| 1 |
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.
| 2 |
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
| 3 |
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.
| 4 |
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.
| 5 |
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
| 6 |
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
| 7 |
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.
| 8 |
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 .
| 9 |
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.
| 10 |
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.
| 11 |
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.
| 12 |
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.
| 13 |
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.
| 14 |
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.
| 15 |
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.
| 16 |
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
| 17 |
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.
| 18 |
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.
| 19 |
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.
| 20 |
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.
| 21 |
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.
| 22 |
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.
