page No : 1-5
|
Financial Planning and Budgeting: A Strategic Approach to Organizational Success
Abstract
Financial planning and budgeting are essential components of effective organizational management,
enabling firms to allocate resources efficiently and achieve long-term objectives. This study examines
the role of financial planning, controlling, and budgeting as strategic tools for organizational success.
It highlights how systematic financial planning ensures proper forecasting, while budgeting provides
a framework for resource allocation and performance evaluation. Controlling mechanisms further
ensure that actual performance aligns with planned objectives.
The research adopts a qualitative approach, reviewing existing literature and organizational practices
to understand how these financial tools contribute to decision-making and operational efficiency. The
study emphasizes that organizations with robust financial planning and budgeting systems are better
equipped to manage uncertainties, reduce financial risks, and enhance profitability.
Additionally, the paper explores the integration of financial control systems with modern strategic
management practices. The findings suggest that a well-structured financial framework not only
improves accountability but also supports sustainable growth. The study concludes that financial
planning and budgeting are not merely accounting practices but strategic necessities that influence
organizational performance and competitiveness in a dynamic business environment.
| 42 |
Author(s):
Mouleeshwaran .G , Suyam Praba . R.
Page No : 1-5
|
The Hidden Cost of Poor Hiring Decisions: A Human Capital Analytics Approach
Abstract
In today’s competitive business environment, effective hiring plays a crucial role in determining organizational success and long-term sustainability. Poor hiring decisions often lead to significant hidden costs that extend beyond direct expenses such as salaries and recruitment fees. These hidden costs include reduced employee productivity, increased turnover, additional training and onboarding expenses, negative impact on team morale, and potential loss of customer satisfaction. This study aims to identify and analyze the hidden costs associated with poor hiring decisions . The research is based on both primary data collected through structured questionnaires from HR managers, employees, and team leaders, and secondary data obtained from journals, books, and industry reports. A descriptive research design and mixed research approach have been adopted to understand both quantitative and qualitative aspects of the issue. The findings indicate that factors such as inadequate screening processes, lack of structured interviews, time pressure in recruitment, and poor evaluation of cultural fit contribute significantly to hiring inefficiencies. The study concludes that implementing structured recruitment strategies, data-driven hiring practices, and effective onboarding programs can minimize hidden costs and enhance overall organizational performance and employee satisfaction.
| 43 |
Author(s):
Logeswari P .
Page No : 1-5
|
EFFECT OF ONLINE ADVERTISING ON USER BUYING BEHAVIOUR
Abstract
Online advertising has become a dominant promotional tool due to the rapid growth of the internet and digital technologies. Businesses increasingly rely on online platforms to influence consumer buying behaviour. The purpose of this study is to examine the effect of online advertising on users’ buying behaviour, focusing on factors such as awareness, attitude, and purchase intention. The study adopts a descriptive research design and uses both primary and secondary data. Primary data were collected through a structured questionnaire from a sample of 100 respondents, while secondary data were obtained from journals, websites, and previous research studies. Statistical tools such as percentage analysis and graphical representation were used for data analysis. The findings reveal that online advertisements significantly influence consumer purchasing decisions, especially through social media ads, search engine ads, and personalized content. The study concludes that effective online advertising
positively impacts user buying behaviour by enhancing brand awareness, trust, and purchase intention. The results highlight the importance of strategic digital marketing for businesses in the competitive online environment.
| 44 |
Author(s):
G.VIGNESHWARAN.
Page No : 1-5
|
Contribution of Primary Agricultural Cooperative Credit Societies (PACCS) to Women Entrepreneurship through Self-Help Groups in Tamil Nadu
Abstract
Women entrepreneurship plays a crucial role in improving rural livelihoods and promoting inclusive economic growth. In Tamil Nadu, Primary Agricultural Cooperative Credit Societies (PACCS) and Self-Help Groups (SHGs) have emerged as critical institutional mechanisms for supporting women’s economic activities. This study examines PACCS's contribution to women's entrepreneurship through SHGs in Tamil Nadu. The study is based on secondary data collected from Tamil Nadu Government Annual Reports and relevant cooperative and development literature. The analysis highlights PACCS's role in providing timely, affordable credit, strengthening SHG linkages, and supporting income-generating activities among women members. The study also compares different operational approaches adopted by PACCS, namely the Target Approach and the Umbrella Approach, and assesses their impact on women’s entrepreneurial development. The findings indicate that while credit support has expanded significantly over the years, approaches that combine financial assistance with guidance, training, and institutional support are more effective in promoting sustainable women's enterprises. Overall, the PACCS–SHG linkage contributes positively to financial inclusion, women’s economic empowerment, and rural development in Tamil Nadu.
| 45 |
Author(s):
Thennarasu E.
Page No : 1-5
|
A Study on Social Media Influence Analysis for Influencer Marketing Infinity Software Solutions Private Limited
Abstract
This study examines the influence of social media on consumer behavior through influencer marketing, with specific reference to Infinity Software Solutions Private Limited. In the digital era, social media platforms have become powerful tools for marketing, enabling organizations to reach a wider audience and engage with customers more effectively. Influencer marketing, in particular, has emerged as a key strategy where individuals with significant online presence promote products and services to their followers.
The research focuses on analyzing how influencer marketing impacts brand awareness, customer engagement, and purchasing decisions. A descriptive research design is adopted, utilizing both primary and secondary data. Primary data were collected through surveys and interactions with social media users, while secondary data were obtained from company records, online sources, and existing literature. The study evaluates the effectiveness of various social media platforms, types of influencers, and content strategies used by the company.
The findings indicate that influencer marketing significantly enhances brand visibility and consumer trust, leading to increased customer engagement and higher conversion rates. However, challenges such as authenticity, influencer credibility, and measurement of return on investment were also identified. The study concludes that a well-planned influencer marketing strategy can provide a competitive advantage and contribute to business growth. Recommendations are provided to improve campaign effectiveness and ensure sustainable digital marketing practices.
| 46 |
Author(s):
Syed Abdullah, Dr. Shivaprasad.
Page No : 1-5
|
Role of Forensic Accounting in Detecting Financial Fraud: A Comparative Analysis
Abstract
Financial fraud continues to undermine institutional integrity, investor confidence, and broader economic stability. As fraudulent schemes grow more sophisticated — leveraging digital platforms, complex ownership structures, and regulatory loopholes — traditional auditing methods prove increasingly insufficient for timely detection. This study investigates the role of forensic accounting as a superior alternative framework for detecting financial fraud and compares its effectiveness against conventional audit processes.
| 47 |
Author(s):
Sanskrati Bhawsar.
Page No : 1-5
|
HR Innovations and Educational Excellence: “A Study on HR Innovations in Education Sector ’’
Abstract
The education sector is experiencing rapid transformation due to globalization, technological advancements, and increasing competition. In this context, Human Resource (HR) innovations have become essential in enhancing employee performance and achieving institutional excellence. This study examines the impact of modern HR practices on employee performance within the education sector. A quantitative research approach was adopted, and primary data was collected through structured questionnaires distributed among respondents. The research focuses on key HR innovations such as employee engagement strategies, flexible work arrangements, continuous training and development, and data-driven HR decision-making. The findings indicate a strong positive relationship between HR innovations and employee productivity, job satisfaction, and organizational effectiveness. The study concludes that the successful implementation of innovative HR practices, supported by leadership and strategic planning, plays a crucial role in achieving educational excellence and sustaining institutional growth.
| 48 |
Author(s):
DHINESH BHARATHI K .
Page No : 1-5
|
ENHANCING FIREWORKS SALES DURING FESTIVALS THROUGH ARTIFICIAL INTELLIGENCE-BASED MARKETING STRATEGIES
Abstract
Festivals such as Diwali play a significant role in driving fireworks sales in India. However, increasing competition, changing consumer preferences, and unpredictable demand create challenges for traditional marketing approaches. This study examines how Artificial Intelligence (AI)-based marketing strategies can enhance fireworks sales during festival seasons. The research adopts a descriptive methodology using secondary data from journals, industry reports, and online resources.
| 49 |
Author(s):
RAJESH.S, Mrs Naveena M.
Page No : 1-5
|
A STUDY OF CUSTOMER RELATIONSHIP MANAGEMENT AT RASI FEEDS PRIVATE LIMITED
Abstract
Customer Relationship Management (CRM) refers to the strategies, technologies, and practices used by organizations to manage and analyze interactions with customers throughout the customer lifecycle. The main objective of CRM is to improve customer service relationships, assist in customer retention, and drive sales growth.
CRM focuses on understanding customer needs, maintaining long-term relationships, and providing value-added services. In the modern competitive business environment, companies must focus on customer satisfaction to survive and grow.
Organizations use CRM systems to collect and analyze customer data such as purchasing behavior, preferences, feedback, and complaints. By understanding customer expectations, companies can develop strategies that enhance loyalty and trust.
CRM is widely used in industries such as retail, banking, manufacturing, and agriculturerelated businesses like poultry and feed manufacturing companies. For companies like Rasi Feeds Private Limited, CRM plays an important role in maintaining strong relationships with farmers, distributors, and dealers.
| 50 |
Author(s):
Dr Prasanna Kumar , Punith R , Rajshekar P N ,Rakshith Gowda K P, Sudeepraj V C.
Page No : 1-5
|
A WAR FIELD ROVER
Abstract
The War Field Spying Robot is an advanced robotic system designed for military surveillance and reconnaissance in hostile environments. The robot integrates the ESP32 microcontroller, ESP32-CAM for live video streaming, and various sensors for environmental monitoring. It is equipped with a gas sensor for smoke detection, a fire sensor for fire detection, and an ultrasonic sensor for obstacle detection and avoidance. The robot is controlled via a mobile-based voice application connected through Bluetooth (HC-05). In case of fire or smoke detection, the system sends real-time alerts to border officers using the Telegram service. This project demonstrates the successful integration of hardware and software components to create a versatile and efficient spying robot for military applications
| 51 |
Author(s):
Prof. Puneshkumar Tembhare, Ms. Bhagyashri Donagrawar,Ms. Harsha Vishwakarma,Ms. Sneha Waghmare,Ms. Srushti Pilley,Ms. Ranjana Bhendarkar.
Page No : 1-5
|
SMART NUTRITION MONITORING SYSTEM
Abstract
Maintaining a balanced and nutritious diet has become increasingly challenging due to busy lifestyles, irregular eating habits, and lack of proper guidance. NutriPlan is an intelligent nutrition planning system that generates personalized meal recommendations using artificial intelligence. The system considers user-specific parameters such as age, weight, height, dietary preferences, and health conditions to provide customized diet plans. In addition, it integrates external factors like weather conditions to enhance the relevance and practicality of recommendations. By combining artificial intelligence with cloud-based backend services, NutriPlan delivers dynamic and scalable solutions for nutrition planning. This approach reduces manual effort, improves user engagement, and promotes healthier lifestyle choices through data-driven decision-making.
| 52 |
Author(s):
Noor Ul Haq.
Page No : 1-5
|
SECURE FILE SHARING SYSTEM ON CLOUD
Abstract
Cloud computing is widely used for data storage and sharing due to its scalability and cost-effectiveness, but it introduces security risks such as unauthorized access and data breaches. This research proposes a secure cloud-based file sharing system that ensures data confidentiality, integrity, and controlled access. The system uses AES encryption for securing file content and RSA for secure key exchange, allowing only authorized users to access data. It also incorporates multi-factor authentication, role-based access control, and secure key management. Additionally, SHA-256 hashing is used to verify data integrity. The proposed solution enhances security in cloud environments while maintaining efficiency and usability.
| 53 |
Author(s):
Adarsh Raj .
Page No : 1-5
|
SecureVault: A Privacy-Centric Encrypted Storage Application for Android
Abstract
Abstract—Abstract—Smartphones have increasingly become the primary platforms for storing sensitive personal and professional data. However, many existing storage solutions do not provide sufficient privacy protection. Cloud-based services offer convenience, but they introduce risks such as unauthorized access and exposure to third-party data handling. Likewise, several on-device vault applications rely on weak or non-standard encryption methods, making them susceptible to compromise using common forensic tools.To address these challenges, this work presents SecureVault, an Android application designed with strong cryptographic foundations and layered authentication mechanisms. The application secures all stored data, including images, videos, audio, and documents, using AES-256 encryption. In addition, it supports both PIN-based and biometric authentication for enhanced access control. By operating entirely on-device without reliance on cloud services, SecureVault minimizes potential security vulnerabilities and significantly reduces the overall attack surface. Our evaluation on real Android hardware showed that the system achieves strong security guarantees while keeping encryption overhead low enough for practical daily use. We also outline planned extensions, including optional encrypted cloud backup, AI-driven anomaly detection, and intrusion lockout mechanisms.
Keywords—AES-256 encryption, Android security, secure local storage, biometric authentication, data privacy, mobile application security
| 54 |
Author(s):
N.Rajesh Babu.
Page No : 1-5
|
SMART EV CHARGING STATION ON GRID GREEN POWER AND WIRELESS CHARGING
Abstract
The increasing demand for electric vehicles (EVs) has created the need for efficient, reliable, and eco-friendly charging infrastructure. Traditional charging systems rely heavily on grid electricity generated from fossil fuels, which contributes to environmental pollution and energy shortages. The proposed system, Smart EV Charging Station on Grid Green Power and Wireless Charging, aims to integrate renewable energy sources such as solar power with grid supply to provide sustainable and uninterrupted charging facilities.
This project utilizes green energy generation through solar panels and stores energy in batteries for continuous operation. The system also incorporates wireless charging technology, enabling EVs to charge without physical cable connections. A smart control unit manages energy flow between solar panels, battery storage, and grid supply, ensuring efficient power utilization.
The system enhances energy efficiency, reduces carbon emissions, and supports the transition toward clean transportation. It also improves user convenience and safety by enabling automated charging and monitoring. This project demonstrates the feasibility of combining renewable energy and wireless technology for modern EV infrastructure.
| 55 |
Author(s):
Maheshwaran.M.
Page No : 1-5
|
Lursen Finance: A Machine Learning-Based Smart Trading Recommendation Application for Informed Investment Decisions.
Abstract
Lursen Finance is a machine learning–based smart trading recommendation application that analyzes historical and real-time market data, including prices, volumes, and technical indicators, to identify patterns and trends. It addresses challenges in manual trading such as emotional bias, incomplete information, and time constraints by providing actionable insights instead of raw data. The system uses preprocessing, feature extraction (moving averages, RSI, MACD), and predictive models like Random Forest and LSTM, along with sentiment analysis for enhanced forecasting. It generates buy, sell, or hold recommendations with risk assessment through a scalable and modular pipeline. Experimental results indicate improved prediction accuracy, reduced risk exposure, and consistent performance across different market conditions.
| 56 |
Author(s):
A. Vamsi Krishna.
Page No : 1-5
|
SOLAR POWERED SMART MULTIPURPOSE AGRICULTURE ROBOT
Abstract
Multipurpose agricultural robots are becoming increasingly important in modern farming due to labor shortages and the need
for improved efficiency and productivity. Traditional farming
methods require significant manual effort and time, which can
be reduced through automation. This project focuses on the design and implementation of a multipurpose agriculture robot capable of performing six essential farming operations: spraying,
digging, cultivating, seeding, solar charging, and grass cutting.
The robot is designed to operate efficiently in various agricultural conditions while minimizing human intervention. The system integrates multiple mechanisms and control units to perform
different tasks using a single platform and utilizes electric motors, sensors, and control circuits to switch between operations
effectively. Solar charging is incorporated to provide a sustainable and energy-efficient power source, enabling longer operation time in the field. The robot enhances precision in farming
activities such as uniform seed distribution, controlled pesticide
spraying, and efficient soil preparation. Additionally, the robot
improves overall farm productivity by reducing labor costs and
increasing operational speed. The multipurpose functionality
eliminates the need for multiple machines, making it cost-effective for farmers. The system aims to support smart agriculture
practices and promote the adoption of modern technology in
farming
| 57 |
Author(s):
SriDharani A.
Page No : 1-5
|
AI- Driven Career Path Recommendation and Guidance System
Abstract
-The use of Artificial Intelligence in career
guidance has gained importance due to rapidly evolving job
market demands and the limitations of traditional counselling
systems, which often provide generic and non-personalised
recommendations. This paper presents an AI-Driven Career
Guidance and Development Platform that integrates key
functionalities such as resume building, interview preparation,
skill analysis, and career recommendation into a unified
system. The platform is developed using Next.js for the
frontend, Clerk for authentication, Prisma ORM with NeonDB
for
database management, and Inngest for handling
asynchronous background workflows. It leverages the Google
Gemini API to generate context-aware outputs, including
resume content, interview questions, and personalised career
suggestions based on user inputs such as skills, interests, and
experience. The system relies on structured data combined with
prompt-based AI generation rather than complex standalone
machine learning models, ensuring simplicity and scalability.
Performance is evaluated based on response time, relevance of
generated outputs, and user interaction efficiency. Results
indicate improved user experience, faster resume creation, and
more relevant career guidance. The proposed architecture
demonstrates how modern full-stack technologies combined
with generative AI can deliver scalable and practical career
support solutions.
| 58 |
Author(s):
Arpit Arvind tatte, Yaseer Khan , Rohan Jayant Meshram ,Krushna Ganesh Chinkure, Kapil Jadhav.
Page No : 1-5
|
AI-Driven Speed Breaker Detection and Alert System
Abstract
The AI-Driven Speed Breaker Detection and
Alert System aims to improve road safety by detecting road
hazards such as speed breakers, potholes, and damaged roads
surfaces in real time. The system uses a camera-based
approach combined with the YOLOv8 deep learning model
to analyze live video frames. The model identifies road
anomalies under various lighting and environmental
conditions and provides timely alerts to the driver. The
system generates both visual and audio warnings, helping to
reduce accidents, prevent sudden braking, and enhance
driving comfort. This approach demonstrates the effective
use of computer vision and artificial intelligence in
intelligent transportation systems.
| 59 |
Author(s):
Poorav Chaurasia.
Page No : 1-5
|
An AI-Driven System for Automated Question Paper Generation from Curriculum Documents
Abstract
The process of designing question papers in academic institutions is often manual, time consuming, and prone to inconsistencies in terms of difficulty, coverage, and structure. With the growing demand for scalable and standardized assessment systems, there is a need for intelligent automation in exam generation. This paper presents PaperPilot, an AI-driven system that automates the generation of question papers directly from syllabus documents in PDF format. The proposed system leverages Natural Language Processing (NLP) techniques to extract, preprocess, and structure syllabus content, followed by the use of Large Language Models (LLMs) to generate contextually relevant questions. PaperPilot allows users to configure parameters such as difficulty level, question types, marks distribution, and exam patterns, enabling flexible and customized paper creation. In addition, the system provides AI-based insights, including topic importance analysis and predicted question trends, along with an integrated student assistant for real-time doubt resolution and concept explanation.
| 60 |
Author(s):
B Arjun, Mr. Mohammed Saif N.
Page No : 1-5
|
A STUDY ON MARINE SUPPLY CHAIN STRUCTURE.
Abstract
The marine supply chain can be understood as a coordinated system of activities that ensures the smooth movement of goods from producers to end consumers across international markets. This process begins at the point of origin, where goods are prepared, packaged, and made ready for transportation. From there, the cargo is transported to the port using suitable inland transport systems such as trucks or railways. Once the cargo reaches the port, it must undergo a series of documentation and customs clearance procedures before it is approved for shipment. After completing these formalities, the cargo is loaded onto vessels and transported to its destination. such as logistics providers, port authorities, customs officials, and shipping companies coordinate with each other. Even minor disruptions in communication, documentation errors, or infrastructure limitations can result in delays, increased operational costs, and inefficiencies within the supply chain.
| 61 |
Author(s):
D. Vijaya Lakshmi.
Page No : 1-5
|
CHARGING OF ELECTRIC VEHICLE FOR LOW-POWER APPLICATIONS WITH IMPROVED POWER FACTOR CORRECTION
Abstract
This paper presents a cohesive power electronics system for charging the battery in low-power EV applications with improved power factor correction. The system employs a diode bridge rectifier (DBR) to convert AC to DC efficiently. An interleaved boost converter (IBC) is utilized, incorporating a dual loop control technique to effectively manage the DC link voltage and ensure power factor correction. Small signal modeling is conducted, leading to the development of transfer functions that streamline controller design, ensuring robust and stable operation. The interleaved boost converter is linked to a buck converter for battery charging, operating in constant current and constant voltage (CC-CV) modes to govern the charging process. MATLAB simulations are carried out to validate the proposed model. The results confirm that the proposed charging system successfully achieves its objectives, including power factor correction, reduction of Total Harmonic Distortion (THD) in input current, and Constant Current Constant Voltage (CC-CV) charging of the battery.
| 62 |
Author(s):
Atharva Shinde, Vinit Shetti, Ashutosh Jadhav, Nishank Shetty and Vijaypal Yadav.
Page No : 1-5
|
Automated Attendance System Using Facial Recognition System
Abstract
Traditional manual attendance methods in educational institutions are time consuming, prone to human error and susceptible to fradualent activities such as proxy attendance. This paper presents an Automated Biometric Attendance System designed to streamline the attendance process using facial recognition technology. The proposed system utilizes a Raspberry pi 4 interfaced with a high - definition USB camera to capture real-time video frames of students entering the classroom. By employing the official Picamera2 library for hardware-optimized capture and Dlib for deep-learning-based feature extraction, the system detects facial landmarks and encodes them into 128-dimensional embeddings. The backend integrates a local SQLite database and a Flask web server to map timestamps to a predefined lecture schedule. This contactless approach eliminates the need for manual name-calling, saving valuable lecture time while ensuring the attendance data is accurate and automatically timestamped. In our testing the system worked accurately in most cases especially in proper lighting conditions, although some challenges were observed in low light. offering a cost effective and secure alternative to RFID or fingerprint-based systems. This project helped us understand practical challenges in real-time face recognition system
| 63 |
Author(s):
Mathanraj.s.
Page No : 1-5
|
DIGITAL MARKETING IN MODERN BUSINESS STRATEGIES, IMPACT, AND CHALLENGES
Abstract
Digital marketing has emerged as a powerful tool in modern business, transforming how organizations communicate with customers and promote their products and services. The purpose of this study is to examine the role, effectiveness, and challenges of digital marketing in today’s competitive business environment. The study adopts a descriptive research methodology based on secondary data collected from journals, books, research articles, and credible online sources. The analysis highlights major digital marketing channels such as search engine optimization, social media marketing, content marketing, email marketing, and online advertising. The findings reveal that digital marketing enables businesses to reach a wider audience at a lower cost, improve customer engagement, and measure performance accurately using data analytics. However, issues such as intense competition, changing algorithms, and data privacy concerns pose significant challenges. The study concludes that digital marketing is no longer optional but essential for business growth and sustainability. Organizations that effectively adopt digital marketing strategies and adapt to technological changes can gain a strong competitive advantage in the modern business landscape.
| 64 |
Author(s):
Ajitha SM , Aakash Raj A , Dinesh Kumar T , Manikandan P.
Page No : 1-5
|
Smart Farm Price Advisor: A Machine Learning Approach to Crop Price Prediction and Farmer Decision Support
Abstract
ndian farmers, the ones with small farms
have a big problem. They do not know how
much money they will make from their
crops. This is because the prices of crops can
change suddenly and the people who buy the
crops decide the prices. To help the farmers
we made something called the Smart Farm
Price Advisor. This is a tool that farmers can
use on the internet. It uses computer
programs to tell the farmers how much
money they can make from their crops in the
coming weeks or months. We used a lot of
information to make this tool work. We
looked at what happened to seven crops in
fifteen areas of Tamil Nadu. We thought
about things like how rain there was, what
time of year it was where the crops were
grown and what kind of crops they were.
Our computer program is very good at guessing
the prices of crops. It is right at 72.93 percent of
the time. We used a lot of computer programs to
make the Smart Farm Price Advisor work. We
used Python and Flask to make predictions
about crop prices.
Used an Angular 17 to make the interface,
which's what the farmers see when they use the
tool. We used MySQL to store all the
information. The Indian farmers can use the
Smart Farm Price Advisor to get a lot of
information. They can find out how much
money they might make from their crops. They
can find out if they will make a profit or a loss.
They can even get advice on whether they
should sell their crops or wait.
| 65 |
Author(s):
Kalukuracha Guna vardhan.
Page No : 1-6
|
SpendRight: A Unified Framework for E-Commerce Decision Support via Price Volatility Tracking and NLP-based Sentiment Analysis
Abstract
Online shopping platforms use dynamic pricing, which makes it difficult for users to determine whether a product is truly worth buying. Many users rely only on discounts without analyzing product quality and reviews, leading to impulsive buying and poor decisions.
SpendRight is an AI-based system that combines price volatility tracking with sentiment analysis using Natural Language Processing. The system collects product data, analyzes user reviews, and evaluates price trends to generate a “Worth-It” score. This helps users make informed purchasing decisions by considering both price and product quality.
The proposed system improves decision-making accuracy and reduces impulsive buying behavior, making online shopping more reliable and efficient.
| 66 |
Author(s):
Mr. Karthick Kumar S, Abith SV, Harish V, Rajeshwari R, Santhosh S.
Page No : 1-6
|
AI – DRIVEN PUBLIC HEALTH CHATBOT
Abstract
Healthcare systems often face challenges such as high patient load, limited medical professionals, and lack of access to reliable health information. This paper presents an AI-Driven Public Health Chatbot designed to provide instant healthcare assistance and improve public health awareness. The system uses Natural Language Processing (NLP) and Machine Learning techniques to understand user queries and generate relevant responses. The chatbot provides guidance on symptoms, preventive measures, hygiene practices, and general health information. It also supports features like BMI calculation, health tracking, and medicine suggestions. The system ensures 24/7 availability and reduces dependency on healthcare professionals for basic queries. The proposed solution is scalable, cost-effective, and suitable for modern digital healthcare systems.
| 67 |
Author(s):
Md Saad Bin Rizvi.
Page No : 1-6
|
Cybersecurity Threat Detection Using Machine Learning: A Comparative Analysis of Gradient Boosting Approaches on Network Intrusion Data
Abstract
Due to emerging attacks, signature-based threat detection systems are no longer efficient for current attack strategies. In this research paper, we will propose an end-to-end machine learning solution based on two state-of-the-art gradient boosting methods (XGBoost & LightGBM), which can classify network connection into five categories of threat attacks. This study uses the dataset provided by the KDD Cup 1999 challenge, which consists of 494,021 network connection samples labeled with threats. To train an accurate model, we implement a strict data preprocessing procedure, which involves eliminating duplicates, performing one-hot encoding, class label aggregation, and applying min-max normalization. Experimentation reveals that our model achieves the maximum accuracy level of 99.2% using XGBoost and 99.0% using LightGBM, compared to the baseline models of Decision Tree (97.8%), Naive Bayes (88.4%), K-Nearest Neighbors (96.1%), and Random Forest (98.5%). It turns out that our model works great when identifying high-frequency attacks (Denial-of-Service, Probe) but does not perform well enough for detecting minority attack classes (R2L, U2R).
| 68 |
Author(s):
Mohini kontamwar, Aastha Mohale, Pratiksha Ashtankar, Sanjana Kapgate, Aditya Sarkate.
Page No : 1-6
|
IoT Based Smart Saline Drip Monitoring System Using Load Cell
Abstract
Intravenous (IV) drip therapy is one of the most common clinical procedures performed in healthcare facilities worldwide. Manual monitoring of IV drip bags by nursing staff is resource-intensive, error-prone, and may lead to critical patient safety incidents when drip bags run dry undetected. This paper presents MediDrip, a low-cost, real-time IoT-based intravenous drip monitoring system that employs a high-precision HX711-interfaced load cell to continuously measure the remaining saline volume by weight. The proposed system integrates an ESP32 microcontroller with the Blynk IoT cloud platform to enable wireless data transmission, remote monitoring via a web dashboard, and configurable multi-threshold alert generation. A 1.3-inch OLED display, tri-color LED indicator array (green, yellow, red), and an audible buzzer provide local real-time feedback. Experimental validation was conducted using 100 mL saline bags across 30 test cycles, demonstrating a mean absolute weight error of 1.8 g and percentage level accuracy of ±2.3%. The system successfully triggered remote alerts and local alarms within 1.2 seconds of threshold breach. MediDrip offers a cost-effective, scalable, and clinically practical solution for automated IV drip monitoring, with potential for multi-bed deployment in resource-constrained healthcare environments.
| 69 |
Author(s):
Anamika Yadav.
Page No : 1-6
|
A Review Study of Cognitive Load in Website and Mobile Application User Interface Design
Abstract
The aim of the present paper is to evaluate the cognitive load, specifically in relation to websites and applications, with special emphasis on improving the user experience. It has been noticed that, as the complexity of digital platforms increases, the cognitive load of the users has also increased, as there is a lot of information involved. Cognitive load, as defined, refers to the mental load required to process the information. Cognitive load plays a vital role in the interaction of the user with the digital platforms. The cognitive load of the user, specifically in relation to the user interface and the user experience, has been discussed in detail, based on the cognitive load theory, which states that the cognitive load of the user can be of three types: intrinsic, extraneous, and germane cognitive load. In this context, the intrinsic cognitive load refers to the complexity of the task, the extraneous cognitive load refers to the load of the poor design of the digital platforms, and the germane cognitive load refers to the mental load required to learn. The role of the various aspects of the interaction of the user with the digital platforms, specifically the user experience, has been discussed, as it plays a vital role in influencing the cognitive load, which ultimately leads to confusion, frustration, and frustration of the user, based on the studies available on the topic.
| 70 |
Author(s):
Sheik Mohammed Aman, Dr. Shivaprasad G.
Page No : 1-6
|
Liquidity Preference and Its Behavioural Cost on Long-Term Investment Outcomes
Abstract
This study looks at how young people in Bangalore, like those between 22 and 35, tend to hold onto too much cash instead of investing it long term, and how that choice ends up costing them in terms of better returns later on. I am drawing from some theories here, you know, the Keynesian one on liquidity preference, and Tobins portfolio balance idea, plus the prospect theory from Kahneman and Tversky, and that behavioral portfolio thing by Shefrin and Statman. All of these help explain the psychological stuff pushing people toward this, things like feeling anxious about money, hating losses more than usual, and just perceiving risk in a way that makes them play it safe.
The main drivers seem to be financial anxiety, loss aversion, and how they see risks, which lead to putting money in the wrong places, not enough in growth assets or whatever. We used a survey back in March 2026 with 128 people from that age group, structured questions to test five hypotheses. Ran chi square tests, some simple linear regressions, multiple ones too, and a one way ANOVA to check things out.
| 71 |
Author(s):
Mr. Alston Sudarshan.
Page No : 1-6
|
BEHAVIORAL BIASES IN RETAIL INVESTING: A Comparative Empirical Study of Advised versus Self-Directed Retail Investors in the Indian Financial Market
Abstract
This study aims to investigate the presence of behavioral biases among retail investors of Indian financial market by comparing between advised and self-directed investors. Using data from 135 investors, the study focuses on five behavioral biases namely overconfidence, herding, loss aversion, anchoring and disposition effect by comparing using various statistical tools such as t-tests and regression analysis. It was found that, advised investors suffer less from behavioral biases in general than self-directed investors and difference in disposition effect was statistically significant. The results also suggest that more investment experience leads to increased bias and overconfidence in the investors may be the cause.
| 72 |
Author(s):
Sanjay Krishna B.
Page No : 1-6
|
Automated Extraction of Meeting Summaries and Action Items Using Whisper and LLMs
Abstract
Meetings generate large volumes of unstructured conversational data, making manual documentation time-consuming and error-prone. Although platforms such as Google Meet provide automated note-taking and summarization features, these capabilities are typically limited to their own ecosystems and offer restricted customization and export flexibility. This paper presents a platform-independent automated meeting documentation system that converts spoken conversations into structured summaries and actionable insights. The system utilizes Whisper for accurate speech-to-text transcription and Large Language Models (LLMs) deployed locally using Ollama for extracting key discussion points, decisions, and action items. Unlike existing solutions, the proposed system supports multiple input sources including recordings, transcripts, and meetings from platforms such as Microsoft Teams and Zoom.
| 73 |
Author(s):
Jery J.S, Ayushmaan D.J. Neog, Pavan Karthikeya, Ranveer Kakati, Yashwanth Rayalu G.V..
Page No : 1-6
|
AirTouch: A TOF Sensor-Based Touchless Human-Computer Interaction System
Abstract
This paper presents AirTouch, a touchless human-computer interaction (HCI) system that leverages Time-of-Flight (TOF) range sensors to detect mid-air finger gestures and translate them into precise click and hover events on connected devices. The growing reliance on shared digital interfaces has underscored the need for hygienic, surface-independent interaction modalities. AirTouch addresses this gap by fusing TOF-based depth sensing with real-time gesture recognition algorithms—including Kalman filtering, histogram-based noise reduction, and machine learning classification—to achieve sub-5 ms latency with millimetre-level spatial accuracy. The proposed architecture encompasses sensor fusion, microcontroller-driven signal processing, and cross-platform communication interfaces (USB, Bluetooth, Wi-Fi). Comparative analysis of proximity sensing technologies reveals that TOF sensors offer the optimal balance between accuracy (~1 mm/cm), latency (1–5 ms), power consumption (20–200 mA), and cost (₹700–₹10,500). AirTouch targets deployment in healthcare, retail, education, and public infrastructure environments, with implications for hygiene enhancement, accessibility, and novel interaction paradigms. The system was prototyped using an Arduino Uno R3, infrared proximity sensors, and a Python/TensorFlow Lite/Flutter software stack running on Windows 11.
| 74 |
Author(s):
Rohit C Hegde, Dr. Shivaprasad G..
Page No : 1-6
|
Taxation and Compliance Challenges Arising from Exchange Rate Fluctuations in Indian Import-Export Businesses
Abstract
The fluctuating exchange rates create multiple layers of taxes and regulations for Indian exporters and importers. Fluctuations between the INR and USD, EUR, and GBP lead to cascading impacts on GST, Customs, FEMA, Income Tax, and Ind AS 21. The research covers 2017-2024, during which time periods include the COVID-19 outbreak, Russia-Ukraine war, and the US Federal Reserve's monetary tightening cycle. Five different compliance areas have been studied: assessment of value in computing the customs duty, GST considerations on foreign currency transactions, income tax provisions on foreign exchange gains/losses, FEMA considerations on remittance and hedging, and Ind AS 21 considerations on tax-accounting differences. The study concludes that SMEs face significant compliance costs, hedging contracts add further complications in terms of taxes, and regulatory inconsistencies between CBIC, CBDT, and RBI create litigation risks. Five recommended policies have been made.
| 75 |
Author(s):
Danish Choudhary, Dr. Renuka S, Professor of Practice.
Page No : 1-6
|
Finfluencers and Retail Investment Behaviour: Credibility, Cognitive Bias, and Regulatory Implications
Abstract
The proliferation of financial influencers—commonly termed finfluencers—on social media platforms has created a new paradigm in how retail investors access, evaluate, and act upon financial information. Drawing on a structured survey of 51 active retail investors in an emerging-market context, this study examines the mechanisms through which finfluencer content shapes individual investment decisions, with particular attention to perceived credibility, parasocial trust, cognitive-bias activation (fear of missing out, herding, overconfidence, and anchoring), and the moderating role of financial literacy. Anchored in Behavioural Finance Theory (Kahneman & Tversky, 1979) and Kelman's (1958) Social Influence framework, the findings reveal that finfluencer exposure significantly amplifies cognitive biases and increases trading frequency, even among respondents with advanced academic qualifications. Notably, 64.2% of participants favour mandatory professional certification for financial influencers, signalling public readiness for tighter oversight. The study contributes empirical evidence to an underexplored intersection of digital communication and retail finance in developing economies, and offers actionable implications for regulators, financial institutions, and platform designers.
| 76 |
Author(s):
Kavya Shree Raksha P .
Page No : 1-6
|
Market Trends and Portfolio Diversification: A Sector-Based Analysis
Abstract
Investment decisions in the stock market require a careful balance between risk and return, making portfolio diversification an essential strategy for investors. In the Indian context, sector-based diversification has become increasingly relevant as different industries respond differently to economic conditions and market trends. This study evaluates the effectiveness of sectoral diversification by analysing five major sectors Information Technology (IT), FMCG, Banking, Automobiles, and Pharmaceuticals against the NIFTY 100 index over a period of 20 years (2005–2024).
The study incorporates both sectoral indices and individual stock analysis to provide a comprehensive understanding of market performance. Financial metrics such as CAGR, Beta, Sharpe Ratio, and Value at Risk (VaR) are used to assess growth, volatility, and risk-adjusted returns. Statistical techniques including correlation analysis, forecasting are applied to examine sectoral relationships and predict trends.
The findings indicate that FMCG and Pharmaceutical sectors offer stability with lower risk, while Banking and Automobile sectors exhibit higher volatility and growth potential. The IT sector provides a balanced risk-return profile. At the stock level, HDFC Bank, TCS, and Sun Pharma consistently outperform both sectoral indices and the broader market.
The study concludes that combining sectoral diversification with effective stock selection improves portfolio performance and supports long-term wealth creation.
Keywords: Portfolio Diversification, Sectoral Analysis, Risk-Return, NIFTY 100, Indian Stock Market
| 77 |
Author(s):
R.Sravani.
Page No : 1-6
|
STSMC-Based Analysis and ADRC Design for an LCC-LCC Wireless Power Transfer System
Abstract
This project presents that Wireless Power Transfer (WPT) systems using resonant topologies, such as the LCC–LCC configuration, offer high efficiency and stable performance for applications including electric vehicles and automated systems. However, variations in coupling and load changes introduce control challenges that affect output voltage stability. This project presents the design and evaluation of an Active Disturbance Rejection Control (ADRC) strategy enhanced with a Super-Twisting Sliding Mode Controller (STSMC) for an LCC–LCC WPT system. The proposed controller aims to improve dynamic response, reduce overshoot, and enhance robustness against disturbances and parameter uncertainties. A comparison with a conventional Proportional-Integral (PI) controller is performed to assess settling time, stability, and voltage regulation under varying load conditions. the STSMC-based ADRC controller achieves faster transient response and superior steady-state voltage regulation compared to the PI controller, demonstrating its effectiveness for reliable and efficient WPT applications.
| 78 |
Author(s):
SUDHARSAN S.
Page No : 1-6
|
ShopNest: Design and Development of a Scalable Web-Based E-Commerce Platform Using Modern Web Technologies
Abstract
The proliferation of digital technology has fundamentally restructured commercial landscapes worldwide, catalysing a paradigm shift from conventional brick-and-mortar retail to dynamic online marketplaces. This paper presents the design and development of ShopNest, a full-stack web-based e-commerce platform engineered to offer an intuitive, secure, and scalable online shopping experience. The system provides a comprehensive suite of features including user authentication, multi-category product browsing, real-time cart management, structured order processing, and an administrative control panel for inventory and transaction supervision. The frontend layer is constructed with HTML5, CSS3, and JavaScript to deliver a responsive and accessible interface, while the backend is implemented in Python to orchestrate server-side business logic. MySQL serves as the relational database management system, ensuring transactional integrity and efficient data retrieval. An architectural analysis demonstrates that the modular design of ShopNest facilitates ease of maintenance and scalability. Performance evaluation confirms satisfactory response times and system reliability under standard operating conditions. The study further identifies limitations of extant e-commerce solutions, articulates the research gaps addressed by ShopNest, and outlines prospective enhancements encompassing AI-driven recommendations, mobile application development, real-time order tracking, and reinforced security protocols.
| 79 |
Author(s):
DR. S. ADILINISSA.
Page No : 1-6
|
A Study on The Influence of Buy Now, Pay Later Services on Impulse Buying Behaviour among College Students in Chennai
Abstract
Buy Now, Pay Later (BNPL) services have emerged as a popular financial tool, transforming consumer purchasing patterns, especially among young consumers. The present study examines the influence of BNPL services on impulse buying behaviour among college students in Chennai, focusing on factors such as ease of payment, availability of credit, promotional offers, and peer influence. The research adopts a descriptive research design and is based on primary data collected from 150 respondents using a structured questionnaire through a Simple random sampling technique. The study aims to analyze the level of awareness, usage patterns, and behavioural responses of students towards BNPL services. The collected data were analyzed using Percentage analysis, Chi-Square test, Analysis of Variance (ANOVA), and Regression analysis to identify significant relationships and the impact of BNPL usage on impulse buying behaviour across different demographic variables. The findings reveal that BNPL services significantly influence impulse buying behaviour, encouraging unplanned purchases due to deferred payment options and attractive offers. Regression results indicate a positive relationship between BNPL usage and impulse buying tendencies among students. The study concludes that while BNPL services enhance purchasing convenience, they also contribute to increased impulsive spending, highlighting the need for greater financial awareness and responsible usage among young consumers.
Keywords:
Buy Now, Pay Later (BNPL), College Students, Consumer Behaviour, Digital Payments, Regression Analysis.
| 80 |
Author(s):
L.JYOTHI,AKASH JV,SARVESHA R,PRASANNA V.
Page No : 1-6
|
Real-Time Scam Script Generator To Train Call Center Defenses
Abstract
The increasing sophistication of social engineering attacks and phone-based fraud schemes has created significant security challenges within modern call center operations. Despite routine training programs, many organizations remain vulnerable due to static learning modules that fail to replicate the evolving tactics used by real-world scammers. The problem arises from limited scenario variability, lack of real-time adaptability, and absence of measurable performance assessment, which often leaves agents underprepared to detect complex scam attempts involving impersonation, urgency tactics, and psychological manipulation.
This paper presents the design and implementation of a Real-Time Scam Script Generator, an intelligent simulation-based training framework developed to enhance defensive preparedness. The proposed system employs scam pattern databases, behavioral modeling techniques, and rule-based conversational logic to dynamically generate realistic fraud scenarios. It supports multiple scam categories including phishing, impersonation fraud, and financial exploitation schemes. A dedicated performance evaluation module measures metrics such as detection accuracy, response time, protocol compliance, and false positive rate to assess agent effectiveness.
Experimental results indicate improved threat recognition capability and faster decision-making compared to traditional training methods. The proposed solution provides a scalable and automated approach to strengthen cybersecurity resilience and reduce fraud susceptibility in call center environments.
| 81 |
Author(s):
Umesh Joge, Utkarsh Sahare, Vipul Navghare, Vrushbh Agalawe, Yash Umak.
Page No : 1-6
|
Leveraging Large Language Model For Code Understanding Using Offline Mode
Abstract
Understanding unfamiliar source code is a
significant challenge for developers,
particularly in the absence of proper
documentation and reliable resources. While
Large Language Models (LLMs) have shown
strong capabilities in code generation, their
application in code comprehension remains
limited and often dependent on internet
connectivity.
This paper presents an offline LLM-based
assistant integrated within an Integrated
Development Environment (IDE) to provide
context-aware explanations, API details, and
example usage directly from highlighted code.
The proposed system eliminates the need for
manual prompt engineering and reduces
context switching by offering real-time
assistance inside the development workflow.
The system was evaluated through a user study
comparing traditional web search and online AI
tools. Experimental results demonstrate that the
proposed approach reduces task completion
time by up to 50% and improves code
understanding accuracy to 88%. Additionally,
user satisfaction was significantly higher due to
offline availability and improved workflow
continuity.
The findings indicate that integrating offline
LLMs within IDEs can enhance developer
productivity, ensure data privacy, and provide
efficient code comprehension support in low-
connectivity environments.
| 82 |
Author(s):
Nishant patel.
Page No : 1-6
|
CalmConnect -A Mental Health Awareness Project Using MERN Stack and Data Science
Abstract
In this project, I worked on building CalmConnect, a web-based platform focused on mental health awareness and support. The idea was to create a space where users can not only interact with a chatbot but also join communities, attend events, and manage wellness activities like yoga or trainer sessions.
| 83 |
Author(s):
MD Shameem.
Page No : 1-6
|
Flying Squirrel Search Optimization Based Maximum Power Point Tracking for Photovoltaic Systems
Abstract
This paper presents a Flying Squirrel Search Optimization (FSSO) based Maximum Power Point Tracking (MPPT) technique for photovoltaic (PV) systems operating under varying environmental and partial shading conditions. The nonlinear characteristics of PV systems and the presence of multiple local maxima under shading make conventional MPPT methods less effective. The proposed method utilizes a bio-inspired FSSO algorithm to optimize the duty cycle of a DC–DC boost converter, considering the PV output power as the objective function. The algorithm effectively balances global exploration and local exploitation, enabling accurate and fast tracking of the global maximum power point (GMPP). The performance of the proposed method is evaluated using MATLAB/Simulink under different irradiance and temperature conditions. Simulation results demonstrate that the FSSO-based MPPT technique achieves faster convergence, reduced steady-state oscillations, and improved tracking efficiency compared to conventional methods such as Perturb and Observe (P&O) and Particle Swarm Optimization (PSO). Overall, the proposed approach enhances the efficiency, stability, and reliability of photovoltaic systems, making it suitable for real-time renewable energy applications.
Key Words: Flying Squirrel Search Optimization (FSSO), MPPT, Photovoltaic System, Partial Shading, Boost Converter, MATLAB/Simulink.
| 84 |
Author(s):
Srinithi. S.
Page No : 1-6
|
Phishing detection in facial recognition using AACO enhanced GLCM features in machine learning
Abstract
Phishing attacks exploiting facial recognition pose rising threats by mimicking legitimate biometric authentication. This study introduces a novel phishing detection framework using Artificial Aquarium Colony Optimization (AACO)-enhanced Gray Level Co-occurrence Matrix (GLCM) features combined with machine learning classifiers. AACO optimizes GLCM texture parameters for robust facial image analysis, capturing subtle phishing artifacts like synthetic distortions. Evaluated on custom and public datasets, the approach achieves 97.2% accuracy and outperforms standard GLCM-SVM by 12%, with low false positives in real-time scenarios. It offers a scalable solution for securing face-based systems.
| 85 |
Author(s):
Vijayalakshmi T.
Page No : 1-6
|
Hybrid Graph Neural Network for Scalable Network Intrusion Detection
Abstract
Network intrusion detection systems (NIDS) face scalability challenges with growing network traffic and complex attack patterns. This paper proposes a hybrid graph neural network (HGNN) that combines graph convolutional networks (GCN) with recurrent layers for efficient feature extraction and temporal modeling. By representing network flows as dynamic graphs, HGNN captures spatial dependencies and sequential behaviors, enabling real-time anomaly detection on large-scale datasets. Experiments on benchmark datasets like CIC-IDS2018 demonstrate superior accuracy (97.8% F1-score) and 5x faster inference compared to traditional deep learning baselines, making it ideal for high-volume environments.
| 86 |
Author(s):
Ashish Gupta.
Page No : 1-6
|
Game Theory and Its Evolving Role in Complex Systems
Abstract
Game Theory provides a mathematical framework for analysing strategic interactions among rational agents and has found widespread applications in economics, engineering, and network science [37], [2]. In particular, Cooperative Game Theory enables the study of coalition formation and collective behaviour, which is crucial in modelling real-world systems such as social and communication networks [24], [16]. One prominent application is Community Detection, where nodes in a network form group based on shared properties or interactions [1], [5]. However, these problems are computationally complex due to the combinatorial explosion of possible coalitions [16], [35].
This paper explores the foundational principles of game theory, the role of cooperative approaches in community detection, and the computational challenges involved. Furthermore, emerging technologies such as Quantum Computing and Quantum Algorithms are discussed as potential tools to address these challenges [15], [23]. While current hardware limitations persist, ongoing algorithmic advancements demonstrate promising directions for solving complex optimization problems inherent in game-theoretic models [20].
| 87 |
Author(s):
SAILESHWARAN D , N.GAYATHRI.
Page No : 1-7
|
A STUDY ON TOTAL PRODUCTIVITY MAINTENANCE SYSTEMS IN SRD LOGISTICS
Abstract
This study examines the implementation and impact of Total Productivity Maintenance (TPM) systems at SRD Logistics India Private Limited, Salem. TPM is a proactive maintenance strategy that involves all employees in equipment upkeep to maximise operational efficiency and minimise losses. Using a descriptive research design, primary data was gathered from 130 respondents through a structured questionnaire. Statistical tools including simple percentage analysis, Chi-square test, Pearson correlation, and one-way ANOVA were applied. Key findings reveal that 64.6% of respondents are in the early stages of TPM implementation, 73.8% confirm improvement in operation and maintenance skills, and 48.5% strongly agree that TPM enhances overall equipment effectiveness (OEE). The study identifies equipment breakdown (53.1%), Just-in-Time maintenance focus (52.3%), and result-oriented goal formulation (46.2%) as dominant TPM characteristics. Chi-square analysis confirms a significant association between TPM policy orientation and improvement stage selection. ANOVA reveals a significant relationship between educational qualification and perception of TPM productivity contribution (F = 106.508, p < 0.05). The study concludes that integrating TPM fully into logistics operations—supported by training, employee coordination, and technology—is critical for achieving operational excellence and competitive advantage.
| 88 |
Author(s):
komal somnath kale.
Page No : 1-7
|
TB Care: AI-Based Tuberculosis Detection and Healthcare Assistant
Abstract
Tuberculosis (TB) is still a major infectious disease which we are
fighting at global scale and we require for it prompt and accurate
diagnosis to breaks its transmission and to improve patient results.
Presently we use traditional screening methods like sputum
microscopy and manual interpretation of Chest X-rays (CXRs)
which are very labor intensive, time consuming and also, we see
great variation between readers which in turn affects the result
especially in resource poor settings. In this work we present a full
scale deep learning based system for what we have put forward is
an automated TB detection solution also we aim to open up the AI
which is at present a “black box”. We go in to the public chest x ray
sets for preprocessing and then we use Deep Convolutional Neural
Networks (CNNs) for very strong feature extraction and
classification To solve the issue of standard AI models which are
black box in nature we introduce Explainable AI (XAI) which we
use Grad-CAM to visualized the infected areas. Also to close the
gap between what we technically diagnose and what the patient
understands we have put in a LLaMA-3 driven conversational AI
which issues out medical reports in a human friendly language and
also answers questions. We evaluate performance of the model to
prove out its reliability. This study reports our work which is to
present a transparent, intelligent and interactive tool for TB
diagnosis via the use of this platform which in turn we hope will
improve efficiency of clinical workflows
| 89 |
Author(s):
Humaid Ahmad Kidwai.
Page No : 1-7
|
A Comparative Review of Fake Review Detection Techniques Using Machine Learning and Transformer Models
Abstract
With the rapid growth of e-commerce platforms, online reviews have become a critical factor influencing consumer decisions. However, the presence of deceptive or fake reviews poses significant challenges for both users and businesses. This paper presents a comparative review of various fake review detection techniques, including traditional machine learning approaches, deep learning models, and transformer-based architectures. A detailed analysis of representative studies is conducted based on methodology, datasets, and performance metrics. The study highlights the evolution of detection techniques from feature-based models to advanced context-aware systems. Additionally, a machine learning-based approach using TF-IDF and Support Vector Machine (SVM) is discussed to demonstrate practical implementation. Key research gaps such as generalization, computational complexity, and interpretability are identified, along with potential directions for future work. The findings provide valuable insights for developing more robust and scalable fake review detection systems.
| 90 |
Author(s):
CHARUNETRA S.V.
Page No : 1-7
|
The Influence of Digital Marketing on Sales of Industrial Products
Abstract
The integration of Artificial Intelligence (AI) and digital marketing has revolutionized the modern business landscape, introducing automation, predictive analytics, and data-driven decision-making to streamline both external sales and internal operations. This study assesses the impact of varying levels of digital and AI implementation—high, medium, and low—on organizational efficiency, with a specific focus on Swan Pipes Support, an industrial B2B entity based in Madurai. By analyzing data from 300 organizations through comparative and statistical methods, the research unveils that higher technology utilization results in expedited processes, reduced recruitment and operational expenses, enhanced employee retention rates, and a more diverse workforce.
| 91 |
Author(s):
Tanaya Vikil Salunke , Vaishnavi Sudhakar Handekar , Bhumika Vikasrao Falke , Bhushan Devidas Kamdi ,Swayam madhukar Dumane , Achal Sandip nagpure , F.N.Mawale..
Page No : 1-7
|
Fraud Detection in Payment System using Genetic Algorithm
Abstract
The rapid growth of digital payment systems has significantly increased the risk of fraudulent transactions, posing serious challenges to financial institutions and users. Detecting fraud accurately and efficiently has become essential to maintain the security and reliability of online payment platforms. Traditional rule-based systems often fail to identify complex and evolving fraud patterns, creating the need for intelligent and adaptive approaches. This project presents a fraud detection system in payment environments using Genetic Algorithms (GA). Genetic Algorithms, inspired by the principles of natural evolution, are used to optimize feature selection and improve the performance of classification models. By selecting the most relevant features from large datasets, GA enhances detection accuracy while reducing computational complexity. The proposed system integrates Genetic Algorithms with machine learning techniques to identify fraudulent transactions. The methodology involves data preprocessing, feature optimization using GA, and classification using suitable models. The performance of the system is evaluated using metrics such as accuracy, precision, recall, and F1-score. The results demonstrate that the use of Genetic Algorithms significantly improves fraud detection efficiency by reducing false positives and increasing the detection rate of fraudulent activities. This approach provides a scalable and effective solution for modern payment systems, making it highly suitable for real-time fraud detection applications.
| 92 |
Author(s):
Nimish Gupta.
Page No : 1-7
|
Awareness and Empowerment: A Review of Deceptive Design and Interventions
Abstract
This paper discusses the progress the User Experience(UX) design community has made in making users aware of dark patterns and what actions it has taken to remove them. It also looks at the legal side of the conversation to see how laws are implemented to tackle this problem. We explore how these patterns affect everyone from young children to adults, and why simple awareness or higher prices do not stop them from working. The review looks at the shift toward active empowerment, such as new technical tools that let users block deceptive designs themselves. It also looks at how mild tricks allow companies to avoid a negative reputation while still manipulating users. Finally, we discuss how internal company goals drive these designs and why we need a legal and a digital system where fairness is built into the design from the start to protect people from these manipulative tactics including the new, hyper-personalized artificial intelligent(AI) traps.
| 93 |
Author(s):
Z. Ananth Angel.
Page No : 1-7
|
Hybrid Convolutional Neural Network with Global Token Mixer for Medical Imaging
Abstract
Medical image classification is a critical component in computer-aided diagnosis, yet existing deep learning models often struggle with generalization across diverse imaging modalities. This paper proposes a Hybrid Convolutional Neural Network (HybridCNN) integrated with a Global Token Mixing mechanism to address both local and global feature extraction challenges. The model is trained on the full MedMNIST dataset, enabling exposure to a wide range of medical imaging types including X-rays, histopathology images, and ultrasounds. The architecture combines convolutional layers for fine-grained local feature extraction with token-based global interaction layers inspired by Vision Transformers and MLP-Mixer models. Experimental evaluation demonstrates that the proposed approach improves contextual understanding, enhances classification robustness, and supports scalable medical image analysis across heterogeneous datasets. The system is further validated through an inference pipeline capable of real-time predictions with confidence estimation.
| 94 |
Author(s):
Prithi Jessica J, Kaavya K, Tharshini A .
Page No : 1-7
|
Design and Implementation of a Web-Based SIEM Framework with Secure Authentication and Interactive Threat Visualization
Abstract
Security Information and Event Management (SIEM) systems play a crucial role in modern cybersecurity by enabling centralized log analysis, threat detection, and incident response. However, many existing SIEM solutions are complex, resource-intensive, and costly, making them less suitable for academic environments and small-scale deployments. This paper presents SIEM Secure, a lightweight, web- based SIEM framework designed to provide secure authentication, real-time log analysis, rule- based threat detection, and interactive visualization through an intuitive dashboard.
The proposed system adopts a three-layer architecture comprising data, processing, and presentation layers. It supports both local and remote log collection, where logs are parsed and normalized to extract key attributes such as timestamp, IP address, username, and event type. A rule-based detection engine is implemented to identify common security threats, including brute- force login attempts, suspicious access patterns, and unauthorized activities. Detected events are classified into severity levels and stored in structured JSON databases for efficient management.
The system integrates role-based authentication with SHA-256 password hashing, account lockout mechanisms, and audit logging to enhance security. Alerts generated during analysis are visualized using interactive charts and tables, enabling users to monitor system activity effectively. Additionally, a notification module provides real-time dashboard alerts and email notifications for critical incidents using SMTP configuration.
Experimental evaluation demonstrates that SIEM Secure effectively detects simulated attack patterns and provides meaningful insights through visualization. The proposed framework offers a practical, scalable, and user-friendly solution for security monitoring, particularly suitable for
educational purposes and small to medium-scale environments.
| 95 |
Author(s):
Malaika Matheen Khan.
Page No : 1-7
|
Social Media’s Impact on Self-Esteem in Adolescence
Abstract
This research paper investigates the role of social media in shaping the self-esteem of adolescents between the ages of thirteen and nineteen. It looks into the ways in which different social media behaviours, such as the hours spent on social media, engaging in social comparisons, seeking approval and validation, affect the individuals’ self-esteem. Data was collected though a survey questionnaire. The results of the study revealed that social media can have both positive and negative implications for the adolescent’s sense of self-esteem. On the one hand, social media allows for self expression, social interaction, and emotional support; however, at the same time, it can induce heightened dissatisfaction, negative social comparisons, and pressure to conform to idolized standards. Many in this age group become very dependent on types of self-worth gained from the number of likes received and interested comments on one’s posts. This egocentric amount of concern for their online identity can lead to increased feelings of inadequacy and insecurity, which can be psychologically damaging. Conversely, emotionally supportive online communities can trigger feelings of acceptance and importance. Based on this research, it can be inferred that the consequences of social media depend on use patterns, and the negative effects should be mitigated through practicing moderation and playing an active part in positive online communities.
| 96 |
Author(s):
Jyothi Pravallika Reddy Yannam.
Page No : 1-7
|
HYBRID MACHINE LEARNING FRAMEWORK FOR IDENTIFICATION AND DETECTION OF UNAUTHORIZED WI-FI ACCESS POINTS
Abstract
Wireless networks are increasingly being compromised by Wi-Fi access points which execute man in the middle attacks, eavesdrop on conversations as well as stealing passwords. Traditional methods of detection which involve application of fixed rules or signatures tend to miss out the new or unknown threats. To detect the unauthorized Wi-Fi access points, this research paper provides a hybrid machine learning approach to analyze behavioral traffic. A preprocessing pipeline is leakage-free and it comprises of data cleaning, removal of suspicious features, feature encoding, scaling, and feature selection which increases model reliability. XGBoost, random forest and Linear Support Vector machine are used to classify access points as safe or rogue. In order to reduce the false negatives and to enhance the accuracy of detection, the predictions of such models are used in an ensemble voting process. Evaluation is done with the AWID Wi-Fi intrusion dataset that consists of 154 traffic characteristics. The proposed architecture is very accurate and recalls high in experiments. With the help of Flask web application, trained models would be deployed to enable detection of rogue access points in real-time.
| 97 |
Author(s):
S. JIGEESHA SAI .
Page No : 1-8
|
FACT FUSION – UNIFIED AI DETECTION FOR FAKE NEWS & IMAGE MISINFORMATION
Abstract
The rapid increase of AI-generated text and manipulated images on social media platforms has raised serious concerns about the reliability of online information. Most existing fake news detection systems focus on a single modality, either text or images, which limits their ability to detect modern misinformation that often combines both. To address this, this paper proposes Fact Fusion, a multi-modal deep learning framework that integrates separate models for text and image analysis. For textual data, a pre-trained BERT-based encoder is used to generate contextual embeddings, which are further processed using a feed-forward neural network for classification. For visual data, a custom-designed Convolutional Neural Network (CNN) is employed to identify manipulated or fake images. Experimental results show that the text model achieves an accuracy of 91.3% with a weighted F1-score of 0.9256, while the image model achieves 93.8% accuracy with an F1-score of 0.9379. An additional comparison of embedding strategies demonstrates that mean pooling provides better performance than other methods. The complete system is deployed using a Streamlit-based interface, enabling real-time predictions with low latency. The proposed approach provides an efficient and scalable solution for detecting multi-modal misinformation in real-world scenarios.
| 98 |
Author(s):
Sneha Manigandan, Dr. Kiran Kumar M .
Page No : 1-8
|
Detecting Accounting Fraud in Global Corporations: An Audit-Based Analysis Using Benford’s Law
Abstract
This paper focuses on the problem of Benford Law as the effective statistical method which can help to discover the presence of accounting anomalies among large non-banking MNCs. The data used to perform the study are the initial decimal place distributions of six financial variables using 593 financial items with data retrieved through SEC 10-K filings of 20 global companies over five fiscal years (20202024) namely Revenue, Cost of Goods Sold (COGS), Operating Expenses, Total Assets, Net Income, and Accounts Receivable. These findings suggest that there are statistically significant departures of the data in terms of the distribution of Benford, achieving the chi-square value of 23.642 and the Mean Absolute Deviation (MAD) of 0.0195 highly exceed the critical value of 15.507 and 0.015, respectively. COGS and Total Assets have the most significant degrees of deviation, whereas Accounts Receivable has the least number of deviations. Sectoral analysis shows that the firms in the energy sector have the highest structural divergence; this is associated majorly with the volatility of the commodity prices. Moreover, there was also a steady increase in conformity levels in 2021-24, which can be attributed to post-pandemic regulatory changes. The research findings are that Benford Law although it is a good preliminary audit screening can never be utilized alone as evidence of fraud. When used in conjunction with more general forensic accounting methods, its usefulness improves greatly.
| 99 |
Author(s):
B Rinku, Dr. Shivaprasad G, Assistant.
Page No : 1-8
|
Robo-Advisors, Algorithmic Trading, And Their Impact On Portfolio Diversification And Herding Behavior: Evidence From The Indian Retail Investment Market
Abstract
The rapid evolution of financial technology (fintech) has brought about revolutionary changes in investment management through robo-advisors and algorithmic trading. The current research seeks to examine the effect of these technologies on portfolio diversification and herding behavior among investors in the Indian retail stock market. Applying a quantitative deductive research methodology, the study uses secondary financial data collected from National Stock Exchange (NSE), Bombay Stock Exchange (BSE), and popular robo-advisory platforms in the time span 2019–2024. To assess portfolio diversification, the Herfindahl-Hirschman Index (HHI) and the correlation analysis among the assets held by investors will be used. On the other hand, the Cross- Sectional Absolute Deviation (CSAD) model and the Lakonishok-Shleifer-Vishny (LSV) index will be applied to measure herding behavior among investors. The research findings demonstrate that portfolios advised by robots have much lower HHI (0.21) than portfolios managed by traditional methods (0.39), which shows higher levels of diversification. At the same time, herding behavior was proved to exist based on the negative value of the CSAD model's squared market return coefficient (β= -0.35; p=0.02), with LSV figures rising from 0.07 in relatively stable market periods to 0.19 when markets become highly volatile. Furthermore, regression analysis proves the existence of a significant negative relationship between algorithmic trading and portfolio concentration (β=-0.28; p=0.01). Thus, robo-advisors have been proved not only to lead to more effective diversification but also to generate herding risk due to their similarity. These findings have important implications for investors, fintech companies, government authorities, and financial regulation bodies.
| 100 |
Author(s):
AVD.Suresh Kumar.
Page No : 1-8
|
IoT Based Mobile Application for Monitoring of Hydroponic Vertical Farming
Abstract
The demand for infrastructure has tremendously increased with the population growth and it has a direct impact on the availability of agricultural land. Other factors such as climate change, declining water levels, increasing food demands, and loss of biodiversity are posing threat to agricultural production. Therefore, new agriculture techniques and practices such as vertical farming and soi-less farming have a high potential to fulfill the needs of the future world and can mitigate the requirement for arable land. This paper presents the design of an IoT-based mobile application implemented on android studio for controlling and monitoring the growth of plants using Hydroponic vertical farming. The environmental conditions and nutritional parameters, such as temperature, humidity, TDS, pH, water level, etc., recorded from the sensors are sent to the ThingSpeak cloud. The Tashi Home Pindfresh system is used for vertical farming setup and Arduino along with Raspberry Pi are used as the main controller unit.
| 101 |
Author(s):
AVD.Suresh Kumar.
Page No : 1-8
|
IoT Based Mobile Application for Monitoring of Hydroponic Vertical Farming
Abstract
The demand for infrastructure has tremendously increased with the population growth and it has a direct impact on the availability of agricultural land. Other factors such as climate change, declining water levels, increasing food demands, and loss of biodiversity are posing threat to agricultural production. Therefore, new agriculture techniques and practices such as vertical farming and soi-less farming have a high potential to fulfill the needs of the future world and can mitigate the requirement for arable land. This paper presents the design of an IoT-based mobile application implemented on android studio for controlling and monitoring the growth of plants using Hydroponic vertical farming. The environmental conditions and nutritional parameters, such as temperature, humidity, TDS, pH, water level, etc., recorded from the sensors are sent to the ThingSpeak cloud. The Tashi Home Pindfresh system is used for vertical farming setup and Arduino along with Raspberry Pi are used as the main controller unit.
| 102 |
Author(s):
Ali Ashjaa.
Page No : 1-8
|
Farmer Advisory Chatbot
Abstract
Agriculture has long been the backbone of the Indian economy, yet farmers, particularly smallholders, continue to struggle with accessing timely, reliable, and actionable information about crop health, weather patterns, and commodity market prices. This paper presents AgriChatbot, a full-stack conversational system built on the MERN (MongoDB, Express.js, React, Node.js) architecture with a Python-based backend, developed to bring integrated agricultural advisory services to farmers through a single chat interface. The system brings together a natural language processing engine with three dedicated modules: an AI-powered crop disease detector that works from leaf images, a real-time weather forecasting component, and a live agricultural market price retrieval service. Users interact through a responsive web application that routes their queries to the right backend service and returns structured, plain-language responses. The architecture keeps the React frontend, Node.js/Express middleware, and specialist Python services clearly separated, making each module straightforward to develop and scale on its own. AgriChatbot is, at its heart, an attempt to make agricultural expertise more democratically accessible, bringing together several streams of specialized advice into one conversational platform that any farmer with a smartphone can use.
| 103 |
Author(s):
Joshua Fernando.
Page No : 1-8
|
AWVERT: Automated Web Vulnerability Exploitation and Reporting Tool
Abstract
Web application vulnerabilities, particularly SQL Injection (SQLi) and Cross-Site Scripting (XSS), continue to dominate the global threat landscape, accounting for over 25% of documented security breaches annually. Existing tools such as Burp Suite, OWASP ZAP, and Nikto, while valuable, require significant manual intervention and lack the ability to leverage real-world Cyber Threat Intelligence (CTI) for automated payload testing. This paper presents AWVERT (Automated Web Vulnerability Exploitation and Reporting Tool), a Python-based automated vulnerability scanner for web applications. AWVERT integrates a Breadth-First Search (BFS) web crawler with support for both classic server-rendered and Single Page Application (SPA) architectures using headless Chromium via Playwright. The tool tests six injection categories — SQL Injection, Cross-Site Scripting, PHP/Command Injection, HTML Injection, XML/XXE Injection, and NoSQL Injection — using CTI-sourced payloads from a structured vault. Detection employs three modes: reflection analysis, error-signature matching, and statistical time-based inference. Tested against the OWASP Juice Shop intentionally vulnerable application, AWVERT demonstrates a detection rate of 77.8% across all injection types with a false positive rate of 9.0%.
| 104 |
Author(s):
Kavinraj S.
Page No : 1-8
|
EduMate: A Personalized AI Chatbot for Empowering Students with On Demand College Information
Abstract
Educational institutions across the globe are
challenged by the sheer volume of enquiries received
from prospective students, current students, and parents
regarding admissions, academic courses, fee structures,
campus facilities, placement statistics, and departmental
services. Conventional enquiry handling methods such as
telephone helplines, email correspondence, and in-person
visits to administrative offices are not only time-intensive
but also inconsistent in quality and unavailable beyond
working hours. The rapid evolution of Artificial
Intelligence (AI) and Natural Language Processing (NLP)
has opened new avenues for automating such interactions
through intelligent conversational agents. This paper
introduces EduMate, a personalized, AI-driven college
enquiry chatbot developed to bridge the communication
gap between students and educational institutions.
EduMate harnesses state-of-the-art NLP techniques to
accurately interpret user intent and deliver contextually
appropriate, real-time responses. Built on the Python
programming ecosystem with a Streamlit-based graphical
interface, the system provides an intuitive and accessible
platform for interaction. A distinctive feature of EduMate
is its bilingual capability, supporting both English and
Tamil, which greatly broadens its reach among diverse
student communities in Tamil Nadu and beyond.
Additionally, the integration of Speech-to-Text (STT) and
Text-to-Speech (TTS) technologies enables voice-driven
interaction, further enhancing accessibility for users who
prefer verbal communication. Evaluation results confirm
that EduMate achieves significant improvements in
enquiry response time, accuracy, and user satisfaction,
while substantially reducing the operational burden on
administrative personnel.
| 105 |
Author(s):
Aman Kumar Verma, Kumail Mujtaba, Asim Kaif, Syed Tabish Sajjad.
Page No : 1-9
|
AssignMatch: Intelligent Matching of Student Submissions
Abstract
Recent advances in digital learning environments and AI-assisted content generation have significantly changed how academic assignments are created and evaluated. Conventional manual grading approaches are increasingly difficult to scale, often requiring substantial instructor effort while remaining vulnerable to inconsistency and undetected semantic copying.
This paper introduces AssignMatch, an intelligent assignment evaluation framework designed to automate assessment through the integration of Optical Character Recognition (OCR), Natural Language Processing (NLP), large language models (LLMs), and semantic similarity analysis. The system accepts submissions in multiple formats, including scanned documents and images, extracts textual content using OCR, and performs structured preprocessing before evaluating responses against reference solutions using meaning-aware comparison techniques.
Beyond automated scoring, AssignMatch incorporates embedding-based plagiarism detection and cross-document similarity analysis to identify paraphrased or highly similar submissions. Experimental observations indicate that the proposed system substantially reduces grading time while maintaining strong agreement with instructor evaluation. The framework provides a scalable and adaptable solution for institutions seeking efficient, transparent, and AI-supported academic assessment.
| 106 |
Author(s):
Chaitanya Handa, Vasudha.
Page No : 1-9
|
Integrating accessibility in UI UX Design : a review of current methods
Abstract
Digital accessibility has become non-negotiable for websites and applications used across the world from healthcare to education and public services. Despite having the right tools and standards in place, accessibility is often checked at a later stage leading to developer frustration, fragmented fixes, and a dissatisfied user experience for users with disabilities. Existing practices fail to bridge the gap between evaluated issues and implementation of those insights. To advance the current state of methodologies, this review evaluates recent publications, compares existing methodologies, and addresses the critical challenges and future opportunities facing the industry.A basic understanding of digital accessibility is provided, with a focus on the growing importance of developing inclusive digital platforms. It discusses why accessibility checkpoints should be considered during the transition between the design and development phases rather than being treated as a final checklist item. The selected studies collectively explore different accessibility evaluation methods, including automated tools, expert reviews and manual checks, but they are not integrating the findings into early stages of design and a part of development workflow.Through this, the review aims to present how these methods contribute to identifying accessibility barriers and supporting more inclusive user interaction and user experience design practices.
| 107 |
Author(s):
Shaik Azeem hussain, Dr. Kiran Kumar M.
Page No : 1-9
|
Financial Statement Manipulations in Global Corporations: An Audit-Based Analysis Using the Beneish M-Score Model
Abstract
This paper focuses on the probability of manipulation of financial statements in twenty large international companies, including ten Indian companies and ten non-Indian companies, in the future (2021- 2025) through the Beneish M-Score model. The sample size is 100 publicly traded firm-years based on annual reports prepared in Ind AS, IFRS and US GAAP financial reporting frameworks. All the eight Beneish variables are included to determine composite M-Scores which are compared to the standard threshold of -2.22.
The results show that about 95 percent of the observations lie below the manipulation threshold, implying that financial reporting integrity of the sampled firms is high. Nevertheless, the individual cases of high M-Scores can be traced among a few companies, whose increase or decrease is mainly caused by changes in the Sales Growth Index and indicators based on accruals. The comparison of cross country shows no statistically significant difference in mean M-Scores between non-Indian and Indian corporations and a larger variability among non-Indian corporations.
The findings emphasize the applicability of the Beneish M-Score as a beneficial analytical instrument to promptly identify possible earnings manipulation. The research has a practical implication to the auditors, the regulators and investors as it supports risk-based assessment and improves the quality of financial reporting evaluation in multinational corporate settings.
| 108 |
Author(s):
Ruthik Donthu.
Page No : 1-10
|
The Impact of Mutual Recognition Agreements (MRA) on Inventory Optimization: A Simulation of Safety Stock Reduction in the India-EU Pharmaceutical Supply Chain
Abstract
The formal ratification of the India-EU Free Trade Agreement (FTA) on January 27, 2026, marks a structural paradigm shift for the Indian pharmaceutical export sector. While mainstream economic discourse centres on tariff liberalisation, this research contends that the Mutual Recognition Agreement (MRA) concerning Good Manufacturing Practices (GMP) is the true operational catalyst. Historically, Indian exporters have been burdened by extreme Lead Time Variability arising from redundant, non-synchronised regulatory inspections at EU borders, forcing firms to maintain bloated Safety Stock levels as a buffer against bureaucratic delays. This study quantifies the inventory optimisation potential unlocked by the MRA's removal of these non-tariff barriers. Utilising a Quantitative Simulation Research Design, the research models two supply chain environments: a pre-FTA baseline characterised by stochastic border disruptions (mean = 47.4 days, σL = 8.6 days), and a streamlined post-FTA Green Channel scenario (mean = 28.9 days, σL = 1.2 days). Applying the Probabilistic Safety Stock model (SS = Z × √(L·σD² + D²·σL²)) with 95% CSL, the simulation demonstrates an 86% reduction in required Safety Stock — from 14,190 units to 1,980 units per SKU. These findings are validated by a decisive F-Test (F-Stat = 51.34, p = 4.2 × 10⁻¹⁶). The study concludes that the MRA enables Indian firms to transition from a defensive Just-in-Case strategy to a lean Just-in-Time model, releasing approximately ₹610 Crores in working capital across a 1,000-SKU portfolio and generating ₹152 Crores in annual P&L improvement.
| 109 |
Author(s):
1Dr. A. V. Santhosh Babu, Magesh Hariram K, Hariharan S, Sowmiya A, Nisha G .
Page No : 1-11
|
A Decentralized IoT and Machine Learning Framework for Hyperlocal Cloudburst Prediction
Abstract
Cloudbursts are sudden and highly localized
extreme rainfall events that occur within a short duration and
often lead to flash floods, landslides, and severe infrastructure
damage. These events are particularly dangerous in
mountainous and high-risk regions where warning time is
limited. Existing cloudburst prediction systems mainly rely on
satellite
imagery,
weather radars, and large-scale
meteorological models. Although these approaches provide
regional forecasts, they often fail to deliver accurate hyperlocal
predictions due to the lack of real-time ground-level
environmental data. This limitation results in delayed warnings
and reduces the effectiveness of disaster preparedness.
| 110 |
Author(s):
Amaan Javed.
Page No : 1-11
|
CLOUD BASED SMART HEALTHCARE MONITORING SYSTEM USING MACHINE LEARNING
Abstract
The global convergence of cloud computing and machine learning (ML) has catalyzed a paradigm shift in the delivery and management of modern healthcare. Traditional hospital centric models are progressively giving way to proactive, data-driven, remote patient monitoring systems that can detect physiological anomalies in real time, thereby reducing the burden on overwhelmed healthcare infrastructure and enabling preventive rather than reactive medical intervention. This is particularly critical in the context of the United Nations Sustainable Development Goal 3 (SDG 3: Good Health and Well-being), which demands scalable, equitable, and technologically advanced solutions for healthcare delivery worldwide.
Despite significant advancements in wearable biosensor technology and cloud architectures, existing remote health monitoring systems frequently suffer from latency in anomaly detection, insufficient predictive capability for chronic disease progression, and inadequate data security frameworks for managing sensitive patient biometrics. Lightweight edge-cloud hybrid models are often either too computationally shallow for accurate multi-parameter disease prediction or too architecturally heavy for deployment on resource-constrained IoT medical devices.
To address these critical limitations, this paper proposes a highly optimized, cloud-based smart healthcare monitoring framework that synergizes real-time data acquisition from wearable IoT biosensors with the predictive power of ensemble machine learning algorithms deployed on a
scalable cloud backend. The system continuously monitors key vital signs including heart rate, blood oxygen saturation (SpO2), blood pressure, body temperature, and electrocardiogram (ECG) signals. Anomalies and disease risk patterns are detected using a hybrid ML pipeline combining Random Forest classifiers with Long Short-Term Memory (LSTM) networks for temporal pattern recognition. Furthermore, this research systematically synthesizes 25 pivotal studies, mapping the evolutionary trajectory of healthcare monitoring from rudimentary telemetry systems to modern ML-powered predictive analytics platforms.
Empirical evaluations on benchmark medical datasets demonstrate that the proposed ensemble classifier achieves an exceptional classification accuracy of 96.8% with a sensitivity of 95.4% and specificity of 97.2% for critical cardiac events. The system sustains an average alert latency of under 1.2 seconds from anomaly detection to clinician notification, decisively satisfying real-time health surveillance requirements. This framework ultimately provides a scalable, privacy-compliant, and economically accessible blueprint for the global deployment of AI-augmented preventive healthcare ecosystems.
| 111 |
Author(s):
Mukta Joshi, Dnyaneshree Vaidya, Pranum Jadhav, Janhavi Kalve.
Page No : 1-11
|
Smart Waste Management System
Abstract
Traditional municipal waste collection systems operate on fixed schedules, sending collection vehicles regardless of actual bin conditions, which leads to inefficient resource utilization, unnecessary fuel consumption, higher operational costs, and environmental pollution. To address these challenges, this project proposes an intelligent IoT-based Smart Waste Management System that transforms conventional schedule-driven waste collection into a demand-based and data-driven process using real-time monitoring and predictive analytics.
| 112 |
Author(s):
Sheryl Radley.
Page No : 1-11
|
SMART GRID PROTECTION SYSTEM WITH REAL-TIME CYBER THREAT DETECTION
Abstract
Project presents a Smart grid protection system with real-time cyber threat detection designed to enhance the cybersecurity and operational reliability of smart grid and industrial control systems. Traditional power grid systems face increasing cyber threats such as unauthorized access, denial-of-service attacks, malware infections, and protocol-based exploits, leading to disruptions and financial losses. To address these challenges, the proposed system integrates real-time system monitoring, network traffic analysis, machine learning-based anomaly detection, and industrial protocol inspection. It continuously monitors parameters such as CPU usage, memory utilization, network traffic, and running processes, detecting suspicious activities using rule-based methods and an Isolation Forest-based anomaly detection model.
The system also inspects industrial communication protocols like Modbus and DNP3 to identify unauthorized access and abnormal commands. A file scanning module integrated with the Virus. Total API enhances malware detection. Upon identifying threats, the system automatically responds by blocking malicious IPs, terminating suspicious processes, and generating alerts.
A real-time web-based dashboard provides continuous monitoring and visualization, along with email notifications to ensure quick response. The system is designed to be scalable, efficient, and cost-effective for modern smart grid environments. In addition, a custom spyware attack using a keylogger was created to test the system. The attack collects keystrokes, screenshots, audio, and system data, and tries to send it outside. The SGPS detects this activity in real time and automatically responds by sending alerts and stopping the process, showing its effectiveness against real-world cyber threats.
| 113 |
Author(s):
Dr. A. V. Santhosh Babu¹, D. Vimal Kumar², K. Surya Prakash³, A. Anton Maria Jones⁴, S. Logeswar⁵, S. Mokith⁶ .
Page No : 1-13
|
IoT Based Smart Traffic Control System with Emergency Vehicle Identification and Real-Time Web Monitoring
Abstract
This project is about a traffic control system that
uses the Internet of Things or IoT to make traffic flow better in
cities. It helps emergency vehicles get through quickly. The
system uses three IR sensors at each intersection to check how
busy the traffic is. These sensors can tell if the traffic is low,
medium or high. Depending on how busy it's the green light stays
on for 5, 10 or 15 seconds. There’s also an RF module that works
at 433 MHz It can detect when an emergency vehicle is coming.
When it does it makes a corridor so the emergency vehicle can
pass through without stopping. The system uses an Arduino
Mega 2560 microcontroller. It also sends traffic data to the Thing
Speak cloud. This way people can monitor the traffic in time. We
also made a web dashboard using HTML, CSS, JavaScript and
Node.js. This dashboard has maps shows data in a visual way and
lets users export data. Our system is pretty accurate. It can detect
things 97.3% of the time. It also reduces the waiting time by
58%. The system helps make traffic flow better and gets
emergency vehicles where they need to go. The IoT-based traffic
control system is a tool, for cities. It uses technology to make a
big difference.
| 114 |
Author(s):
Asif Kareem.
Page No : 1-13
|
Fake News Detection Using Machine Learning
Abstract
The proliferation of digitally fabricated information across social media platforms, online news portals, and messaging ecosystems has precipitated a global epistemic crisis with measurable consequences for democratic governance, public health, and socioeconomic stability. The velocity at which misinformation propagates through hyper-connected social networks now far exceeds the capacity of traditional human fact-checking mechanisms, rendering automated, scalable detection systems not merely beneficial but structurally imperative. While substantial academic effort has been directed towards Natural Language Processing (NLP)-based misinformation classifiers, existing systems frequently suffer from an unresolved dichotomy: heavyweight transformer models such as BERT and RoBERTa achieve exceptional classification accuracy but are computationally prohibitive for real-time content moderation at platform scale, whereas lightweight classical machine learning approaches lack the deep semantic reasoning capacity required to detect sophisticated, contextually coherent synthetic narratives. To address these critical limitations, this paper proposes a highly optimized, real-time fake news detection framework that synergizes the deep bidirectional contextual encoding capabilities of a fine-tuned DistilBERT architecture with the rapid, low-parameter classification efficiency of a Gradient Boosting meta-learner. By mathematically compressing transformer attention layers through knowledge distillation and coupling the resulting dense semantic embeddings with a suite of engineered psycholinguistic and stylometric features, the proposed hybrid pipeline is engineered for seamless, low-latency deployment on standard commodity server hardware. Furthermore, this research
systematically synthesizes 25 pivotal studies, mapping the evolutionary trajectory of automated deception detection from early rule-based heuristics and classical machine learning classifiers to modern pre-trained language models and multimodal misinformation networks, thereby providing a comprehensive theoretical foundation. Empirical evaluations on a withheld testing partition of the LIAR and FakeNewsNet benchmark datasets demonstrate that the proposed hybrid classifier achieves an exceptional validation accuracy of 96.8% with an F1-score of 0.971. Concurrently, the system maintains an average inference latency of 18 milliseconds per article on standard CPU hardware, decisively satisfying the real-time throughput requirements of production-grade content moderation APIs. Ultimately, this framework provides a scalable, robust, and interpretable blueprint for integrating localized artificial intelligence into permanent, proactive information integrity architectures.
| 115 |
Author(s):
Sanika Kachwe.
Page No : 1-16
|
An Automated Deep Learning Framework for Multiclass Brain Tumor Detection in MRI Images
Abstract
Using magnetic resonance imaging (MRI) to detect and classify brain tumors continues to be a crucial challenge in medical diagnostics, requiring precise, effective, and solutions that are easily available. This thorough study examines 25 cutting-edge research publications published between 2015 and 2025 with an emphasis on deep learning techniques for automated brain tumor identification, classification, and segmentation. Traditional CNNs, sophisticated YOLO architectures, U-Net variations, Transformer-based models, and hybrid ensemble methods are among the methodologies that are methodically examined in this research. According to performance measures from several research, 3D segmentation methods yield Dice coefficients of 93–98%, while 2D CNN algorithms achieve accuracy between 82 and 98%. YOLOv7 and YOLOv8 real-time detection systems have mean Average Precision (mAP) values ranging from 0.91 to 0.95, providing notable benefits in computing efficiency. Surgical planning benefits from improved spatial knowledge through the combination of augmented reality (AR) and 3D visualization approaches. Limited multi-institutional dataset validation, computational limitations in resource-constrained environments, class imbalance issues, and a lack of real-world clinical deployment studies are some of the major research gaps that have been found. This review lays the groundwork for future research directions in easily accessible, precise, and clinically feasible brain tumor diagnostic systems by offering a systematic comparative comparison of methodology, datasets, and performance indicators.
| 116 |
Author(s):
Dr. Prerna N. Bhautik.
Page No : 1-21
|
Instagram Aesthetics and Tourist Behavior: Shaping Destination Choice and Satisfaction in Pune and Goa
Abstract
Instagrammable tourism has intensified the role of visual social media in shaping how travelers imagine and evaluate destinations, with Instagram aesthetics becoming a powerful cue for desirability and status. Within this context, this study examines how Instagram-based social media aesthetics influence destination choice and post-visit guest satisfaction for two Indian leisure destinations (Pune and Goa). Using a cross-sectional survey of leisure travelers exposed to Instagram content about these destinations, this study applies a structured questionnaire and variance-based structural equation modeling to test a model linking perceived aesthetics, destination choice, and satisfaction. The results show that perceived social media aesthetics, encompassing visual quality, uniqueness, and authenticity, significantly increase the likelihood of choosing Pune or Goa over alternative destinations. In turn, both perceived aesthetics and the resulting destination choice positively predict guest satisfaction, indicating that visually driven expectations and the act of choosing an “Instagrammable” destination jointly shape post-visit evaluation. These findings highlight Instagram aesthetics as a strategic lever for tourism marketers seeking to influence travelers’ destinations and post-stay satisfaction.