http://210.212.227.212:8080/xmlui/handle/123456789/294 2026-05-27T20:57:51Z 2026-05-27T20:57:51Z Abina, S Jasmin, M R http://210.212.227.212:8080/xmlui/handle/123456789/431 2023-07-15T06:40:23Z 2023-05-16T00:00:00Z

Title: AUTOMATED GRADING SYSTEM Authors: Abina, S; Jasmin, M R Abstract: AUTOMATED GRADING SYSTEM for essays refers to the utilization of computer programs to evaluate and score essays written in response to specific prompts. It involves automating the assessment process, which offers benefits to both educators and learners by facilitating iterative improvements in students’ writing skills. In traditional grading methods, evaluators need to manually read and evaluate each paper, which can be a time-consuming process, especially when dealing with a large number of papers. Automated grading systems leverage the power of machine learning algorithms to analyze essays and provide accurate grades. By implementing these systems, institutions can significantly reduce the time required for grading papers, allowing teachers to focus on other important tasks such as providing feedback to students. The proposed grading system mentioned in the project aims to use machine learning algorithms such as Linear Regression, support vector regression (SVR), and Random Forest (RF) to automate the grading process. By analyzing various features extracted from essays and incorporating natural language processing techniques, the system aims to accurately predict scores for essays in a timely and efficient manner. The effectiveness of the system is evaluated using mean squared error as a performance metric. The results demonstrate the potential of machine learning models in automating the grading process and providing reliable feedback to students.

2023-05-16T00:00:00Z Adharsh, H Fousia, M Shamsudeen http://210.212.227.212:8080/xmlui/handle/123456789/430 2023-07-15T06:37:56Z 2023-05-16T00:00:00Z

Title: SOLIDCROWD - CROWD FUNDING PLATFORM USING BLOCKCHAIN Authors: Adharsh, H; Fousia, M Shamsudeen Abstract: SOLIDCROWD - CROWD FUNDING PLATFORM USING BLOCKCHAIN, aims to lever age blockchain technology to create a new decentralized crowdfunding platform that removes intermediaries and enhances transparency and security. The platform will allow project creators to directly interact with backers, providing a transparent and secure environment for crowdfunding campaigns. By leveraging blockchain, the proposed crowdfunding platform eliminates the need for intermediaries, allowing direct interaction between project creators and backers. Smart contracts deployed on the blockchain ensure the transparent and immutable execution of crowdfunding campaigns. The decentralized nature of the blockchain network enhances security, mitigating the risk of fraudulent activities and increasing trust among participants. The project also aims to address the issue of financial inclusion by allowing backers to participate using various cryptocurrencies, thereby removing barriers associated with traditional banking systems. Smart contract functionality ensures automated and secure distribution of rewards or returns to project backers, reducing administrative overheads and increasing efficiency.

2023-05-16T00:00:00Z Afeef, KP Fousia, M Shamsudeen http://210.212.227.212:8080/xmlui/handle/123456789/429 2023-07-15T06:33:28Z 2023-05-16T00:00:00Z

Title: REAL-TIME YOGA POSE DETECTION AND CORRECTION Authors: Afeef, KP; Fousia, M Shamsudeen Abstract: With the increasing popularity of yoga and its numerous health benefits, it is crucial to ensure that practitioners are able to perform the poses correctly to avoid injury and maximize the benefits. However, traditional methods of learning and practicing yoga often lack real time feedback and guidance.This project addresses the need for an effective and user-friendly solution to enhance the practice of yoga and aims to develop a real-time yoga pose detection system that can accurately analyze and provide feedback on the user’s pose, helping them improve their form and achieve better results. The system incorporates the K-Nearest Neighbors (KNN) algorithm, Mediapipe library, and a dataset sourced from Kaggle. The KNN algorithm is employed for pose recognition, utilizing the distances between poses to classify and identify the closest match. Mediapipe library is utilized to extract pose landmarks from input video frames, providing valuable information for pose detection. The dataset from Kaggle serves as the training data, enabling the system to learn and recognize various yoga poses accurately. This combination of KNN, Mediapipe, and the Kaggle dataset enhances the system’s ability to perform real-time and accurate yoga pose detection, facilitating effective feedback and guidance for users during their yoga practice. The results obtained from the project demonstrate the effectiveness of the KNN-based system in accurately detecting and recognizing yoga poses in real-time. The accuracy of the system is evaluated using appropriate metrics, providing insights into its performance and ability to assist users in achieving correct poses. The findings of this project contribute to the development of interactive and reliable tools for yoga practitioners, enhancing their practice and improving pose correctness

2023-05-16T00:00:00Z Ajil, K Vaheetha, Salam http://210.212.227.212:8080/xmlui/handle/123456789/428 2023-07-15T06:29:54Z 2023-05-19T00:00:00Z

Title: IOT MANAGER - DEVICE MANAGEMENT Authors: Ajil, K; Vaheetha, Salam Abstract: IOT MANAGER - DEVICE MANAGEMENT, is a web application designed to provide a comprehensive solution for managing remote edge and IoT devices. It enables users to monitor, control, and configure devices from a centralized platform, making it easier to manage and maintain large networks of devices. The application provides a user-friendly interface that allows users to quickly and easily access device data and perform various operations. Users can view device status, track device performance, and set alerts for key metrics. The application also allows users to remotely control devices, enabling them to configure settings, update firmware, and troubleshoot issues. One of the key features of this application is its ability to handle large volumes of data from a variety of devices. It uses advanced analytics and machine learning algorithms to analyze data and generate insights that can be used to optimize device performance and improve operational efficiency. Overall, this web application provides a comprehensive solution for managing remote edge and IoT devices, helping users to reduce downtime, improve device performance, and streamline operations

2023-05-19T00:00:00Z