Volume 9 Issue 3
Author's Name: Juhaeri, Ali Maddinsyah, Sewaka
Abstract—— In the view of massive content explosion in World Wide Web through diverse sources, it has become mandatory to have content filtering tools. The filtering of contents of the web pages holds greater significance in cases of access by minor-age people. The traditional web page blocking systems goes by the Boolean methodology of either displaying the full page or blocking it completely. With the increased dynamism in the web pages, it has become a common phenomenon that different portions of the web page holds different types of content at different time instances. This paper proposes a model to block the contents at a fine-grained level i.e. instead of completely blocking the page it would be efficient to block only those segments which holds the contents to be blocked. The advantages of this method over the traditional methods are fine-graining level of blocking and automatic identification of portions of the page to be blocked. The experiments conducted on the proposed model indicate 88% of accuracy in filtering out the segments.
Author's Name: Danjunior and Makesh kumar
Abstract— — In the view of massive content explosion in World Wide Web through diverse sources, it has become mandatory to have content filtering tools. The filtering of contents of the web pages holds greater significance in cases of access by minor-age people. The traditional web page blocking systems goes by the Boolean methodology of either displaying the full page or blocking it completely. With the increased dynamism in the web pages, it has become a common phenomenon that different portions of the web page holds different types of content at different time instances. This paper proposes a model to block the contents at a fine-grained level i.e. instead of completely blocking the page it would be efficient to block only those segments which holds the contents to be blocked. The advantages of this method over the traditional methods are fine-graining level of blocking and automatic identification of portions of the page to be blocked. The experiments conducted on the proposed model indicate 88% of accuracy in filtering out the segments.
Author's Name: Anita nikil, Durairaj
Abstract— Due to the arrival of new technologies, devices, and communication means, the amount of data produced by mankind is growing rapidly every year. This gives rise to the era of big data. The term big data comes with the new challenges to input, process and output the data. The paper focuses on limitation of traditional approach to manage the data and the components that are useful in handling big data. One of the approaches used in processing big data is Hadoop framework, the paper presents the major components of the framework and working process within the framework.
Author's Name: Raman Vasanth, Subramaniya Karthik
Abstract— Advent of smart phones has brought with it revolution in mobile applications that are available for everyday functions. In this paper we review security requirements for apps from different domains that are communicating sensitive information over insecure network. Some of these apps are already available and some are expected to be introduced in future. We find that there are many parameters that affect security of apps but some are prominent compared to others based on domain of the app. Based on analysis of security requirements we determine the application domain most suitable for implementation of our proposed protocol.
Author's Name: Sheeba Venket, K.Chandrasekhara Rao
Abstract— Companies are doing marketing or branding of their products and services using digital media. Life is becoming so smooth and transparent by the sharing of information through the digital mediums. Whether it is a small or a big company, everybody is running for the competition, because they want to lock their customers. In this paper current market scenario is included with respect to cloud computing solution. Data access at present has limitations. Government data which is publicly accessible should have some policy. Cloud Computing is likely to be one of the key pillars on which various e-Governance services would ride. Digital India is a program to prepare India for a knowledge future. Digital India should have policy wherein the Government will be providing information and services to internal and external stakeholders. Cloud computing has become the most stimulating development and delivery alternative in the new millennium. A lot of departments are showing interest to adopt Cloud technology, but awareness on Cloud security needs to be increased. The adoption of Cloud is helping organizations innovate, do things faster, become more agile and enhance their revenue stream. In this paper, the information regarding cloud services and models are provided. Also, the main focus is on what government can do with the help of it for Digital India mission?
Author's Name: Saurabh S. Hher, Dhainje V. S
Abstract— In India large population is living all over the country and electricity supply demand need for this population makes recruitment of a large transmission and distribution system. Formulation of Transmission tower is proffered in assessment of confronting high voltage transmitting conductors and insulators to stance in need of altitude from ground level. Transmission Line Towers comprise of about 28 to 45 percent of the absolute cost of the Transmission Lines. The purpose of a transmission line tower is to support conductors booming electrical power and one or two ground wires at appropriate distances above the ground level and from each other. The observations from both structural and electrical fields are analysis in designing transmission line towers. There are various factors which influence the stability and performance of transmission tower are viewed in this paper. This Paper discussed and review the Methodology adopted for Analysis and Design of transmission towers. This paper can also be used for study of different parameters used in Analyzing and Designing of transmission towers.
Author's Name: Mangal Kalyani, Gupta Raju
Abstract— In this paper we are merely want to explore digital image processing which is a motivating field because it provides the higher image information for human understanding and process the image for storage, transmission, and illustration for machine perception. Image process could be a technique to reinforce raw pictures received from cameras/sensors placed on satellites, aircrafts or photos taken in traditional everyday life for varied applications. Pre-processing is the initial process applied on images which are at lowest level of abstraction. Also Shape analysis methods play an important role in systems for object recognition, matching, registration, analysis, accurate detection of image, Research in shape analysis has been motivated in part, for fast recognition of image from large data base. Accessing the desired and relevant image from large data base in an efficient manner is another motive for research. Various techniques of shape detection are based on shape boundary or interior.
Author's Name: Raju Patel, Rishil Mayank
Abstract— The use of different types of pavement block has been increased in India a decade ago. The specific requirements of paver block has been increased in the areas of footpaths and parking areas. Port land Cement Concrete and Asphalt Concrete are the most common roadway and highway construction material used. It is very necessary to use the materials which is durable and have the high compressive strength and can absorb the water to greater extent to have the greater water absorption value. In this project we have given greater stress on about the use of materials and machinery involved for the manufacture of different types of paver block in construction Purposes. For design of paver block the tests is to be performed is used to find the compressive strength and water absorption. The blocks having greater compressive strength and of less cost and can be used for much more time have been studied out in this project.
Author's Name: Gaurav Paniwal, Shruti Gupta
Abstract— This work explores the tools and technologies used in smart agriculture. Artificial Intelligence and Machine Learning techniques, including basic block models that are used to do smart agriculture. How can we use fuzzy logic and Artificial Neural Network, is also covered in this paper. We have explored some of the IOT based irrigation systems including crop prediction systems. The necessary hardware, software and sensors that can be used to make precision agriculture are also included. The main motto of this paper is to get a detailed literature review that is required for smart agriculture.
Author's Name: Aaditya Sharma, Aman Sharma, Punit Sharma, Punit Ekka
Abstract— Physically challenged people or the people with disabilities are those section of the society in which the society embarks no decision or gives any judgement about their physical abilities of the working body parts and the other requirements of them according to their physical fitness as well, the present generation has the awareness regarding keeping themselves fit and sportingly active but on the other hand the people who are physically challenged are unable to work on the same. The project hereby tries to implement the solution for the same by giving the various physical exercises that could be done by the physically challenges people according to their working body parts and according to their ability accordingly.
Author's Name: Santhosh, Sai Laxmi
Abstract— Identifying of the plant diseases is essential in prevention of yield and volume losses in agriculture Product. Studies of plant diseases mean studies of visually observable patterns on the plant. Health surveillance and detecting diseases in plants is essential for sustainable development agriculture. It is very difficult to monitor plant diseases manually. It requires a lot of experiences in work, expertise in these field plant diseases and also requires excessive processing time. Therefore; image processing is used to detect plant diseases. Disease detection includes steps such as acquisition, image Pre-processing, image segmentation, feature extraction and Classification. We describe these methods for the detection of plant diseases on the basis of their leaf images; automatic detection of plant disease is done by the image processing and machine learning. The different leaf images of plant disease are collected and feature extracted of the various machine learning methods
Author's Name: Shubham Kumar, Kanchan Bhatt
Abstract— Weather Forecasting is the attempt to predict the weather conditions based on parameters such as temperature, wind, humidity and rainfall. These parameters will be considered for experimental analysis to give the desired results. Data used in this project has been collected from various government institution sites. The algorithm used to predict weather includes Neural Networks(NN), Random Forest, Classification and Regression tree (C &RT), Support Vector Machine, KNN Nearest neighbor. The correlation analysis of the parameters will help in predicting the future values. This web based application we will have its own chat bot where user can directly communicate about their query related to Weather Forecast and can have experience of two-way communication.
Author's Name: J.R.Arun Kumar, Naman Gupta, Harman Singh, Rahul Sharma, Prateek, Rahul Saini
Abstract— Abstract— The rapid growth of Artificial Intelligence (AI) and Natural Language Processing (NLP) has opened up new opportunities in digital education. It allows for personalized, interactive, and adaptive learning experiences. This project introduces a Personalized Learning Assistant Using GPT Models, an AI driven solution that helps students grasp academic concepts, resolve doubts, and improve subject mastery. The system uses advanced GPT-based language models to generate human-like explanations, step-by-step solutions, quizzes, and personalized study support in real time. By incorporating Retrieval Augmented Generation (RAG), the assistant boosts accuracy and reliability by grounding AI-generated responses in relevant educational materials. This reduces errors and keeps responses in line with the academic curriculum. The system includes a dynamic student profiling method that tracks performance, identifies strengths and weaknesses, and updates mastery levels based on assessments and interaction history. This allows the assistant to adjust to each learner’s pace, learning style, and areas of challenge, offering a customized learning path. Features like AI-generated quizzes, automated grading, progress tracking dashboards, and topic recommendations enrich the learning process, making the platform act like a complete virtual tutor.
Author's Name: Rarishma Kaushik, Rahesh Parmar
Abstract— Air pollution and its harm to human health has become a serious problem in many cities around the world. In recent years, research interests in measuring and predicting the quality of air around people has spiked. Since the Internet of things has been widely used in different domains to improve the quality for people by connecting multiple sensors. In this work an IOT based air pollution monitoring with prediction system is proposed. The internet of Things is a action interrelated computing devices that are given unique identifiers and the capability of exchange information over a system without anticipating that human to human or human to machine communication. The deep learning algorithm approach is to evaluate the accuracy for the prediction of air pollution. The main objective of the project is used to predict the air Quality. The large dataset works with LSTM for better air quality prediction. The prediction accuracy of air quality with LSTM, the evaluation indicator Root means square error is chosen to measure performance.
Author's Name: P. Kavitha, S. Ramadevi
Abstract— Sentimental analysis is also called "opinion mining" analyses attitudes and classifies text views. It relates to the use of natural language processing, text, and linguistic processing. A huge amount of data is created with the rapid growth of web technologies. Social networking sites are now popular and normal places where feelings can be shared by short messages. These sentiments involve happiness, sadness, anxiety, fear, etc. The analysis of short texts tends to recognize the crowd's sentiment. Sentiment Analysis on IMDb moviereviews describes a reviewer's general feeling or impression of a movie. Since the perceptions of humans improve the effectiveness of products & since a movie'ssuccess or failure depending on its review, costs are rising, and a good sentiment analysis model needs to be developed, that classifies moviereviews. Machine learning methods use ML algorithms to carry out sentiment analysis as a standard classification problem using syntactic and language characteristics. There are some methods of machine learning used for sentiment analysis in this paper. Most of the sentiment analysis is performed using SVM, RF, ANN, and NB, Algorithms of DT, BN, & KNN.
Author's Name: Khaily Mohammed Shah,
Abstract— A human brain responds at a much faster rate to images and the information it contains. An image is considered as proof of past events that have occurred, but in today's world where editing tools are made available so easily tampering of images and hiding the original content has become too mainstream. The identification of these tampered images is very important as images are considered as vital sources of information in crime investigation and in various other fields. The image forgery detection techniques check the credibility of the image. Various research has been carried out in dealing with image forgery and tampering detection techniques, this paper highlights various the type of forgery and how they can be detected using various techniques. The fusion of various algorithms so that a complete reliable type of algorithm can be developed to deal mainly with copy-move and image splicing forgery. The copy-move and image splicing method are main focus of this paper.
Author's Name: Aditya Swami, shish Kumar
Abstract— By this research, we want to display the key factors of how effective blogging as technology is. We collected information curated by several researchers on the same for understanding their point of view as well. By doing this we found out what makes blogging the best way of sharing information online. We also analyzed the technological aspect of modern-day blogging which includes modern technologies being used, privacy rules and control as well as data analytics. By these approaches, we showed how blogging is not only the best medium for sharing information but can also help in other fields as well like marketing, education, data analysis, community development. With this research, we also wanted to highlight the downsides of using blogging or microblogging.
Author's Name: Gaurav Paniwal, Shruti Gupta
Abstract— This work explores the tools and technologies used in smart agriculture. Artificial Intelligence and Machine Learning techniques, including basic block models that are used to do smart agriculture. How can we use fuzzy logic and Artificial Neural Network, is also covered in this paper. We have explored some of the IOT based irrigation systems including crop prediction systems. The necessary hardware, software and sensors that can be used to make precision agriculture are also included. The main motto of this paper is to get a detailed literature review that is required for smart agriculture.
Author's Name: Tulshiram Bansod , Monali Shivram
Abstract— With the quick rise in living standards, people's shopping passion grew, and their desire for clothing grew as well. A growing number of people are interested in fashion these days. However, when confronted with a large number of garments, consumers are forced to try them on multiple times, which takes time and energy. As a result of the suggested Fashion Recommendation System, a variety of online fashion businesses and web applications allow buyers to view collages of stylish items that look nice together. Clients and sellers benefit from such recommendations. On the one hand, customers can make smarter shopping decisions and discover new articles of clothes that complement one other. Complex outfit recommendations, on the other hand, assist vendors in selling more products, which has an impact on their business. FashionNet is made up of two parts: a feature network for extracting features and a matching network for calculating compatibility. A deep convolutional network is used to achieve the former. For the latter, a multi-layer completely connected network topology is used. For FashionNet, you must create and compare three different architectures. To achieve individualised recommendations, a two-stage training technique was created.
Author's Name: Shubham Patil, Saurav Daware, Ameya Bhagat
Abstract— This paper is aimed at developing an Online College Management System that is of importance to the educational institute or college. This system is named College ERP using MERN stack. This system may be used to monitor college students and their various activities. This application is being developed for an engineering college to maintain and facilitate ease of access to information. For this the users must be registered with the system. College ERP is an Internet based application that aims at providing information to all levels of management within an organization. This system is used as an information management system for the college. For a given student and staff (technical and nontechnical) can access the system to either upload and access some information from the database.
Author's Name: S.Dhannabasava,M. Shennashetty, M.Majashekhar and K.Vijaykumar
Abstract— — Soft Computing techniques are fast growing technology used for problem solving, Information security is of essence factor in the age of computer world. Protecting information, systems and resources from unauthorized use, duplication, modification ,adjustment or any kind of cause which damage the resources such that it cannot be repaired or no longer exist to the real user is one of the part of soft computing. Researcher proposed several mechanism to fight against cyber attacks. Several existing techniques available intrusion detection systems are responsible to face upcoming cyber attacks. Soft computing is one of the best presently using techniques which is applied in Intrusion Detection System to manage network traffic and use to detect cyber attacks with increased efficiency and accuracy.
Author's Name: J.R.Arun Kumar, Gopal Sharma, Guddu, Saloni, Sneha
Abstract— — The aim of this project is to detect fake or synthetic human faces using deep learning technology to ensure digital trust and security.With the rapid rise of AI-generated deepfakes, fake human faces have become a serious concern for privacy, identity verification, and online authenticity. Therefore, early and accurate detection of such manipulated images is essential to prevent their misuse. This project employs a Convolutional Neural Network (CNN) model trained on the RVF10K dataset, which contains real and fake human face images. The CNN automatically learns distinctive facial patterns and features to accurately classify images as real or fake. The proposed model specifically works on human faces and rejects non-human images during detection.This system can be effectively utilized in social media verification, cybersecurity, and forensic investigations, providing a reliable tool to maintain the authenticity of human digital content and strengthen protection against AI-based facial forgeries.
Author's Name: M.Prabakaran, Ajay Kaurav, S.Sibi Chakkaravarthy
Abstract— In today's world, data is generated at a very rapid speed and final destination of such data is database. Data is stored in database for easy and efficient way to manage these data. All the operations of data manipulation and maintenance are done using Database Management System. Considering the importance of data in organization, it is absolutely essential to secure the data present in the database. A secure database is the one which is reciprocated from different possible database attacks. Security models are required to develop for databases. These models are different in many aspects as they are dealing with different issues of the database security. They may different also because of they are taking different assumptions about what constitutes a secure database. So, it becomes very difficult for database security seekers to select appropriate model for securing their database. In this paper, we have discussed some of the attacks that can be possible with its counter measures and its control methods that can be possible. Securing database is important approach for the planning of explicit and directive based database security requirements. Ensuring security for database is very critical issues for the companies. As complexity of database increases, we may tend to have more complex security issues of database.
Author's Name: J.R.Arun Kumar, Vinay Kumar, Tarun Yadav, Rishi Jangid, Pooja
Abstract— The proliferation of online job applications has led to an overwhelming volume of resumes for recruiters to screen. The manual review process is often time-consuming, prone to human error, and may result in the overlooking of highly qualified candidates. To address this challenge, this project introduces a web-based, AI-powered Resume Analyzer system. This application leverages advanced Natural Language Processing (NLP) techniques to automate the matching of candidate resumes with specific job descriptions. By parsing resumes and job requirements, the system quantitatively scores a candidate's fit, highlights essential keyword matches, and identifies skill gaps. The primary objective is to streamline the recruitment workflow, providing a rapid, objective, and efficient tool for both recruiters and job seekers to assess a candidate's suitability for a role, thereby saving time and improving hiring accuracy.
Author's Name: J. R. Arun Kumar, Lakshya Sharma, Akshat Sharma, Deepak Singh, Aditya Sharma, Himek Saini
Abstract—Rapid urbanization has placed increasing pressure on city administrations to manage road infrastructure and public safety effectively. Existing systems rely on manual inspections and reactive complaint portals that lack real-time automation and structured data collection. This paper presents City Guardian, an AI-powered urban monitoring platform that integrates deep learning-based hazard detection, citizen crowdsourcing, geolocation mapping, and an administrative analytics dashboard. The system employs a YOLOv8 object detection model to identify road anomalies — including potholes and open manholes — from smartphone images, achieving a detection confidence of 0.95. Geotagged reports are stored in a Firebase cloud backend and visualized on interactive maps, enabling municipal authorities to monitor and prioritize repairs in real time. A gamified Guardian Points mechanism incentivizes citizen participation while crowd-based verification maintains data integrity. The cross-platform mobile application, built with Flutter, delivers proximity-based hazard alerts and an invalid-report penalty system to prevent misuse. Experimental results demonstrate high detection accuracy and practical feasibility across real urban environments. City Guardian provides a scalable and proactive framework for smart city governance, aligned with national initiatives such as Smart Cities Mission and Digital India.
Author's Name: J.R.Arun Kumar, Shreya Mittal, Tanishka Vedi, Aryan
Abstract—The AI-Powered Fitness Assistant is an intelligent platform designed to help users achieve fitness goals through real-time posture analysis, personalized workout planning, and adaptive progress tracking. Using Computer Vision (MediaPipe Pose), Machine Learning, and a cross-platform mobile application, the system detects body keypoints, calculates joint angles, identifies exercise types, and provides instant corrective feedback. A user dashboard displays workout statistics, BMI, calories burned, and progress trends. The system eliminates the need for professional supervision by functioning as a costeffective virtual personal trainer accessible from any device with a camera.
Author's Name: J.R.Arun Kumar, Harshit Gupta, Meet Singh, Dhruv Mukhija, Sahibdeep Singh
Abstract—The rapid growth of scientific literature has created a significant challenge for researchers who must analyze, interpret, and synthesize large volumes of information within limited timeframes. Traditional manual research methods are slow, error-prone, and often insufficient for identifying hidden insights, research gaps, and relevant citations. Recent advancements in Natural Language Processing (NLP), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) provide an opportunity to automate and accelerate the research workflow. This project presents an NLP-Based Autonomous Research Assistant, a system designed to support researchers by automating literature analysis, summarization, question answering, and metadata extraction. The system enables users to upload research documents, extract meaningful chunks, generate vector embeddings, identify top-K relevant segments, and produce context-based answers with accurate citations. It integrates key technologies such as FastAPI for backend services, a React-based frontend interface, Chroma DB for vector storage, MongoDB for metadata storage, and an LLM service for generating high-quality responses. The proposed solution includes multiple components—document ingestion, embedding generation, semantic retrieval, autonomous gap analysis, dashboard visualization, and AI-supported summaries.
Author's Name:D.Venkatesan* , Vasanthapriyan V, Mukeshkumar S, Ragul R
Abstract— Physically challenged people or the people with disabilities are those section of the society in which the society embarks no decision or gives any judgement about their physical abilities of the working body parts and the other requirements of them according to their physical fitness as well, the present generation has the awareness regarding keeping themselves fit and sportingly active but on the other hand the people who are physically challenged are unable to work on the same. The project hereby tries to implement the solution for the same by giving the various physical exercises that could be done by the physically challenges people according to their working body parts and according to their ability accordingly.
Author's Name:J.R.Arun Kumar, Krishnakant, Harshit Jain, Mehul Agrawal, Aasif Khan
Abstract— In today’s fast-changing world, the job market has become highly competitive due to rapid technological growth and digital transformation. Companies now expect candidates to have not only theoretical knowledge but also practical skills, communication abilities, and confidence. However, many students and job seekers still depend on traditional methods of job preparation, which are not enough to meet current industry needs. One of the biggest problems is the gap between what students learn in college and what companies actually require. Many candidates face difficulties in creating effective resumes, preparing for interviews, and understanding job roles. Also, modern hiring processes use tools like Applicant Tracking Systems (ATS) and online tests, which make it harder for candidates to succeed without proper guidance. Artificial Intelligence (AI) can solve these problems by providing smart and personalized solutions. Technologies like Machine Learning (ML) and Natural Language Processing (NLP) can analyze user data, suggest improvements, and help candidates prepare better for jobs. In this project, we introduce an AI-Powered Job Preparation SaaS Platform that helps users prepare for jobs in a smarter way. The platform provides features like resume checking, ATS score analysis, mock interviews, and personalized learning plans. It also offers practice tests and performance tracking to help users improve their skills.
Author's Name: Ganesh Sahadevan, Padma Joseph
Abstract— This paper gives complete guidelines on BigData, Different Views of BigData, etc.How the BigData is useful to us and what are the factors affecting BigData all the things are covered under this paper. The paper also contains the BigData Machine learning techniques and how the Hadoop comes into the picture. It also contains the what is importance of BigData security. The paper mostly covers all the main point that affect Big Data and Machine Learning.
Author's Name: J. R. Arun Kumar, Lavish Saini, Hitesh Kumar, Menaka Sharma
Abstract— In today’s digital era, real-time monitoring systems play an important role in areas such as traffic management, security, and crowd control. This paper introduces an AI-based system for real-time object detection and counting using deep learning methods. The system uses the YOLOv8 model to identify different objects in video frames and applies a Kalman Filter to track their movement over time. A mobile application is developed using Flutter to provide a simple and user-friendly interface, while the backend is built using Python and FastAPI for efficient processing. The system is capable of handling both live video from a camera and recorded video files, delivering results instantly. WebSocket communication is used to maintain fast and continuous data exchange between the mobile application and the server. The experimental results show that the system performs well in detecting and counting objects with good accuracy and speed. Overall, the proposed system is useful for real-world applications that require quick, reliable, and automated monitoring.
Author's Name: J. R. Arun Kumar, Mayank, Mansi Gothwal, Akshita Sharma, Mohit Bambhani
Abstract— Choosing the right gift has become difficult today due to too many options and varying personal preferences. PresentAI simplifies this process by providing personalized gift suggestions based on factors like occasion, recipient, and budget. Instead of relying on complex AI models, it uses a structured, rule-based approach to filter and rank options, ensuring the results are relevant, diverse, and easy to understand. The platform also supports group gifting by allowing users to discuss, shortlist, and vote on ideas together. Built using React and Flask, PresentAI focuses on reliability, low cost, and clear explanations, making the overall gifting experience more practical and user-friendly..
Author's Name: Juhaeri, Ali Maddinsyah, Sewaka
Abstract—— In the view of massive content explosion in World Wide Web through diverse sources, it has become mandatory to have content filtering tools. The filtering of contents of the web pages holds greater significance in cases of access by minor-age people. The traditional web page blocking systems goes by the Boolean methodology of either displaying the full page or blocking it completely. With the increased dynamism in the web pages, it has become a common phenomenon that different portions of the web page holds different types of content at different time instances. This paper proposes a model to block the contents at a fine-grained level i.e. instead of completely blocking the page it would be efficient to block only those segments which holds the contents to be blocked. The advantages of this method over the traditional methods are fine-graining level of blocking and automatic identification of portions of the page to be blocked. The experiments conducted on the proposed model indicate 88% of accuracy in filtering out the segments.
Author's Name: J.R.Arun Kumar, Mukul Choudhary, Harsh Saini, Naveen Kanwat, Naveen Gurjar
Abstract— Legal documents are often written in highly technical and complex language filled with jargon, lengthy clauses, and intricate sentence structures. While these documents are critical for everyday matters—such as contracts, agreements, property papers, and government policies—most common people without legal expertise struggle to understand them. This lack of comprehension can lead to misinterpretation, dependency on costly legal consultations, and in some cases, unintentional violation of terms. There is a need for an accessible system that can automatically simplify complex legal language into plain, everyday language without losing the original meaning or context. By using advanced Natural Language Processing (NLP) techniques and powerful models , it is possible to bridge the gap between legal professionals and the general public,
Author's Name: Raman Vasanth, Subramaniya Karthik
Abstract— Advent of smart phones has brought with it revolution in mobile applications that are available for everyday functions. In this paper we review security requirements for apps from different domains that are communicating sensitive information over insecure network. Some of these apps are already available and some are expected to be introduced in future. We find that there are many parameters that affect security of apps but some are prominent compared to others based on domain of the app. Based on analysis of security requirements we determine the application domain most suitable for implementation of our proposed protocol.
Author's Name: J.R. Arun Kumar, Vivek Jangid, Nisha, Virendra Yadav, Monu
Abstract— Facial emotion recognition plays an important role in enabling intelligent systems to understand human emotions and enhance human computer interaction. This paper presents a deep learning based facial emotion detection system capable of identifying multiple emotional states from facial images. The model is trained on a standard facial expression dataset containing classes such as happy, sad, angry, surprise, fear, disgust, and neutral. A convolutional neural network is used to automatically extract features from preprocessed images, where preprocessing includes resizing, normalization, and augmentation to improve performance. The model is evaluated on test data to ensure reliable emotion classification. The system is deployed as a user friendly web application that supports both image upload and real time webcam input. It provides predicted emotions with confidence scores and includes an audio feedback feature for better user interaction. The proposed system offers an effective solution for real time facial emotion recognition with applications in intelligent systems and human computer interaction. Future work focuses on improving accuracy and enhancing system capabilities for real world use.
Author's Name: J.R.Arun Kumar, Nitesh Tiwari, Suyash Pradhan, Neeraj Sharma, Divyanshu Airan, Vinay Saini
Abstract— Phishing websites are a major cyber threat designed to steal sensitive information by imitating legitimate sites. Traditional blacklist-based methods are ineffective against newly generated phishing domains. This project proposes a machine learning–based phishing detection system that analyzes URL and domain-level features to classify websites as legitimate or phishing. Using models such as Random Forest and Logistic Regression, the system achieved an accuracy on benchmark datasets. The trained model is integrated into a Flask application, enabling users to check URLs, and a Chrome extension provides real-time alerts while browsing. This dual approach offers both high detection accuracy and practical usability, making it a reliable solution for enhancing online security. Phishing attacks are one of the most common cyber threats that aim to steal sensitive user information such as login credentials, banking details, and personal data by creating fraudulent websites that imitate legitimate ones. Due to the rapid growth of internet usage, phishing websites have become increasingly sophisticated and difficult for users to identify manually. Therefore, an effective automated detection system is required to protect users from such malicious attacks. The developed tool provides users with a simple interface where they can enter a website URL and receive a prediction about its authenticity. The results demonstrate that the system can effectively detect phishing websites and help reduce the risk of cyber fraud.
Author's Name: Mohit Sharma, Pulkit Gupta, Abhijeet Singh, Sahil Soni, Nehal Choudhary, Sonu Singh
Abstract— Phishing websites are a major cyber threat designed to steal sensitive information by imitating legitimate sites. Traditional blacklist-based methods are ineffective against newly generated phishing domains. This project proposes a machine learning–based phishing detection system that analyzes URL and domain-level features to classify websites as legitimate or phishing. Using models such as Random Forest and Logistic Regression, the system achieved an accuracy on benchmark datasets. The trained model is integrated into a Flask application, enabling users to check URLs, and a Chrome extension provides real-time alerts while browsing. This dual approach offers both high detection accuracy and practical usability, making it a reliable solution for enhancing online security. Phishing attacks are one of the most common cyber threats that aim to steal sensitive user information such as login credentials, banking details, and personal data by creating fraudulent websites that imitate legitimate ones. Due to the rapid growth of internet usage, phishing websites have become increasingly sophisticated and difficult for users to identify manually. Therefore, an effective automated detection system is required to protect users from such malicious attacks. The developed tool provides users with a simple interface where they can enter a website URL and receive a prediction about its authenticity. The results demonstrate that the system can effectively detect phishing websites and help reduce the risk of cyber fraud.
Author's Name: J. R. Arun Kumar, Yashi Garg, Anshika Jain
Abstract— The Face-Based Attendance System is an innovative automated solution designed to simplify and modernize the process of managing attendance in educational institutions and organizations. Traditional methods of attendance marking — such as manual roll calls or ID-based systems — are often time-consuming, prone to human error, and susceptible to fraudulent practices like proxy attendance. To overcome these limitations, this project utilizes face recognition technology, which offers a contactless, efficient, and highly reliable approach to verifying individual identity and recording attendance automatically. The system functions by capturing the facial image of a student or employee using a camera in real time. The captured image is then processed through advanced image processing and facial recognition algorithms. Key facial features are extracted and compared with the stored records in the database. If a match is found, the system marks the individual as “Present” and updates the attendance record in the database automatically. In the case of an unrecognized or undetected face, the system prompts for re-capture or manual verification. This process ensures high accuracy, consistency, and security in attendance tracking
Author's Name: J.R. Arun Kumar, Garima Avasthi, Abhinav Gupta, Aditya Kumar Mishra, Dipanshu
Abstract— The rapid advancement of Artificial Intelligence (AI) and Machine Learning (ML) has opened new doors in delivery of digital healthcare. This paper presents a solution in form of a comprehensive web-based platform that improves how patients access medical services, schedule appointments, and receive health guidance. There are two different ML-models in this project, one is for diabetes detection and other is an eye -disease detection model. The platform supports role- based access for patients, doctors, admins, lab assistants, and pharmacy. Key features include real- time appointment tracking, e-prescriptions, geo-location-based hospital recommendations, lab test booking, telemedicine via video consultation, and an emergency SOS module. The system addresses critical gaps in traditional healthcare like long queues, limited accessibility, poor transparency, and lack of intelligent guidance by offering a secure, scalable, and user-centric solution. Results demonstrate the platform's capability to serve as a full-stack healthcare ecosystem with ML-driven disease prediction, laying a strong foundation for future AI-powered public health management.
Author's Name: Sheeba Venket, K.Chandrasekhara Rao
Abstract— Companies are doing marketing or branding of their products and services using digital media. Life is becoming so smooth and transparent by the sharing of information through the digital mediums. Whether it is a small or a big company, everybody is running for the competition, because they want to lock their customers. In this paper current market scenario is included with respect to cloud computing solution. Data access at present has limitations. Government data which is publicly accessible should have some policy. Cloud Computing is likely to be one of the key pillars on which various e-Governance services would ride. Digital India is a program to prepare India for a knowledge future. Digital India should have policy wherein the Government will be providing information and services to internal and external stakeholders. Cloud computing has become the most stimulating development and delivery alternative in the new millennium. A lot of departments are showing interest to adopt Cloud technology, but awareness on Cloud security needs to be increased. The adoption of Cloud is helping organizations innovate, do things faster, become more agile and enhance their revenue stream. In this paper, the information regarding cloud services and models are provided. Also, the main focus is on what government can do with the help of it for Digital India mission?
Author's Name: Deepak Sharma, Dhruv Saini, Lily Singhal, Ankit Yadav, Mayank.
Abstract— India's Aditya-L1 mission features the SWIS instrument that allows a continuous recording of the solar wind ion flux, energy, and directional properties. For this purpose, it uses two Top- Hat Analysers covering 0.1–20 keV with full 360° angular coverage. The magnetic mass analyser in THA-1 separates H⁺ from He²⁺, thus allowing the accurate monitoring of helium abundance changes that frequently occur during the passing of halo CMEs and the structures connected to them. Such measurements provide a timeline for the arrival of the CME through the detection of early signatures like ion composition changes, speed, and High-Speed particle levels. By observing the time-dependent changes of the solar wind parameters measured by SWIS, the research intends to enhance the short-term forecasting of halo CME arrival at L1 and deepen the understanding of their impact. The multi-directional and adjustable configuration of the instrument enables it to keep a continuous record of the disturbances in the Heliosphere layer and be able to anticipate space weather.
Author's Name: Mohit Sharma, Piyush Jain, Adnan Danish, Rohan Sanwariya, Robin Sanwariya, Amar kumar pandey
Abstract— The rapid digital transformation in the education sector has created an urgent need for platforms that can streamline teaching, learning, and academic administration in both physical and virtual environments. Traditional learning methods often lack scalability, transparency, and real-time engagement, making it difficult for institutions to deliver personalized learning experiences and track student performance efficiently. Modern educational ecosystems require integrated, technology-driven solutions that support interactive content delivery, automated evaluation, and seamless communication. Learning Management Systems (LMS) have emerged as a crucial tool to address these challenges by providing flexible, scalable, and data-driven learning environments. This project presents a Learning Management System (LMS) designed to enhance academic delivery, improve learner engagement, and simplify instructor and administrator workflows.
Author's Name: R. Anusuya , Divyansh Mittal, Gajal Sharma, Bharti, Dimpal
Abstract— Mental health support has become essential today due to increasing stress, anxiety, and limited access to professional help. The Mental Health Companion simplifies this by providing real-time emotional support and guidance based on user input such as text or voice. It uses Natural Language Processing (NLP) to detect emotions and deliver personalized responses, mood insights, and stress-relief suggestions. Instead of relying entirely on complex models, the system follows a structured and modular approach to ensure reliable, fast, and understandable interactions. The platform also maintains user privacy and offers a safe space for open expression. Built using modern technologies, the Mental Health Companion focuses on accessibility, low cost, and continuous support, making mental health care more practical and user-friendly.
Author's Name: J.R.Arun Kumar, Mayank Kumar, Vaibhav Sharma, Naman Jain, Harshit Sharma
Abstract— Access to safe drinking water is a critical public health requirement. In many regions, water quality is still assessed manually or using laboratory-based chemical tests, which are often time-consuming, costly, and not scalable for continuous monitoring. This project presents Water Quality Prediction Using Deep Learning, a system that utilizes computer vision and deep learning to estimate water turbidity from images and optionally integrates user-provided TDS values to determine overall potability. The system allows the user to capture or upload an image of water in a container. A convolutional neural network (CNN)-based deep learning model predicts an approximate turbidity range directly from the image. The solution follows a modular approach: image acquisition, preprocessing, turbidity estimation using a deep learning model, fusion with optional TDS input, and final classification into Drinkable or Not Drinkable based on predefined thresholds inspired by standard water quality guidelines. The system can be deployed as a simple web application, enabling non-expert users to quickly check water quality without requiring chemical labs.
Author's Name: Dr. Anusuya, Vanshika Joshi, Vinay Kumar, Shriya Jain, Mohit Saini
Abstract— Visually impaired individuals often face significant challenges accessing essential product information such as ingredients, usage instructions, expiry details, and safety warnings independently. This project presents Vision-to-Voice, a web-based, AI-powered assistive system that leverages computer vision, Optical Character Recognition (OCR), Natural Language Processing (NLP), and Text-to-Speech (TTS) technology within a smartphone application. When a user scans a product using the camera, a Convolutional Neural Network (CNN) model detects the object and extracts printed text from the product label. The extracted text is processed to highlight relevant information such as usage guidelines, warnings, and key ingredients, which is then delivered as natural voice output through a speech synthesis engine. By combining intelligent recognition, flexible language processing, and a highly accessible interface, Vision-to-Voice enhances independence, convenience, and safety for visually impaired individuals.
Author's Name: Dr. Neeraj Jain, Ajeet Thakur, Mohit Shekhawat, Hardik Arora, Rohit Saini
Abstract— Navigating university websites for specific academic details is often frustrating. While generic AI chatbots offer conversational retrieval, they frequently hallucinate by pulling outdated statistics from third-party sources. To resolve this, this project introduces a specialized full-stack AI Assistant built exclusively for the Modern Institute of Technology & Research Centre (MITRC). The primary objective is to eliminate generative inaccuracies by forcing the AI to analyze only live institutional web pages. The system features a responsive HTML/Tailwind frontend and a secure Node.js backend using SQLite, bcrypt encryption, and JSON Web Tokens. Crucially, instead of relying on standard search APIs, the backend utilizes a custom Axios and Cheerio scraping engine. An intelligent routing algorithm dynamically extracts raw HTML text directly from targeted MITRC webpages. This domain-specific text is then passed to the Google Gemini Large Language Model. By setting the generation temperature to absolute zero, the AI acts solely as a rigid reading comprehension tool. This architecture completely mitigates hallucinations, providing users with precise, context-aware responses alongside verifiable source links.
