| 1 |
Author(s):
Lavanya N Kurahatti, Kavya B Ramasali, Keerti V Navalagunda.
Page No : 1-3
|
Designing and implementation of 32-bit RISC Processor using verilog HDL
Abstract
This paper presents the design and implementation of a 32-bit RISC processor using Verilog HDL. The processor follows a simplified instruction set and pipelined architecture to achieve higher performance and reduced hardware complexity. The design includes basic processing units such as ALU, register file, control unit, and memory modules. The processor is verified using simulation tools and synthesized for FPGA implementation. The proposed design is suitable for educational and embedded system applications.
| 2 |
Author(s):
ANISHASHARAN.
Page No : 1-3
|
AI-Assisted Grid-Based Music Sequencing A Study Using Tenori-Off
Abstract
This paper introduces an interactive AI-based music generation system built using the Tenori-Off project. Inspired by Yamaha’s Tenori-On, this system allows users to create melodies and rhythms using a visual grid interface. Each grid cell represents a musical note or drum sound, and when activated, it plays automatically in sequence. This project helps beginners understand how sound, timing, and AI can combine to produce creative musical patterns in real time. Additionally, the system leverages machine learning algorithms to suggest harmonious note combinations and rhythmic variations. It serves as both an educational tool and a creative platform for exploring generative music through AI interaction.
| 3 |
Author(s):
Pradeep S.
Page No : 1-3
|
Digital Vote System With Real Time Result Tracking
Abstract
By offering a safe online platform where qualified voters can cast their ballots electronically the Digital Voting System aims to revolutionize traditional elections. By providing a rapid reliable and user-friendly way to cast a ballot the system does away with the need for traditional polling places and avoids lengthy lines. Before accessing the portal voters must authenticate themselves. Strict validation procedures prevent duplicate voting and each user is only permitted to cast one ballot. Encryption protects the data from unwanted access and all votes are kept in a secure database for confidentiality. This strategy reduces the manual counting errors that are frequently observed in conventional techniques. The real-time counting module offers continuously updated election results encouraging transparency and cutting down on delays and administrators can effectively manage voter lists and candidate information. The systems scalability makes it suitable for adoption by communities organizations and educational institutions. It provides a straightforward interface for simple navigation and facilitates seamless operation during periods of high user activity. To safeguard the voting process the project places a strong emphasis on operational accuracy system integrity and multiple security layers. Reducing human intervention lowers the possibility of tampering which eventually boosts confidence in digital election platforms.
| 4 |
Author(s):
ANANYA .B L.
Page No : 1-3
|
Digital Lost Property Management System
Abstract
This project presents a Python-based Lost and Found Management System developed to help users easily report, search, and recover lost items within an organization. The system allows users to register, log in, and submit details of lost or found objects along with the date and location. All records are securely stored in a database for quick access and easy management. The matching process helps users identify possible item connections efficiently. Administrative control is provided to verify and manage reports. The system also supports basic notification features for updates. By reducing manual effort and paperwork, the project improves accuracy and response time. Overall, the application offers a simple, reliable, and practical solution for lost and found item management.
| 5 |
Author(s):
SUBHASRI S NAYAK.
Page No : 1-3
|
AI-Powered Occupational Health Surveillance System (AI-OHSS) for Enhanced Worker Safety in Aluminum Smelters
Abstract
The primary aluminum smelting industry poses significant occupational health and safety (OHS) risks, including exposure to high heat, noxious fumes (e.g., fluoride, sulfur dioxide), molten metal, and strenuous physical labor. Traditional OHS methods are often reactive. This paper proposes the AI-Powered Occupational Health Surveillance System (AI-OHSS), a novel, proactive, and real-time monitoring system utilizing the Internet of Things (IoT) and Machine Learning (ML). AI-OHSS integrates data from wearable biometrics, environmental sensors, and visual analytics to provide comprehensive surveillance. The system is designed to detect and predict immediate hazards (e.g., heat stress, gas leaks, fatigue) and long-term health risks, significantly enhancing worker safety and well-being in the potroom and casting areas.
| 6 |
Author(s):
Mr. Abhishek Mahadev Rathod.
Page No : 1-3
|
Green Supply Chain Management Practices in Manufacturing-Linked Agribusiness Enterprises
Abstract
Sustainability has become a critical consideration in modern agribusiness, particularly in enterprises linked to manufacturing processes. Green Supply Chain Management (GSCM) integrates environmental thinking into supply chain operations, including product design, material sourcing, manufacturing processes, and distribution, with the aim of reducing environmental impact while enhancing operational efficiency. This conceptual review examines the adoption of GSCM practices in manufacturing-linked agribusiness enterprises, analyzing their role in promoting environmental sustainability, operational efficiency, and competitive advantage. Drawing on existing literature, the paper categorizes key practices such as eco-design, green procurement, waste management, energy-efficient production, and reverse logistics. The study highlights the challenges faced by agribusinesses in implementing GSCM, including high initial costs, technological constraints, and lack of regulatory support. Finally, the review emphasizes the sustainability implications of GSCM adoption, demonstrating that these practices not only contribute to environmental stewardship but also enhance economic performance and long-term resilience in agribusiness supply chains.
| 7 |
Author(s):
Mr. Abhishek Mahadev Rathod, Dr. Jyoti Laxman Zirmire.
Page No : 1-3
|
Potential of Agri-Allied Business Ventures in Achieving Poverty Eradication Goals
Abstract
Poverty eradication remains one of the most pressing global development challenges, particularly in developing and agrarian economies where a large proportion of the population depends on agriculture for livelihood. Traditional crop-based agriculture alone has increasingly failed to provide sufficient income due to small landholdings, climate change, market volatility, and rising production costs. In this context, agri-allied business ventures have emerged as a viable and sustainable approach to enhancing rural income and employment opportunities. This paper examines the potential of agri-allied business ventures in achieving poverty eradication goals by diversifying income sources, generating employment, and strengthening rural entrepreneurship. Based on an extensive review of secondary literature, the study analyzes various forms of agri-allied enterprises, their characteristics, and their role in improving livelihoods. The findings indicate that agri-allied business ventures significantly contribute to poverty reduction by promoting inclusive growth, enhancing income stability, and supporting sustainable rural development. The paper concludes that policy support, financial inclusion, and capacity-building initiatives are essential to fully harness the poverty-alleviating potential of agri-allied businesses.
| 8 |
Author(s):
A.Sivasundari , Dr. K. Malarmathi .
Page No : 1-4
|
Contextualising Rootlessness and Alienation in V.S. Naipaul’s A House for Mr. Biswas
Abstract
This papertries to pinpoint the miseries andsufferings experienced by the characters of V.S. Naipaul have intrinsicconcurrence with the experiences of humans throughout the world, surviving in analien land ruled by a colonized community in his A House for Mr. Biswas. The storyopens with the demise of Mohun Biswas. As a descendant of East Indians who were brought to Trinidad as indentured labourers working in the sugarcane fields, Mr. Biswas has endured humiliation and bad luck. He has been homeless and without love, moving from one job to another and experiencing shame with every minor triumph. As a member of the large Tulsi clan, his wife has always been loyal to them and they have treated him with disdain. Mr. Biswas hastily buys a dilapidated home that he cannot afford, but it is his own and signifies a break from the oppressive Tulsis. His wife and children are left impoverished after his death. His home is deserted. Importantly, the work illustrates the fundamental mechanism of a man’s life, which is the fusion of happiness and sadness, harsh and majestic. In Naipaul’s world, impoverished wanderers are creating a path of escape from Africa or India to the West Indies, then to Britain and back. Even after three centuries, it seems as though there is still no structure or culture of values where these characters can originate. They try to cling to something to give them stability to hold the flux in their life against such a hazy and crumbling background.
| 9 |
Author(s):
Simran Devi1, Sagar Choudhary2.
Page No : 1-4
|
Machine Learning for Early and Accurate Prediction of Cardiovascular Disease Risk
Abstract
Cardiovascular Diseases (CVDs) remain the leading cause of global mortality. Timely and accurate diagnosis is crucial for effective intervention and improved patient prognosis. This paper investigates the utility of advanced Machine Learning (ML) techniques—specifically Random Forest (RF), Support Vector Machine (SVM), and Deep Neural Networks (DNN)—to enhance the early prediction of CVD risk using routine patient health metrics (e.g., age, cholesterol levels, blood pressure, BMI). We analyzed a publicly available clinical dataset of N patients. The results demonstrate that the DNN model achieved the highest predictive performance, with an accuracy of 91.2% and an F1-score of 90.5%, significantly outperforming traditional statistical models and shallower ML methods. This study highlights the immense potential of ML models as a robust decision-support tool for clinicians in proactive CVD management.
| 10 |
Author(s):
Juvvanaboyina Sandhya.
Page No : 1-4
|
IoT-Enabled Smart Grid Monitoring with Dual Communication and Overload Protection
Abstract
This research presents an IoT-based smart grid monitoring system designed to address frequent power interruptions during transmission from grid stations to consumers. The proposed architecture integrates Arduino UNO as the central controller with ESP8266 WiFi module for cloud data transmission to ThingSpeak platform and GSM module for real-time SMS alerts during overload conditions. Key sensors monitor voltage, current, temperature, humidity, and oil levels, while a relay provides automatic load disconnection above safe thresholds (voltage >230V, current >0.7A). Deployed over 7 days, the system achieved 98.2% data transmission reliability via WiFi and 100% SMS delivery success, reducing outage response time from hours to seconds. Costing under INR 4500, this solution offers scalable deployment for rural Indian grids, enhancing energy efficiency and grid stability through bidirectional communication.
| 11 |
Author(s):
Allen Thomas.
Page No : 1-4
|
The Microeconomic Impact of ESG Integation on India’s Oil Sector: Corporate Adaption and Investment Behaviour
Abstract
In recent years, India’s oil sector has undergone a profound transformation under the global wave of sustainability. The integration of Environmental, Social, and Governance (ESG) principles has evolved from being a mere compliance requirement into a decisive factor influencing both corporate strategy and investment behavior. This paper examines the microeconomic impact of ESG integration on India’s oil sector, focusing on how companies are adapting operationally and strategically, and how investors are recalibrating their decisions in response. Using secondary data analysis from government reports, corporate disclosures, sustainability indices, and investor trend studies, this research explores how ESG practices reshape profitability, risk perception, and competitiveness. The study concludes that ESG integration is redefining value creation in India’s oil sector, encouraging transparency, technological innovation, and responsible investment flows.
| 12 |
Author(s):
Krupa H N.
Page No : 1-4
|
SMART VIRTUAL TRAIL ROOM APPLICATION
Abstract
The Smart Virtual Trail Room Application is a modern digital solution designed to improve customer experience by allowing users to see how clothes, jewelry, glasses, and hats would look on them without physically visiting a store. Though online shopping is becoming increasingly popular among consumers, a significant number of them still hold reservations when it comes to buying clothes since they are unable to judge the fitting, style or suitability through usual production images. The method uses a camera to capture a picture of the user and afterward, computer vision algorithms are applied to adjust the body shape and stance, thus simplifying the imaging and fitting process. The chosen garments, rings, shades, and hats out of the online catalogue are then perfectly blended and showcased on the user's body in real time giving a genuine try-on experience.
| 13 |
Author(s):
Anusha Chandrahas Raykar.
Page No : 1-4
|
Enhanced Banking Security System Using AI Based Facial Recognition With Anti-Spoofing
Abstract
The need for reliable and safe methods of user verification has grown as digital banking continues to grow. Passwords PINs and one-time codes are examples of older techniques that are no longer as trustworthy. They are more susceptible to unauthorized access because they can be stolen hacked or misused through phishing attacks. To get around these limitations the current work provides an improved banking security system with anti-spoofing and AI-based facial recognition. Deep learning technology is used in this system to identify a persons face and it also uses small real-time signals like blinking and skin texture to determine if the person is truly alive. A CNN model analyzes a persons facial features and compares them to user information that is safely kept in the system. It is difficult for someone to trick the system with printed photos mobile displays or masks because of the integrated anti-spoofing feature. In general this configuration makes online transactions safer and gives users greater confidence in their digital banking.
| 14 |
Author(s):
Chandana N.
Page No : 1-4
|
Automated Complaint Resolution Platform Using AI
Abstract
The Automated Complaint Resolution Platform is a new means of modern public maintenance, which is based on the use of artificial intelligence mutual with the advanced web technologies to make simpler the process of urban & rural complaints submission and resolution. By uploading images, people can report the most common issues like potholes, garbage collection, broken streetlights or water leaks. The platform, which is built on the MERN architecture and uses secure backend microservices, gives modified dashboards to users, authorities, and administrators to guarantee transparency and effectiveness of operations. The automated processing, intelligent map-reading, and real-time tracking make the user experience better and give departments the possibility of tracking and responding to reported issues. In summary, the AI-based model is very helpful in changing the process of handling complaints from being purely reactive to being common, practical, and scalable in civic governance
| 15 |
Author(s):
SHREELAXMI MN.
Page No : 1-4
|
AI POWERED SMART TOURIST PLANNER&ITINERARY GENERATOR
Abstract
An intelligent travel help system called the AI Powered Smart Tourist Planner and Itinerary Generator was created to give users hassle-free, effective, and customised vacation planning. Travellers today frequently find it difficult to sort through the vast volumes of information available regarding locations, routes, schedules, and activities. By utilising Artificial Intelligence (AI) and Machine Learning (ML) techniques to produce personalised recommendations based on user interests, budget, length, and geographical choices, this project seeks to streamline the entire travel planning process.
| 16 |
Author(s):
Fathima Nida Zarnain.
Page No : 1-4
|
Autonomous Intelligent Detection and Continuous Protection System
Abstract
Phishing schemes and junk emails represent a serious risk to internet users by deceiving them into disclosing confidential information. Current detection systems rely on blacklists and fixed rule-based filtering which often fail to detect newly developed malicious websites and misleading email content. This paper presents a machine learning-based intelligent system that can identify spam in emails and URLs. Preprocessing and TF-IDF vectorization are used in the process to extract features from supplied text and URLs. The inputs are classified as authentic or fraudulent using algorithms such as Random Forest and Logistic Regression. The goal of a Streamlit interface is to give users a simple interesting and easy-to-use experience. According to experimental results the recommended approach is more effective than traditional detection systems at revealing hidden phishing patterns. The developed model provides fast accurate and reliable forecasts for cybersecurity applications in real time.
| 17 |
Author(s):
Swathi C S Naidu.
Page No : 1-4
|
AI-Supported Detection of Missing Persons
Abstract
This study investigates the efficient and precise use of artificial intelligence to find missing people. The system can create massive datasets spot trends and promptly notify authorities by utilizing technologies like facemask recognition machine learning and data analysis. The study demonstrates how AI improves conventional search techniques speeds up response times and raises the possibility of locating people who are missing. To further optimize search operations future enhancements might include predictive modelling and real-time monitoring.
| 18 |
Author(s):
Karthik A S.
Page No : 1-4
|
Social Media Sentiment Analysis Using Twitter
Abstract
This project aims to analyze opinions shared on Twitter by automatically determining whether a tweet expresses a positive, negative, or neutral sentiment. Tweets are collected using available APIs and cleaned to remove irrelevant elements such as links, emojis, hashtags, and common filler words. After preprocessing, text data is analyzed using Natural Language Processing techniques and trained machine learning models to identify sentiment patterns. The system helps in understanding public opinions, user attitudes, and trending reactions on social media. It can support organizations, researchers, and analysts in gaining insights into customer feedback, social issues, and online discussions in an efficient and scalable manner.This project presents an automated approach to understand public opinions by analyzing sentiment from Twitter data. It involves gathering tweets related to specific topics or keywords and refining the text through preprocessing steps such as tokenization, normalization, and noise removal. The refined data is then processed using Natural Language Processing methods and classification algorithms to determine the sentiment expressed in each tweet. The proposed system enables efficient analysis of large volumes of social media data, helping to identify user emotions, public reactions, and opinion trends. Such insights can be valuable for market analysis, social research, and decision-making processes where understanding public perception is important.This project focuses on analyzing public sentiment on Twitter to gain insights into opinions on specific topics or events. It integrates data collection, preprocessing, sentiment classification, and visualization into a unified system. By using NLP techniques and machine learning models, the project can accurately detect emotions expressed in tweets. The real-time analysis and interactive dashboards allow users to monitor trends efficiently. This approach demonstrates the practical application of AI and data analytics in understanding social media behavior.
| 19 |
Author(s):
MANJUNATHA CH, Mrs. Tejaswini A.
Page No : 1-4
|
Decentralized Supply Chain Tracking System
Abstract
In order to enhance security traceability and transparency throughout product lifecycles this paper
proposes a decentralized supply chain tracking system. The suggested solution records supply chain
transactions in an unchangeable and tamper-resistant way using blockchain technology and smart
contracts. To guarantee safe and regulated interactions producers distributors retailers and
consumers are given role-based access. Users can easily communicate with the blockchain network
via cryptographic wallets thanks to a web- based interface. Stakeholders can effectively track the
movement and status of products thanks to real-time event-driven updates. Additionally the system
gives users a visual timeline to track the history of the product. The suggested strategy improves
accountability and trust by doing away with centralized control. This project illustrates how blockchain technology can be used practically in contemporary supply chain management systems.
| 20 |
Author(s):
Dr. Shailaja Mudengudi, Ankita Londve, Deepa Hanamasagar, Prajwal P Danappagoudar.
Page No : 1-5
|
Design and Implementation of High-speed Low-power FIR filter using Cadence tool
Abstract
Finite Impulse Response (FIR) filters are widely used in modern digital signal processing systems that demand high computational speed, low power consumption, and efficient silicon area utilization. This project presents the design and implementation of a high-speed, low-power FIR filter using the Cadence design environment. The proposed architecture employs an optimized multiplier-accumulator (MAC) structure, coefficient symmetry exploitation, and pipelined data paths to minimize critical path delay and reduce overall dynamic power consumption. RTL design was developed using Verilog HDL and synthesized using Cadence Genus, while Cadence power–performance–area (PPA) analysis. Post-layout simulations validate the correctness of the filter and demonstrate significant improvements in maximum operating frequency and power efficiency compared to conventional FIR filter implementations. The results confirm that the proposed design methodology is suitable for high-performance DSP applications such as wireless communication, biomedical signal processing, and real-time embedded systems.
| 21 |
Author(s):
K.Sowmya Deepthi.
Page No : 1-5
|
Intelligent Battery Optimization Framework for Electric Vehicle Power Systems
Abstract
Electric vehicles (EVs) require efficient battery
management systems (BMS) to handle the high voltage
batteries used as power sources. A comprehensive BMS not
only estimates the remaining battery capacity but also
prevents hazards caused by improper use. This paper
reviews contemporary battery management systems
focusing on their functions such as cell balancing, thermal
management, and performance optimization in EVs.
| 22 |
Author(s):
NEHA SP.
Page No : 1-5
|
Clustering -Based Crime Analysis and Pattern Identification
Abstract
Crime has increasingly become a major apprehension used for community security, as increasing criminal actions interrupt social stability and general security. The determined incidents instil fear and uncertainty in the minds of citizens. As a result preventing crime is the main responsibility. It needs to be taught in a deliberate and rational way in order to change crime. K means compiles algorithms in this work cluster that are connected to criminal episodes in an attempt to uncover hidden behavioral patterns. In contemporary crime analysis a variety of datasets and open-source tools are used to analyze past events and predict future criminal activity. In terms of the capacity to anticipate the detection of concealed behavior both groups had similar crime rates. This endeavor aims to enhance self-protective decision making by promoting a better understanding of crime and streamline ongoing projects it.
| 23 |
Author(s):
Madhushree GK.
Page No : 1-5
|
Smart food recognition and calorie system using CNN
Abstract
Heaviness has been a global problem for a long time. This remains the result of dietary problems that increase obesity’s susceptibility to various diseases. Maintaining a healthy diet while balancing the demands of an adult job can be hard. This document describes the creation of a clever diet journal a smartphone app that tracks diet to assist patients and obese individuals in controlling their nutrition amount consumed for a better quality of being.
The suggested system makes use of deep learning to identify food items calculate their nutritive value in relationships of calories 16,000 photos of food products from 14 distinct categories compromise the data that a multi-label classifier is trained on. We were able to calculate average calories within 10% of the definite calorie value and achieve an overall precision of roughly 80.1 per cent by using a pre-trained CNN model for classification.
| 24 |
Author(s):
Sanjana M.
Page No : 1-5
|
Parking Lot Management System
Abstract
The rapid growth of urbanization and the continuous increase in the number of vehicles have created
serious challenges in managing parking spaces efficiently. The majority of conventional parking
systems are manual ineffective and frequently lead to traffic jams time wastage and inefficient use of
available parking spaces. to overcome these obstacles. This project offers a smart parking management
system that combines artificial intelligence and web technologies to offer an automated and clever
parking solution. SQLite is used in the development of the suggested system which is built with Python
and the Flask framework. for the administration of databases. Online parking reservations automated
vehicle check-in and check-out real-time parking slot monitoring and dynamic billing based on parking
duration are all made possible by it. To accurately identify vehicles during entry and exit an AI-based
vehicle number plate recognition module is integrated minimizing human error and intervention.
Additionally the system has a machine learning-based parking demand prediction mechanism that helps
administrators plan parking effectively by identifying peak hours and estimating future occupancy
trends. Additionally the system offers an AI-powered chatbot to help users with parking availability
booking payment details and general inquiries. It also supports a variety of digital payment methods.
Administrators can monitor revenue usage trends and overall parking efficiency with the aid of
comprehensive reports and analytics. The suggested Smart Parking Management System maximizes
resources eases traffic and enhances user convenience. usage and helps to build the infrastructure of
smart cities
| 25 |
Author(s):
Bhanupriya L, Chaitanya MD, Deekshitha S, Meghana CP, Mrs.Nillu Mishra.
Page No : 1-6
|
BIRDS BUDDY: THE SHELTER TO BIRDS
Abstract
The present project relates to a Birds shelter and method. This smart shelter aims to support local bird populations, particularly in urban areas where natural water sources may be scarce and no developing places for birds. By integrating technology with wildlife conservation, the BIRDS BUDDY shelter fosters coexistence between humans and nature, encouraging biodiversity and environmental awareness. The design is simple, scalable, and can be customized to include features like temperature sensors, automated feeders, and cleaning mechanism, water level detector, making it a versatile tool for bird enthusiasts and conservationists alike. Overall, the BIRDS BUDDY project highlights the potential of affordable electronics in wildlife preservation, demonstrating how small innovations can make a meaningful impact on sustaining local ecosystems and protecting avian species for future generations.
| 26 |
Author(s):
Praveensingh Rajput, Revansiddaya Hiremath, Rakesh Bellad.
Page No : 1-6
|
Elevating Wi-fi Controlled Car Using ESP32
Abstract
—The key innovation is a web-based interface hosted
directly on the ESP32, eliminating the need for dedicated appli
cations or internet connectivity. This design choice enhances user
friendliness and reduces system complexity. The hardware setup
involves fundamental components: an ESP32 development board,
an L298N motor driver, and standard DC motors, ensuring cost
effectiveness and ease of replication. The ESP32’s dual-core ar
chitecture and integrated Wi-Fi module allow it to simultaneously
serve web pages and manage real-time motor control. Users can
access the intuitive web interface through any Wi-Fi enabled
device’s browser to send commands to the car. The commands are
wirelessly transmit in the ESP32, which then processes them to
drive the L298N motor driver. The L298N, in turn, regulates the
power supplied to the DC motors, enabling precise control over
the robot’s movement. Primarily intended for educational pur
poses and rapid prototyping, this project effectively demonstrates
the principles of wireless robotic control with minimal hardware
and software overhead. The app-free and internet-independent
nature of the system makes it an ideal platform for students,
hobbyists, and researchers exploring robotics and the Internet of
Things. The paper elaborates on the hardware configuration, the
software implementation on the ESP32, and the functionality of
the user-friendly web control interface. The advantages of this
approach, including its simplicity, low cost, and self-contained
operation, are also discussed. Index terms such as ESP32, Wi-Fi
robot, IoT car, web server control, and remote control categorize
the core aspects of this work. This research contributes to making
wireless robotic control more accessible and easier to implement
| 27 |
Author(s):
Sourav Mandal.
Page No : 1-6
|
AI-Driven Cyber Threat Prediction System Using Dynamic Graph-Based Anomaly Detection in Enterprise Networks
Abstract
Enterprise networks are increasingly exposed to dynamic cyber threats capable of bypassing traditional intrusion detection systems. This research proposes a novel AI-driven threat prediction framework using dynamic graph-based anomaly detection. The model represents enterprise network communication as a continuously evolving graph and applies temporal graph learning, unsupervised anomaly scoring, and behavior modeling to predict malicious activities in real time. The system does not rely on prior attack signatures and adapts automatically to new network behavior. Experimental results demonstrate improved detection accuracy, reduced false positives, and enhanced robustness against zero-day attacks, proving the effectiveness of dynamic graph learning for next-generation enterprise cybersecurity.
| 28 |
Author(s):
Rishu Khadka .
Page No : 1-6
|
VISION-BASED SIGN LANGUAGE INTERPRETATION USING DEEP LEARNING
Abstract
Abstract
This research paper presents an intelligent vision-based sign language interpretation system powered by deep learning and computer vision techniques. The proposed system utilizes Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to recognize and interpret sign language gestures in real-time from video input. The primary objective is to bridge the communication gap between deaf and hearing communities by providing an accurate, efficient, and accessible translation system. The system processes hand gestures, facial expressions, and body movements to interpret American Sign Language (ASL) and Indian Sign Language (ISL) with high accuracy. This research addresses challenges in gesture recognition, real-time processing, and contextual interpretation, demonstrating significant improvements over existing approaches with 94.7% recognition accuracy and sub-100ms latency for real-time interpretation.
Keywords: Sign Language Recognition, Computer Vision, Deep Learning, CNN, LSTM, Gesture Recognition, Human-Computer Interaction
| 29 |
Author(s):
Ismail Z. Y..
Page No : 1-6
|
Face Recognition Attendance Monitoring System Using Deep Learning Approach
Abstract
Face Recognition Attendance Monitoring System offers a cutting-edge replacement for conventional techniques used in educational settings to track attendance. This solution provides a smooth and effective way to track student attendance by utilising the latest developments in artificial intelligence and computer vision. Facial recognition technology replaces manual attendance taking by teachers by automatically recording students' attendance when they enter classes or other authorised areas. The architecture and implementation of the suggested system, which combines database administration, facial recognition, and detection modules, are described in this work. In order to reliably and precisely track student attendance, the system uses deep learning algorithms to precisely recognise and match faces against a pre-registered database of students. Installing such a system in academic environments has numerous advantages. It gives instructors less administrative work, expedites the attendance management procedure, and offers current information on student attendance trends. By producing thorough attendance reports for administrative needs, it also improves accountability and transparency. The efficacy and efficiency of the Face Recognition Attendance Monitoring System are proven through testing and assessment. The findings show that attendance records are accurately recorded, with few false positives and negatives. It provides an advanced, yet approachable, answer to the problems associated with university attendance tracking. The potential for revolutionising existing attendance monitoring procedures through its adoption lies in its ability to develop a more efficient and data-driven approach to academic oversight and student involvement.
| 30 |
Author(s):
Noyal Zachariah Binoy.
Page No : 1-6
|
The Tax Literacy Gap : The Impact Of Tax Knowledge On Financial Decision-Making Among Youth.
Abstract
This research quantitatively examines the hypothesis that a significant Tax Knowledge Gap exists among young adults-defined as those between 18 and 30 years of age, and that this gap critically compromises their ability to engage in Prudent Financial Decision-Making. The study is motivated by the observation that, while general financial literacy has been prioritized, the specialized area of personal taxation remains poorly understood, leading to suboptimal economic outcomes such as ineffective budgeting, underutilization of wealth-building tools, and potential tax non-compliance. This study employs a Cross-Sectional Correlational Design to administer a structured questionnaire to a targeted sample of 300 university students and recent graduates. It measures both the Tax Literacy Score (TK-e.g., understanding marginal tax rates, deductions, and tax-advantaged vehicles) and the Financial Decision-Making Quality Score (FDMQ-e.g., participation in 401(k)/IRA plans, budgeting accuracy, and debt management strategies). Results are expected to strongly confirm a significant positive correlation-such as r≥0.60-between, between TK and FDMQ. It is expected that MLR Analysis will demonstrate that the TK Score is a statistically stronger predictor of FDMQ-β coefficient analysis than general financial literacy, with particular emphasis on driving strategic behaviours such as retirement savings participation. The key implication is that tax knowledge provides the structural foundation necessary to ensure effective financial planning. The paper concludes with an urgent call for targeted educational interventions at the secondary and tertiary levels to integrate practical tax education, thereby fostering fiscally responsible citizenship and long-term economic security among young people.
| 31 |
Author(s):
Hamsa A.
Page No : 1-6
|
Career Path Recommendation System Using AI
Abstract
Choosing the right career has become increasingly challenging due to rapidly evolving technologies, shifting industry expectations, and the wide range of opportunities available to students and job seekers. Traditional career guidance often depends on generic assessments or single-session counselling, which do not reflect individual strengths or real-time market demands. The Career Path Recommendation System Using AI is designed to fill this gap by offering a personalized, intelligent, and data-driven approach to career planning. To provide personalized career recommendations the system assesses a users aptitude interests technical proficiency and educational background. It provides pertinent and useful advice by combining artificial intelligence natural language processing and current market insights. The system offers role-based assessments performance tracking and the creation of professional documents like cover letters and resumes in addition to career recommendations. The platform assists people in identifying their strengths comprehending industry trends and effectively preparing for their intended career paths thanks to its user-friendly interface and frequent updates. In the end the system provides a cutting-edge flexible and easily accessible solution that enables people to make confident and well-informed career decisions. Keywords: NLP AI skill evaluation career counseling career recommendation and personalized learning. .
| 32 |
Author(s):
G.VIGNESHWARAN.
Page No : 1-6
|
Digital Transformation of Primary Agricultural Cooperative Credit Societies (PACCS): Pathway to Financial Inclusion and Rural Livelihood Development in Tamil Nadu
Abstract
This study examines how the digital transformation of Primary Agricultural Cooperative Credit Societies (PACCS) in Tamil Nadu is improving financial inclusion and supporting rural livelihood development. PACCS has gradually adopted digital tools, including mobile applications, e-passbooks, online payment systems, SMS alerts, and core banking platforms, to provide faster and more transparent services. Secondary data from government reports, cooperative department publications, NABARD documents, and academic sources were analysed to understand trends in technology adoption, digital credit delivery, SHG linkage, and member service usage. The findings show that digitalisation has enabled timely KCC loans, smooth online transactions, faster insurance payments, and direct benefit transfers for rural households. SHGs and women members have gained easier access to credit and improved savings practices through digital platforms. The study concludes that digital services reduce dependence on informal credit, strengthen financial access for marginalised groups, and contribute positively to income stability, farm productivity, and overall livelihood improvement in rural Tamil Nadu.
| 33 |
Author(s):
S.NITHYA.
Page No : 1-7
|
THE IMPACT OF E-GOVERNMENT PORTALS ON PUBLIC SERVICES
Abstract
THE IMPACT OF E-GOVERNMENT PORTALS ON PUBLIC SERVICES
Dr.T.REVATHI,
RESEARCH SUPERVISOR, CMS INSTITUTE OF MANAGEMENT STUDIES, AFFILIATED TO BHARATHIAR UNIVERSITY , COIMBATORE-641049.
MRS.S.NITHYA,
RESEARCH SCHOLAR ,CMS INSTITUTE OF MANAGEMENT STUDIES AFFILIATED TO BHARATHIAR UNIVERSITY , COIMBATORE-641049.
ASSISTANT PROFESSOR IN DEPARTMENT OF COMMERCE CA,
N.M.S.SERRMATHAI VASAN COLLEGE FOR WOMEN IN MADURAI.6250012
ABSTRACT
This study investigates the impact of e-government portals on the delivery of public services, with an emphasis on how digital platforms are changing relationships between governments and citizens. E-government portals seek to improve efficiency, openness, and accessibility in public service delivery by digitizing old administrative procedures. The study looks at key factors such as service accessibility, customer satisfaction, cost-effectiveness, and administrative efficiency. Through a review of case studies and current research, the paper demonstrates how well-designed portals can cut service delivery times, boost citizen involvement, and reduce corruption by reducing human interaction. Please let me know if you want it adapted to a specific country or region.. However, the study also cites issues such as digital literacy gaps, restricted internet connection in remote areas, and worries over data protection. The findings indicate that, while e-government portals have the potential to greatly improve public service delivery, their success is heavily reliant on inclusive policies, solid infrastructure, and citizen trust. Recommendations are made to improve the effectiveness and reach of these digital governance efforts.
KEYWORDS:
E-Government , Digital Portals, Administrative Efficiency, Citizen Engagement, Public Service Delivery , Government Transparency , Access to Online Services
| 34 |
Author(s):
Karthik R K,Sudeep G A,Srujankumar Singhashetti.
Page No : 1-7
|
Voice Controlled Car Using ESP32
Abstract
This project presents the design and implementation of a robotic vehicle operated through voice commands. An Android application, interfacing with a microcontroller, is employed to transmit the required instructions. Communication between the Android device and the robotic system is established using Bluetooth technology, enabling the user to control the robot via spoken commands or on-screen buttons within the app.The robotic vehicle's movement is powered by two DC servo motors connected to the microcontroller on the receiving end. The Bluetooth RF module converts the input commands from the application into digital signals, which are transmitted over a range of approximately 100 meters. These signals are then decoded by the receiving unit and processed by the microcontroller, which in turn directs the motors to execute the intended actions. The main objective of this Voice Controlled Bluetooth Car is to carry out tasks in response to voice commands given by the user.To ensure effective operation, a preliminary calibration or training session is conducted, allowing the system to accurately interpret the voice commands. The control logic is embedded within the microcontroller’s code, ensuring smooth interaction between the user and the robot.Beyond its current form, the system can be further enhanced to improve performance and adaptability. Potential applications include military operations, home security, disaster recovery, industrial automation, and healthcare assistance.
| 35 |
Author(s):
Satyam.
Page No : 1-7
|
Decentralized Stable Coin
Abstract
This research paper presents an in-depth study of a decentralized, USD‑pegged
algorithmic stablecoin (similar to MakerDAO’s Dai). We explore its design,
implementation, and innovations, including multi-asset collateral (ETH and BTC),
an on-chain health‑factor mechanism for overcollateralization, and algorithmic
peg maintenance. We compare this protocol to existing stablecoins (DAI, USDC,
TerraUSD/UST, FRAX, etc.), analyze risks and advantages, and outline its
potential use cases. The methodology involves smart-contract development on
Ethereum-compatible blockchains (including zero-knowledge rollups) using tools
like Foundry/Anvil, as well as economic modeling and simulation. Key features
include a dynamic collateral ratio enforced via a health factor metric and
automated supply adjustments. Our coin aims for decentralization and stability,
leveraging lessons from established stablecoins
| 36 |
Author(s):
Sudhakar Kumar Trivedi.
Page No : 1-7
|
Predictive Analytics for Student Performance: A Comprehensive Synthesis of Methodologies, Algorithms, and Educational Implications
Abstract
This paper explores the critical role of Predictive Analytics in education, specifically focusing on forecasting student performance to mitigate high attrition rates. By synthesizing findings from Educational Data Mining (EDM) and Learning Analytics (LA), the study examines the efficacy of various Machine Learning (ML) algorithms, ranging from traditional classifiers like Logistic Regression and Random Forests to advanced Deep Learning architectures such as Long Short-Term Memory (LSTM) networks. The analysis highlights the importance of data granularity, contrasting static demographic features with dynamic behavioral logs, and identifies early prediction as a key challenge for effective intervention. Comparative benchmarks reveal that while Deep Learning excels in processing sequential clickstream data, ensemble methods like XGBoost and Random Forest remain dominant for structured data due to their balance of accuracy and interpretability. The paper concludes by advocating for hybrid systems that integrate the predictive power of complex algorithms with Explainable AI (XAI) techniques, ensuring that insights are actionable for educators and stakeholders.
| 37 |
Author(s):
Shalu Singh.
Page No : 1-8
|
Chatbot for University Enquiry Management System
Abstract
The rapid growth of artificial intelligence has enabled the creation of highly advanced chatbots that significantly improve user interaction. This research introduces an AI-powered chatbot system designed for university students to address academic and administrative queries effectively. The system supports both voice and text interaction by integrating Google’s Speech-to-Text API along with traditional text-based communication. Using natural language processing (NLP) techniques such as tokenization, lemmatization, and part-of-speech tagging, the chatbot analyses user queries and identifies their intent by matching them with predefined responses stored in a JSON knowledge base.[1][4] Acting as a virtual assistant, the chatbot provides accurate, context-aware answers related to admissions, timetables, examination schedules, and other campus information. The model is flexible and can be adapted to different domains simply by updating the intent dataset. Experimental results demonstrate that the system improves response time, enhances user satisfaction, and offers a scalable solution for automated student support. Overall, this study highlights the transformative potential of AI-driven chatbot in educational environments for real-time and efficient query handling.
| 38 |
Author(s):
Vikas Singh.
Page No : 1-8
|
IoT-Based Disaster Management and Early Warning System
Abstract
Disastrous events are cordially involved with the momentum of nature. As such mishaps have been showing off own mastery, situations have gone beyond the control of human resistive mechanisms far ago. Fortunately, several technologies are in service to gain affirmative knowledge and analysis of a disaster’s occurrence. Recently, Internet of Things (IoT) paradigm has opened a promising door toward catering of multitude problems related to agriculture, industry, security, and medicine due to its attractive features, such as heterogeneity, interoperability, light-weight, and edibility. This paper surveys existing approaches to encounter the relevant issues with disasters, such as early warning, notification, data analytics, knowledge aggregation, remote monitoring, real-time analytics, and victim localization. Simultaneous interventions with IoT are also given utmost importance while presenting these facts. A comprehensive discussion on the state-of-the-art scenarios to handle disastrous events is presented. Furthermore, IoT-supported protocols and market-ready deployable products are summarized to address these issues.
| 39 |
Author(s):
Rahul Choudhary.
Page No : 1-8
|
The Evolution of Financial Literacy Research in India: A Bibliometric Analysis (2014–2024)
Abstract
This study conducts a bibliometric analysis of financial literacy research in India from 2014 to 2024 using Scopus and Web of Science data. The findings show a clear evolution in research focus—from financial access and account usage following PMJDY, to digital financial literacy and fintech adoption after demonetization, and finally to financial resilience and behavioural finance during the COVID-19 period. Using VOSviewer and Biblioshiny, the study maps major publication trends, influential authors, and emerging thematic clusters, revealing a shift toward digital competence, cyber hygiene, and sustainable finance. Despite rapid growth in research output, fragmentation across disciplines and gaps in addressing digital vulnerabilities persist. The study provides a comprehensive intellectual overview of the field and offers insights for future research and for strengthening the National Strategy for Financial Education (2020–2025).
| 40 |
Author(s):
Vishnu V.
Page No : 1-8
|
The Behavioral Dynamics of Retail Investment and Intraday Trading Strategies in India: A Secondary Data Analysis of Financial Literacy and Digital Adoption (2014–2024)
Abstract
This study examines how retail investment and intraday trading behavior in India evolved between 2014 and 2024 amid rapid digitalization and major policy shifts. Using secondary data and bibliometric analysis, it identifies how initiatives such as PMJDY, UPI adoption, demonetization, and the COVID-19 pandemic expanded market access but created an “Access–Ability Paradox,” where digital participation grew faster than financial literacy. The findings show that retail trading strategies are increasingly shaped by behavioral factors—overconfidence, financial attitude, social influence, and herd behavior—rather than technical knowledge. The rise of fintech platforms further encouraged speculative intraday activity through ease of use and gamified interfaces. The study concludes that improving digital financial literacy, cyber hygiene, and resilience-focused education is essential for sustainable participation in India’s rapidly evolving retail trading ecosystem.
| 41 |
Author(s):
Dr. K R Kaushik.
Page No : 1-8
|
From Kurukshetra to the Corporate Boardroom: A Comprehensive Analytical Study of the Correlation between the Śrīmad Bhāgavad-Gītā and Modern Management Thought with Textual Evidence from Srimadbhagvad Gita
Abstract
This paper investigates the correlations between the teachings of the Śrīmad Bhāgavad-Gītā (hereafter “Gītā”) and contemporary management thought. Using a qualitative hermeneutic approach, key ślokas from the Gītā (presented in Devanagari and transliteration) are analysed and mapped to modern management principles—leadership, decision-making under uncertainty, delegation, motivation, ethics and corporate governance, stress and resilience, change management, conflict resolution, team dynamics, and strategic thinking. The analysis demonstrates that Gītā’s prescriptive and philosophical guidance provides actionable management wisdom that aligns with, and in some cases anticipates, modern organizational theory. The paper concludes with implications for managerial practice, pedagogy, and future research.
| 42 |
Author(s):
Babagana Ali Dapshima.
Page No : 1-9
|
Secure Image Management in Healthcare and Industry Through Deep Learning and Cryptographic Approaches
Abstract
Securing electronic health records (EHRs) within the Internet of Medical Things (IoMT) ecosystem remains a major challenge due to the complex and evolving nature of healthcare environments. As digital systems expand, maintaining the confidentiality, integrity, and accessibility of medical image data becomes increasingly difficult. Cryptographic techniques offer a foundational approach for protecting sensitive medical images during transmission and storage, while deep learning provides new opportunities to transform traditional encryption processes. This study investigates the integration of deep learning and cryptography to strengthen medical image security. It examines methods such as weight analysis to enhance encryption robustness and the use of chaotic systems to generate highly secure, undetectable encryption patterns. The study also reviews current deep learning–based anomaly detection approaches used in operational settings, focusing on network architectures, supervision models, and evaluation standards. Findings indicate that combining deep learning with cryptographic methods provides strong protection, improved resolution, and enhanced detection capabilities for medical image security. The paper further identifies challenges and opportunities in healthcare and industrial image protection, highlighting the need for continued research to address emerging threats and optimize system performance. By bridging the gap between deep learning and cryptography, this work contributes to improved privacy, integrity, and availability of critical image data across healthcare and industrial sectors.
| 43 |
Author(s):
Ruma Bala.
Page No : 1-9
|
THE ROLE OF SUSTAINABLE ENERGY INNOVATIONS IN REDUCING CARBON EMISSIONS
Abstract
Global energy systems are increasingly challenged by rising carbon emissions, accelerating climate change, and growing dependence on fossil fuels. Traditional energy infrastructures lack the flexibility and sustainability required to support long-term environmental goals, resulting in escalating ecological degradation and resource depletion. Recent advancements in renewable technologies, energy-storage systems, and intelligent energy management have introduced transformative opportunities for reducing greenhouse gas emissions through sustainable energy innovations. However, a major limitation in many existing decarbonization strategies is the reliance on conventional renewable deployment models that lack integration, scalability, and dynamic optimization. This restricts the ability to achieve deep emission reductions across diverse industrial and societal sectors.
This research proposes a comprehensive analytical framework that evaluates the role of next-generation sustainable energy innovations—such as high-efficiency solar photovoltaics, offshore and floating wind systems, green hydrogen production, bioenergy advancements, and AI-enabled smart grids—in reducing global carbon emissions. The study employs lifecycle emission modeling, efficiency analysis, and technological performance assessment to examine how integrated renewable systems can significantly reduce CO₂ output. Experimental and statistical evaluations demonstrate improved energy efficiency, enhanced grid stability, and substantial emission reduction compared to conventional energy practices. The findings highlight the potential of sustainable energy innovations to serve as a cornerstone for global decarbonization, energy transition, and long-term environmental resilience.
| 44 |
Author(s):
Uday Kumar.
Page No : 1-9
|
Smart Waste Management System Using IoT and Machine Learning for Industrial Waste
Abstract
Industrial waste management faces critical challenges due to increasing waste
volumes, hazardous materials, and stringent environmental regulations.
Traditional waste collection and disposal methods are often inefficient and unable
to cope with the dynamic nature of industrial waste generation. This paper
proposes a comprehensive IoT-based smart waste management system tailored
for industrial environments. The system integrates sensors on waste bins and
transport vehicles, GPS tracking for real-time location data, and machine learning
(ML) for intelligent analytics. The architecture comprises sensor-equipped smart
bins that monitor fill levels and waste composition, edge devices and connectivity
modules (e.g. LoRaWAN, NB-IoT), cloud-based data processing, and a user
interface for operators. GPS devices on collection trucks enable dynamic routing
and monitoring. Machine learning is applied for tasks such as waste
classification, fill-level prediction, route optimization, and anomaly detection.
Figures illustrate the system architecture, data flows, and sensor network. We
evaluate performance through literature case studies and simulations: IoT
enabled routing can reduce collection distance by ~21%, while ML classifiers
achieve >95% accuracy. Key benefits include reduced fuel use and emissions,
timely waste pickups, and improved recycling. We discuss challenges of
scalability, energy efficiency (e.g. low-power sensors), and data privacy, and
suggest future directions such as edge AI and robust security. This work
demonstrates that an integrated IoT+ML platform can greatly enhance industrial
waste management effectiveness.
| 45 |
Author(s):
Paritosh Nevase.
Page No : 1-10
|
Intelligent Trading Systems: An Integrated Framework for Adaptive Execution and Machine Learning-Driven Market Simulation
Abstract
The exponential growth of retail investors in Indian
equity markets has created a critical need for accessible, datadriven
decision support systems. This paper presents a novel
hybrid machine learning platform that combines Random Forest
classification, technical analysis, and sentiment analysis to
generate actionable trading signals for National Stock Exchange
(NSE) listed securities. The system addresses the limitations of
pure machine learning approaches, which are prone to overfitting
in financial time-series prediction, by integrating domain-specific
technical indicators and news sentiment into a weighted ensemble
model.
The proposed methodology employs Random Forest classifiers
trained on 25 technical indicators including RSI, MACD,
Bollinger Bands, Stochastic Oscillator, and volume-based metrics,
calculated from five years of historical OHLCV data for 15
NSE large-cap stocks. A hybrid signal generation algorithm
combines ML predictions (40% weight), technical analysis scores
(40% weight), and sentiment analysis (20% weight) to produce
BUY/SELL/HOLD recommendations with confidence levels. The
system achieves 62.3% average prediction accuracy on test data,
outperforming pure ML models (58.1%) and pure technical
analysis (54.7%) by 4–8 percentage points.
The full-stack implementation integrates the ML pipeline into
a production-ready web application featuring paper trading simulation
with 100,000 virtual capital, real-time portfolio analytics
including Sharpe ratio and maximum drawdown calculations,
interactive candlestick charts with technical indicator overlays,
and community-driven features for collaborative learning. The
platform demonstrates practical deployment of machine learning
models in financial applications while maintaining sub-500 ms
inference latency for real-time predictions.
Experimental results on historical data (2020–2025) demonstrate
that portfolios following the hybrid signals achieve an
average Sharpe ratio of 1.47, significantly higher than random
trading (0.23) and buy-and-hold strategies (0.89). The system
successfully handles 100+ concurrent users with 95% of API
requests completing within 2 seconds, validating its scalability
for educational and research applications. This work contributes
a novel hybrid architecture for financial prediction, demonstrates
end-to-end ML deployment patterns, and provides an opensource
educational platform addressing the accessibility gap in
Indian financial technology.
| 46 |
Author(s):
taniya,vanshika garg,vanshika saini,abhishek kumar.
Page No : 1-10
|
ai based comic strip genreator
Abstract
Creating comic strips usually requires drawing skills, creativity, and a good amount of time. Many students who have ideas for short stories are unable to convert them into visual comics because they cannot draw or design. This study explores a simple system that helps users turn written stories into comic-style panels. The system reads the user’s text, identifies the main characters, actions, and scenes, and then produces images that match the story. These images are arranged into panels, and short captions or dialogues are added based on the user’s input.
The aim of the project is to make comic creation easy for beginners, students, and educators. The method focuses on understanding the user’s text clearly and generating scenes that follow a consistent order. The system was tested with short stories and dialogues. The results show that users can create small comic strips quickly without drawing anything. The comics maintained story flow and visual clarity, making them suitable for presentations, learning materials, and social media storytelling.
This work shows that text-based comic generation can support creative expression and save time for users who are not skilled in artwork. Further improvements can make the system better at keeping character appearance consistent and allow more customization options for comic layouts.
| 47 |
Author(s):
Ujjawal Singh.
Page No : 1-10
|
Utilizing Artificial Intelligence Techniques for Wrong-Side Vehicle Recognition and Alerting
Abstract
Incidents involving wrong-way driving (WWD) represent a traffic danger often resulting in severe collisions and deaths. This article presents a detection system for wrong-way driving utilizing computer vision and deep learning techniques aimed at real-time traffic supervision and law enforcement. The approach integrates the YOLOv4 object detection model, centroid tracking for vehicle movement analysis and Automatic License Plate Recognition (ALPR), for identifying violators. Through observation of video feeds from traffic cameras the system accurately detects vehicles traveling against the flow captures their license plates and stores the data in a Firebase database for subsequent analysis and enforcement. This enhanced system incorporates improvements, over existing techniques, including refined centroid tracking methods, adaptive median line calibration and robust performance under challenging environmental factors. Test outcomes demonstrate that the system effectively and dependably identifies wrong-way driving events. The article provides an overview of the system design, algorithms, implementation specifics and experimental assessment highlighting the solutions capability to improve road safety and reduce WWD-related incidents.
| 48 |
Author(s):
RAHUL KUMAR GUPTA, SARVESH SINHA.
Page No : 1-17
|
A Decentralized Document Verification System using Self-Sovereign Identity with IPFS and Smart Contracts
Abstract
Document verification in traditional systems suffers from centralized control, single points of failure, and lack of user sovereignty over personal credentials. This paper presents a novel decentralized document verification system based on Self-Sovereign Identity (SSI) principles, integrating IPFS for distributed storage with smart contracts for immutable verification. Our three-tier architecture comprises users who maintain full control over their documents, verifiers who can authenticate document integrity through QR code scanning, and authorities who manage verifier permissions through blockchain-based access control. The system stores document content on IPFS while maintaining metadata and cryptographic hashes on-chain, ensuring both privacy and verifiability. Users upload documents to IPFS, generate QR codes containing document identifiers, and register hash values in smart contracts. Verifiers scan QR codes to retrieve documents and verify authenticity by comparing stored hashes with computed values through smart contract functions. Security analysis demonstrates resistance to tampering, unauthorized access, and single points of failure. Performance evaluation shows efficient gas usage, scalable verification times, and reduced storage costs compared to fully on-chain approaches. The system addresses critical limitations of existing identity management solutions by providing genuine user sovereignty, eliminating central authorities, and enabling privacy-preserving verification. This work contributes a practical SSI implementation suitable for academic credentials, government documents, and enterprise certificate management, advancing the field of decentralized identity systems.
