2024-25

Permanent URI for this collection

http://192.168.75.5:4000/handle/123456789/17735

Browse

Browsing 2024-25 by Title

Now showing 1 - 20 of 110
  • Thumbnail Image
    Item
    Adventures of thePixel Knight
    (NHCE, 2024) ARYAN B1NH21IS025, CHETHAN D1NH21IS043, DARENA PEARL S A1NH21CS063, AFIYA YOUSUF1NH21CS012
    The Adventures of the Pixel Knight is a fun 2D platformer game that uses Unity 2D and C# The game comes with a pixelated knight hero, giving the experience a retro feel that's full of dynamic challenges, combat mechanics, and strategic exploration. Designed to be accessible and scalable, the game utilizes WebGL technology, allowing players to enjoy the game right in their browsers without needing any additional downloads. This feature ensures a wider reach and enhances the overall gaming experience. This involves control of the knight to fight with enemies, avoid obstacles, and collect coins and potions. Coins are added to the player's score and, upon completing the game, it is a high score. The WebGL version features a local leaderboard system showing high scores for multiple players to encourage friendly competition and play repeatedly. The health system, yet another strategic addition, is such that the player is obliged to make wise decisions navigating the perfectly designed levels. Technical implementation emphasizes smooth and responsive controls through efficient C# scripting. Movement logic is optimized to prevent character sliding; this allows for smooth movement. Combat mechanics add complexity to the game, so the player needs to be as precise and strategic as possible in defeating enemy knights and bosses. The WebGL feature increases accessibility since leaderboard functionality may be displayed in real-time for visually appealing tracking of scores and encouragement of competitive play.
  • Thumbnail Image
    Item
    Agri-Smart 2.0
    (NHCE, 2024) AKASH S CHERIAN1NH21IS012 ASHIMA PRASAD 1NH21IS029 Nagaprasad H S1NH21ME048 Tharun B 1NH21ME077
    The field of agriculture, which has been providing the foundation for human existence and economic security, mcreasingly faces a host of daunting problems, such as inefficient utilization of water, labor deficiencies, and inability to notice crop diseases in their very early stages. These concerns call for innovative solutions toward maintaining agricultural productivity while reducing resource utilization. Agri-Smart 2.0 is a web-based smart imigation and crop monitoring system that seems to answer these challenges comprehensively and through advanced automation Technologies, wireless control mechanisms, and artificial intelligence for enhancing the optimization of farming practice. This project is a step forward for the digital transformation of agriculture with the aim of promoting productivity and resource efficiency.
  • Thumbnail Image
    Item
    AI BASED DIAGNOSTIC SYSTEMS FOR HEART ANOMOLY DETECTION USING CMR and ECG
    (NHCE, 2024) ANIKET HERLE1NH21CS027 , ARPEETA SONOLI1NH21CS031 , SRUSTI HIREGOUDAR 1NH21IS158, Ananya K G 1NH21IS014
    This project focuses on developing an Al-based diagnostic system for heart anomaly detection, integrating cutting-edge deep learning methodologies for both classification and segmentation tasks using Electrocardiogram (ECG) and Cardiac Magnetic Resonance (CMR) imaging data. By leveraging publicly available datasets, including ECG data from Mendeley and CMR images from the ACDC dataset, the system aims to enhance the precision and efficiency of cardiac diagnostics. The system comprises two key components: ECG Image Classification and CMR Image Segmentation. For ECG classification, convolutional neural networks (CNNs) were employed to detect and classify anomalies in ECG images into five categories: normal, myocardial infarction, dilated cardiomyopathy, hypertrophic cardiomyopathy, and abnormal right ventricle. The classification model incorporates advanced preprocessing techniques, including normalization and denoising, to ensure high-quality inputs for training. The model's output is a probability distribution across the categories, optimized using categorical cross-entropy loss and evaluated with standard metrics like accuracy and F1-score.
  • Thumbnail Image
    Item
    AI Based Virtual Patient Assistant Chatbot
    (NHCE, 2024) Abhay G 1NH21CS003 Abishek J1NH21CS004 Bharath J1NH21IS037 BHARATWAJ 1NH21IS080
    This work introduces an Al-based virtual patient assistant chatbot powered by the LLaMA (Large Language Model Meta Al) architecture, designed to enhance healthcare services by offering efficient, real-time medical assistance. The growing demand for Al-driven healthcare solutions highlights the need for tools that can offer timely, accurate responses with minimal computational overhead. LLAMA, developed by Meta Al, addresses this requirement by providing a highly scalable, low-latency solution, making it ideal for use in medical diagnostics, especially where speed and accuracy are paramount. The virtual assistant engages users through natural language conversations, collecting essential patient information such as name, age, and medical history. This personalized data allows the chatbot to provide tailored responses. The system processes symptoms provided by users in real-time, cross-referencing them with a comprehensive medical database to generate potential diagnoses and treatment recommendations. The use of LLaMA's fine-tuned capabilities ensures that the chatbot offers contextually relevant and medically accurate suggestions, making it a reliable tool for symptom analysis and healthcare advice.
  • Thumbnail Image
    Item
    AI Powered Automated Assessment and Evaluation System
    (NHCE, 2024) HARSH AHUJA1NH21CS092 NIKHILA SUVEDA MALLA1NH21IS101 PENTELA DINESH TRILOK1NH21IS112 Siddharth pradeep1NH21CS231
    The Automated Evaluation and Assessment System (AEAS) is an innovative technology designed to modernize evaluation processes in educational institutions. By combining dynamic and static analysis methodologies, AEAS incorporates advanced techniques such as abstract syntax tree analysis, plagiarism detection, and adaptive learning models to give a comprehensive assessment platform. The system is based around three basic interfaces -Administrator, Instructor, and Student - interconnected by a scalable and flexible web server architecture. This modular design provides smooth integration across multiple academic environments while keeping flexibility to accommodate varied evaluation criteria. Key features of AEAS include real-time plagiarism detection, tailored learning pathways depending on students' CGPA, and automated grading of assignments and examinations. These functions aim to reduce manual tasks for instructors, provide fast and actionable feedback to students, and enhance the overall quality of education delivery.
  • Thumbnail Image
    Item
    AutoNav:A Multifunctional Robot with Obstacle Avoidance , Bluetooth and Voice control Capabilities
    (NHCE, 2024) RUDRAMUNI DORE SP1NH22CS414 KIRAN V1NH22CS407 ROOPESH TB 1NH22IS410 UPPUTURI SHEKHAR RAJEEV1NH22IS413
    Autonomous vehicle navigation and obstacle avoidance represent critical components in the development of intelligent transportation systems. This study explores advanced techniques and algorithms designed to enhance the efficiency and safety of autonomous vehicles. We implement a combination of sensor fusion, machine learning, and real-time processing to enable vehicles to perceive their environment accurately and make informed decisions. Utilizing LiDAR, radar, and computer vision, the system identifies and classifies obstacles, predicting their movement to optimize navigation paths. The proposed approach integrates path planning algorithms with dynamic obstacle avoidance mechanisms, ensuring smooth and collision-free travel even in complex and unpredictable environments. Our experimental results, conducted through both simulations and real-world testing, demonstrate the system's robustness and reliability, highlighting improvements in response time and decision accuracy. This research contributes to the advancement of autonomous driving technologies, aiming to reduce traffic accidents and enhance mobility solutions. Future work will focus on refining these techniques, exploring their scalability, and integrating them into broader smart city initiatives.
  • Thumbnail Image
    Item
    Autonomous Vehicle Navigation,Bluetooth and Voice Control
    (NHCE, 2024) Buggesh 1NH22EE401 Sanjeevakumar 1NH22EE411 Shashikiran 1NH22IS411 Vinay Kumar KN1NH22IS415
    The "Autonomous Vehicle Navigation, Bluetooth, and Voice Control" project focuses on developing an intelligent vehicle system that combines advanced navigation, wireless connectivity, and voice command capabilities. The system enables the vehicle to operate autonomously by utilizing sensors for path planning, obstacle detection, and real-time decision-making. Bluetooth integrationprovides a seamless wireless interface for remote control and monitoring, while the incorporation ofvoice recognition technology allows hands-free interaction, enhancing user convenience and accessibility. This hybrid control approach ensuresflexibility, enabling the vehicle to adapt to various applications such as personal transport, industrialautomation, and delivery systems. The autonomous vehicle navigation, Bluetooth, and voice control project combines cutting-edge technologies to enhance the functionality and user interaction of autonomous vehicles. This project integrates three core components: autonomous navigation, Bluetooth communication, and voice-based control, to create an intelligent and user-friendly transportation system.
  • Thumbnail Image
    Item
    Autonomous Vehicles
    (NHCE, 2024) Adithya M\1NH21IS006 Janardhan P1NH21IS068 DINESH .K1NH21EC048 DRUVA P1NH21EC053
    This project is to implement how do self-driving cars stay on the road? How do vehicles with autonomous or driver-assist features automatically brake, steer around obstacles, or perform tasks like adaptive cruise control? Experiment with these behaviors and more in this science project as you build and program your own autonomous Arduino robot. The project aims to demonstrate how Arduino can be used to create a cost effective and accessible platform for AV experimentation and development. It explores the various sensors and algorithms used for environment perception, including lidar, radar, cameras, and ultrasonic sensors. Decision-making algorithms, such as rule-based systems, machine learning, and deep learning. arediscussed in detail, along with their integration into AV control system experience
  • Thumbnail Image
    Item
    Breaking Barriers
    (NHCE, 2024) MOUNIKA S 1NH21IS096 APOORVA S VISHWANATH1NH21IS021 PRAJWAL P1NH21EE080 MUKUND G1NH21EE067
    The idea of translation has become more relevant today than ever, as it has inevitably brought individuals closer together and fomented the necessity for contextually-accurate, affordable, and effective translation systems. As globalization intensifies, boundaries in languages often act as barriers in key sectors such as healthcare, education, business, tourism, and international relations, and the potential for communicating vital information accurately can directly affect outcomes. Though this creates enormous opportunities, the technology needs to be sufficiently advanced to meet such challenges in order to quickly address the solutions required to Translation Technology within the context of Unity model architecture. The proposed multilingual translation system would ensure real-time translation for text and speech.
  • Thumbnail Image
    Item
    Breaking Language Barriers
    (NHCE, 2024) DHARMIK BADARSHAHI1NH21IS049 NIKHIL BHATT1NH21IS100 EIKSHIT SINGHAL1NH21CS078 HRITHIK KAUSHIK1NH21CS099
    The digital era has revolutionized access to education, providing learners worldwide with a wealth of online resources. However, language barriers remain a significant challenge, especially in regions like Karnataka, where Kannada is the primary language. With most educational content available predominantly in English, Kannada-speaking students face difficulties in accessing and comprehending these resources, creating inequities in learning opportunities. This project seeks to address this disparity by developing an automated video translation system to convert educational videos from English to Kannada, fostering inclusivity and equitable learning.
  • Thumbnail Image
    Item
    Breast cancer detection
    (NHCE, 2024) ASHIKA TABASSSUM 1NH21IS028 BANDI PRANAYA SINDHU1NH21IS035 DEEKSHA R1NH21EC042 G PRANATHI1NH21EC055
    Early identification is essential for improving patient outcomes in breast cancer, one of the major worldwide health concerns. In order to develop a thorough and effective breast cancer detection system, this project combines databases, MATLAB, Flask, and machine learning. Users can easily upload medical data or mammography pictures using the Flask framework as a backend. These inputs are processed by a machine learning model that uses methods like support vector machines (SVM) or convolutional neural networks (CNN) to accurately identify cases as benign or malignant. Additionally, by identifying possible anomalies in mammography pictures, MATLAB-based image processing methods improve the diagnostic workflow. The MATLAB method uses median filtering to reduce noise, grayscale conversion, and histogram equalization to improve contrast. The Canny edge detection approach is used to identify critical boundaries. Morphological procedures such as dilation and hole filling are then used to further enhance the process and highlight regions of interest. These areas provide a visually understandable depiction of abnormalities and are superimposed in red on the original mammogram.
  • Thumbnail Image
    Item
    Career Path and Skill Mapping Development Platform
    (NHCE, 2024) PUTTETI SURARADHITH1NH21CS189, SHIVALING BASAVARAJ MENASI1NH21CS219, PRASIDDHA SHETTY1NH21IS118 SAMPATH KUMAR 1NH21IS134
    In today's dynamic job market, individuals often struggle to navigate the myriad career paths available and to identify the skills needed for their desired professions. Our project, the Career Path and Skill Mapping Development Platform, aims to bridge this gap by providing a comprehensive and user-friendly tool for career planning and skill development. This platform will assist users in exploring various career options, understanding the skill sets required for each path, and tracking their progress towards acquiring these skills. The platform leverages data from multiple sources, including industry trends, job market analysis, and educational resources, to offer personalized career recommendations. Users can input their current skills, interests, and career aspirations to receive tailored guidance on potential career paths. Additionally, the platform features a skill mapping function that aligns users' existing skills with those required for their chosen careers, highlighting areas for improvement and suggesting relevant training programs and resources. Through this project, we aim to empower individuals to make informed career decisions, enhance their employability, and achieve their professional goals. The Career Path and Skill Mapping Development Platform is a valuable tool for students, professionals, and career counselors, facilitating a more structured and strategic approach to career development.
  • Thumbnail Image
    Item
    CNN-Based Plant Disease Recognition System
    (NHCE, 2024) ATHARVI RAVI MAHINDRAKAR1NH21IS034, ASTHA TRIPATHI1NH21IS033, ARUSH ASHWIN1NH21CS034, AKASH BHATT1NH21CS017
    The advancement of technology in agriculture has introduced innovative methods for crop management, such as leaf detection and analysis using Python. By leveraging machine learning and computer vision techniques, Python enables the identification and classification of leaf features like shape, size, and colour. Tools like OpenCV for image processing and TensorFlow or PyTorch for model training provide a robust framework for accurate and efficient leaf detection. This technology has transformative applications, including early disease detection, plant health monitoring, and resource optimization. By analysing visual indicators, farmers can identify abnormalities, track stress levels, and allocate water, fertilizers, or pesticides more effectively. Integration with loT devices and drones further enhances data collection and real-time insights, advancing precision agriculture. Python-based leaf detection systems mark a major shift toward data-driven farming practices. These tools empower farmers with actionable insights, improving crop yield, reducing waste, and promoting sustainable agriculture. As these technologies evolve, they hold immense potential to address global food security challenges and foster environmentally friendly farming methods.
  • Thumbnail Image
    Item
    Connect For Game
    (NHCE, 2024) Kisan C Patel 1NH21IS079, MANIKANDAN R 1NHH21IS090, P Dinesha Kumar Reddy 1NH 21IS113, Bhargav Kumar Reddy 1NH21IS137
    This project focuses on the design and development of a Connect Four game, a classic two-player strategy game. The primary objective is to create a digital version of the game that replicates the traditional gameplay experience while offering a user-friendly interface and smooth interaction. Connect Four is played on a vertical grid consisting of 7 columns and 6 rows, where players take turns dropping colored discs into the columns. The goal is to connect four discs of the same color either horizontally, vertically, or diagonally before the opponent. The implementation involves features such as real-time gameplay, win detection algorithms, and a reset option for new rounds. The game also incorporates artificial intelligence (AI) for single-player mode, enabling users to compete against a computer opponent with varying difficulty levels. The development leverages programming concepts such as data structures, arrays, and algorithms for efficient game logic and win-checking mechanisms. This project aims to enhance logical thinking and problem-solving skills while providing an engaging and interactive platform for entertainment. It is suitable for both beginners and experienced players, offering a fun and educational experience
  • Thumbnail Image
    Item
    Custom Cure
    (NHCE, 2024) SAIYAD1NH21CS211 R HARSHAVARDHAN REDDY1NH21CS191 JASWANTH CHOWDARY L1NH21IS069 GOWTHAM M 1NH21IS058
    We provide a user-friendly experience on our website as well as for the doctors. Log in or Register to get access to a number of cool features. Search for their own available doctors, edit profile and send request easily. Receive alerts and have your info available with reliable, safe using. Our application system is user-friendly for the potential doctors. Schedule appointments to see your favourite doctors, and watch them being completed. Admin: Managing doctor applications and everyday user management. Be confidentall data is saved only safely. Come and be a part of this new era in enabling health care anytime, anywhere. The tools and technologies used include HTML5, CSS3, JavaScript, React, Node.js, Express, MongoDB and Redux Toolkit. We have included some essential features such as registration and log in for users, available doctors view, updating profiles, and contact section for queries. The features that keep the user in touch include alert. The admin management system oversees users, appointments, and doctor applications. We include access control, application of doctors, booking for appointments, and admin approval for requests from the doctors, removal of users and doctors, marking of appointments, notification about applications and appointment in the system.
  • Thumbnail Image
    Item
    Design and Development of smart window Control System
    (NHCE, 2024) RAHIL NAJEEB1NH21ME055 MOHAMMED IRFAN1NH22ME409 SANJIVANI MAZUMDER1NH21IS136 SAHANA S1NH21IS130
    This project "design and development of a Smart Window Control System" utilizes technology to enhance interior safety, convenience, and environmental flexibility. The system automates the operation of a motorized window by utilizing an Arduino microcontroller in combination with two crucial sensors: a rain sensor and a smoke sensor. When the rain sensor detects precipitation, it automatically closes the window, preventing water damage to the interior environment and preserving a cozy interior environment even in inclement weather. However, when the smoke sensor detects that there is smoke in the room, it immediately opens the window, promoting air circulation and allowing hazardous gases to dissipate, which improves indoor air quality and increases safety during any fire or smoke-related incidents. A custom-built mobile application that allows for real-time interaction and greater control was created using MIT App Inventor. Using the "Open" and "Close" buttons on the app interface, users may manually control the window. This user-friendly application connects to the Arduino microcontroller over Bluetooth.
  • Thumbnail Image
    Item
    Desktop Bot
    (NHCE, 2024) MANISH PAUL1NH21CS152 SAHIL KUMAR AGRAWAL1NH21CS206 Aastha Bharadwaj1NH21IS001 Abhinav Kumar 1NH21IS003
    The voice recognition system for the desktop bot is designed to make human-computer interaction smooth by using advanced machine learning techniques. It integrates the Google Speech-to-Text API with deep learning models for accurate and efficient speech recognition. Recurrent Neural Networks (RNNs) and their variants, such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRUs), process sequential speech data by capturing temporal dependencies. Complementing this, Convolutional Neural Networks (CNNs) extract features from audio spectrograms, identifying key patterns in frequency and amplitude. Attention mechanisms enhance the system's focus on critical sections of input, improving recognition precision. End-to-end models, including sequence-to-sequence (seq2seq) with attention and the Transformer model, map raw audio to text directly, streamlining the process and boosting efficiency. Specialized models turn raw sounds into meaningful components, while predictive models guess word sequences based on context, improving overall accuracy. This combination of techniques makes the desktop bot highly accurate and reliable, offering natural and intuitive voice-based human-computer interaction.
  • Thumbnail Image
    Item
    Digital identity and learning analysis
    (NHCE, 2024) KAMISETTY JAHNAVI1NH21CS121, JANAK RAJ JOSHI1NH21CS106, G.CHARITHA1NH21IS212, B.RISHITHA HASINI1NH21IS200
    The "Digital Identity and Learning Analysis" project presents a comprehensive solution aimed at addressing the key challenges faced in modern educational environments. By integrating secure authentication mechanisms, personalized learning tools, and advanced analytics, the platform enhances both teaching and learning experiences. The core of the system revolves around innovative PassPoints Authentication-a graphical password mechanism that requires users to select specific points on an image as their password. This novel approach ensures robust security, addressing the vulnerabilities inherent in traditional text-based passwords while adding a layer of creativity and user engagement. The platform caters to two primary user groups: teachers and students. Teachers are equipped with a feature-rich dashboard that allows them to efficiently manage their classes. They can create and assign tasks using an integrated to-do list, upload video content organized by chapters and modules, and monitor student engagement in real-time. Teachers also have access to detailed analytics, enabling them to assess student performance and engagement with learning materials. The platform incorporates a video tracker that marks lessons as "seen" upon completion, providing transparency for both students and teachers. Additionally, the inclusion of a YouTube tracker further enriches the learning experience by integrating external resources. The frontend is built using Flutter, offering a responsive, cross-platform interface that ensures consistent performance across mobile and web applications. In conclusion, the "Digital Identity and Learning Analysis" platform stands out as a comprehensive, secure, and user-centric solution for modern educational challenges. By integrating innovative authentication, personalized learning tools, and advanced analytics, it creates a collaborative ecosystem that empowers teachers and students alike. The platform's emphasis on security, scalability, and adaptability ensures its relevance and effectiveness in diverse educational settings.
  • Thumbnail Image
    Item
    Doctor's Voice :Voice to Text Report Generation
    (NHCE, 2024) SIDDHARTH RAJESH 1NH21EC150 VINAYAK S BANGARSHETRA 1NH21EC184 ARYAMAN PRAJIN1NH21EC023 HARSH JASHVANTBHAI VALAKI1NH21IS060 VINAYAK B SONAR1NH21IS178
    Healthcare providers in remote or low-network areas often struggle with managing patient data due to limited digital infrastructure and heavy reliance on manual processes. To address these challenges, we developed an automated solution designed to streamline data entry, analysis, and report generation for doctors working in such environments. The solution incorporates a user-friendly React.js frontend, offering an intuitive and responsive interface that allows healthcare providers to easily input, view, and manage patient records. A key feature of this system is a custom voice-to-text Al model, enabling doctors to dictate patient details, which are then processed through the Google Gemini 2.0 Al model for accurate text analysis and key data extraction. This approach reduces the need for manual documentation, saving time and improving the accuracy of patient records. To ensure secure storage and retrieval of sensitive information, the backend is powered by MongoDB with advanced encryption techniques and a hierarchical access system. This ensures that only authorized personnel can access patient data, further enhancing data security and privacy. The architecture of the solution not only automates the healthcare workflow but also improves data reliability and operational efficiency. By reducing the administrative burden and facilitating real-time data access, this system can significantly improve healthcare delivery in resource-constrained settings, with the potential for global scalability.
  • Thumbnail Image
    Item
    E-Consult +
    (NHCE, 2024) Gurushashank S R 1NH22IS405 Hanamant Gajanan Kulagude 1NH22IS406 Ajay Krishna A 1NH22AI401 Jayanth S S 1NH22AI404
    The E-Consult Plus platform introduces an innovative approach to telemedicine, aiming to revolutionize healthcare delivery for remote and underserved regions. With the increasing demand for accessible, efficient, and patient-centered healthcare solutions, E-Consult Plus bridges the gap by leveraging real-time video consultations, secure prescription management, and user-friendly interfaces. This system capitalizes on advanced technologies, including artificial intelligence (Al) for predictive diagnostics, Internet of Things (IoT) for continuous patient monitoring, and cloud infrastructure for scalability and reliability. The report begins by analyzing the historical evolution and global adoption of telemedicine, identifying limitations in existing systems such as fragmented communication and inadequate long-term support. E-Consult Plus addresses these gaps through its modular architecture, which includes features like emergency response capabilities, chronic disease monitoring, and enhanced security protocols ensuring compliance with HIPAA and GDPR standards.