Browse
Recent Submissions
Item CVRPTW Algorithm Analysis(NHCE, 2025) ANKIT BHATTACHARJEE 1NH21AI012 CHO LAQSHYA 1NH21AI025The Vehicle Routing Problem with Time Windows (VRPTW) is a combinatorial optimization problem that extends the classic Vehicle Routing Problem (VRP) by incorporating time constraints for customer deliveries. In this problem, a fleet of vehicles, each with a fixed capacity, must deliver goods to a set of customers while minimizing the total travel distance or cost. Each customer has a specific demand that must be met, and deliveries must occur within predefined time windows, meaning a vehicle cannot arrive earlier than the lower bound or later than the upper bound of the assigned timeframe. The goal is to determine a set of optimal routes that minimize the total distance traveled while ensuring all deliveries adhere to capacity and time constraints. The problem is NP-hard, meaning finding an exact solution for large instances is computationally expensive, requiring heuristic or metaheuristic approaches such as Genetic Algorithms (GA), Simulated Annealing, Ant Colony Optimization, or Tabu Search. VRPTW has many real-world applications, including logistics, last-mile delivery, and supply chain management, where companies strive to optimize fuel consumption, reduce operational costs, and improve customer satisfaction by ensuring on-time deliveries. The challenge lies in balancing multiple conflicting objectives, such as minimizing the number of vehicles used, reducing the overall route length, and meeting customer constraints while handling real-world uncertainties such as traffic conditions, vehicle breakdowns, and delays. Given these complexities, modern AI-based optimization techniques play a crucial role in efficiently solving large-scale VRPTW instances.Item AI for combating cyber bullying(NHCE, 2025) CHANDAN R 1NH21AI019 GIRIDHARAN H 1ΝΗ21AI032 CHRIS JORDAN 1NH21CS062 SANJANA JELLA 1NHH21CS299Cyberbullying poses a significant threat to online safety, particularly impacting younger users who are more susceptible to toxic digital interactions. This research presents an innovative Al-based solution designed to automatically detect harmful behavior and toxic comments in online environments. By leveraging advanced deep learning models, specifically Bidirectional Long Short-Term Memory (Bi-LSTM) networks combined with Natural Language Processing (NLP) techniques, the system is trained on extensive datasets of user comments to identify both subtle and overt signs of cyberbullying. The approach incorporates effective preprocessing methods such as TextVectorization, along with caching, shuffling, and batching techniques to optimize performance. The Al system's ability to process and classify harmful content in real-time makes it a powerful tool for monitoring online communities, promoting safer interactions, and significantly reducing incidents of online harassment. Additionally, its adaptability across diverse platforms ensures scalability and flexibility in combating evolving cyberbullying tactics. By equipping digital platforms with this technology, the solution fosters healthier online environments, empowers moderators, and acts as a critical resource for organizations dedicated to enhancing user safety and well-being.Item Deeplang: real-time language translation of Indian languages to English(NHCE, 2025) ROHIT 1NH21A1088 ULLAS -1NH21AI11 ANANYA CS -INH21CE008 MEGNA SALONI-INH21EC032For individuals around the world, especially those living in multilingual societies or engaging in global communication, overcoming language barriers remains a significant challenge. According to Ethnologue, there are over 7,000 languages spoken worldwide, making effective and seamless communication across diverse linguistic groups a persistent difficulty. Language barriers not only impede access to education, healthcare, and employment opportunities but also hinder cultural exchange and understanding. Traditional solutions, such as bilingual dictionaries or human interpreters, have long served as essential tools for bridging these gaps. However, these methods come with inherent limitations. For example, physical dictionaries and phrasebooks are cumbersome and time-consuming, while human interpreters, though invaluable, are often expensive, inaccessible, and impractical for real-time communication in everyday scenarios. These limitations highlight the pressing need for innovative, technologically advanced solutions to break down language barriers and foster seamless communication. Recent advancements in artificial intelligence (AI), particularly in natural language processing (NLP) and deep learning, combined with the proliferation of Internet of Things (IoT) devices, have opened up unprecedented opportunities to address these challenges. This project introduces the "Real-Time Language Translation System," a cutting-edge assistive technology that leverages state-of-the-art deep learning models and IoT integration to facilitate accurate, real-time translation across multiple languages. The primary objective of the system is to empower users with instant, context-aware translations, enabling them to navigate linguistic diversity with confidence and ease.Item Revolutionizing skull classification: leveraging Digital forensics and deep learning in physical Anthropology(NHCE, 2025) VASANTH KUMAR S 1NH21AI116 ABHILASH REDDY B 1NH21AI146 C G PRASANTH REDDY 1NH21EC036 C ANJAN REDDY 1NH21EC039This study explores the integration of digital forensics and deep learning to revolutionize skull classification within physical anthropology. It employs advanced image processing techniques and convolutional neural networks (CNNs) for accurate identification and classification of skulls, particularly based on the presence or absence of the mandible. The research process begins with preprocessing skull images, including resizing, noise removal, and contrast enhancement, to ensure high-quality inputs. Feature extraction techniques such as Gray-Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), Gabor filters, and Segmentation-based Fractal Texture Analysis (SFTA) are used to capture intricate textural and structural details of the skulls. The study compares traditional methods utilizing Support Vector Machines (SVMs) with the proposed CNN-based approach, demonstrating the latter's superior performance with significantly enhanced accuracy metrics. Data augmentation techniques like rotation, flipping, and scaling further bolster model robustness and mitigate overfitting. Evaluation metrics, including accuracy, precision, recall, and F1 score, validate the methodology's effectiveness, achieving classification accuracies exceeding 99%. This innovative framework supports anthropologists, forensic scientists, and archaeologists in efficient management, analysis, and preservation of anthropological collections. Its application extends to museum collections, forensic investigations, archaeological research, and medical studies. The findings emphasize the transformative potential of integrating machine learning and digital forensics in anthropological research, offering a robust tool for advancing our understanding of human evolution and cultural heritageItem Implementation of IoT-based irrigation system for Climate resilient farming(NHCE, 2025) Paruchuri Uday 1NH21AI134 M Babu Dhanush Kumar 1NH21AI144 Bhanu Dhushyanth S 1NH21CS233 Mahendra Reddy Y 1NH21CS269Implementation of IoT-based Smart irrigation System for Climate Resilient Farming is pivotal for enhancing agricultural productivity and sustainability, particularly in the face of climate change. This project implements an intelligent farming system using an Arduino Uno microcontroller integrated with various sensors, including a DHT11 for temperature and humidity, a pH sensor for soil acidity measurement, an LDR sensor for light intensity detection, a soil moisture sensor, and a gas sensor for monitoring air quality. The collected data is analyzed using machine learning algorithms to provide crop recommendations tailored to the specific environmental conditions. In scenarios where soil moisture levels fall below the optimal threshold, an automated pump system is activated to irrigate the soil, ensuring efficient water usage and improved crop health. This approach not only enhances agricultural productivity but also promotes resource conservation, supporting farmers in making informed decisions and fostering resilience against climate variability.Item Wearable Health Monitoring System Embedded In Python(2025) MEKALA HARSHA VARDHAN SAI 1NH21CS155 SANJAY K 1NH21C5214 PIDAPA SATHISH REDDY 1NH21A1076 POOJARI JATHIN NAIK 1NH21A1077With the growing need for personalized healthcare, the wearable health monitoring devices have emerged as critical tools for continuous health tracking, particularly among elderly, high-risk, and chronic disease patients. This research paper presents a robust and scalable wearable health monitoring system that integrates an Arduino microcontroller with an array of biomedical sensors, designed to capture and analyze various biological parameters in real time. The device combines a heart rate sensor for cardiovascular monitoring, a respiratory sensor to assess breathing patterns, a MEMS sensor to detect body movement and posture, and a temperature sensor to measure core body temperature. These sensors continuously collect data, which is then processed using a machine learning model trained to detect early signs of abnormal health patterns In the event of anomalies such as irregular heart rates, abnormal respiratory rates, sudden movement changes, or elevated temperatures the device automatically generates an SMS alert to designated caregivers or healthcare professionals, enabling timely medical response. The machine learning component enhances accuracy by adapting to individual health baselines, thereby reducing false alarms and improving diagnostic relevance. The wearable's compact, lightweight design allows for prolonged use, promoting user comfort and accessibility. This innovative system addresses the limitations of traditional health monitoring by providing real-time, mobile, and predictive insights, which can pointedly improve patient outcomes. Applications of this device extend beyond individual use to remote patient monitoring, emergency health services, and community health programs, underscoring ts potential for large-scale impact in proactive healthcare managementItem Voice command systems for drivers(NHCE, 2025) M SAI VAMSI 1NH21AI135 LIKHITESWAR REDDY 1NH21AI114 VINAY K 1NH21EC182 G RAHUL S 1NH21EC126This project introduces a Bluetooth-enabled, voice command system tailored for drivers, allowing hands-free control over essential vehicle functions, particularly beneficial for tasks such as reversing. Utilizing Bluetooth technology, the system seamlessly connects a smartphone or other Bluetooth-enabled device to the vehicle’s control module, enabling users to issue voice commands in any language to perform specific tasks. The system’s architecture includes a microphone for capturing voice input, a speech processing unit for command recognition, and a control unit that interfaces with the vehicle's motor mechanisms. By employing natural language processing techniques, the system ensures accurate recognition of diverse languages and dialects, enhancing accessibility for a broad range of users. Designed with safety and convenience in mind, this innovative solution minimizes physical interaction with vehicle controls, promoting a more intuitive and safer driving experience. The proposed system’s effectiveness and accuracy have been evaluated through extensive testing in varied acoustic environments, demonstrating its potential to improve driving accessibility and usability. This project explores the technical challenges faced, the solutions implemented, and the broader implications for future vehicle automation and smart mobility technologies.Item Speakeasy: a real-time speech translation system that Simplifies cross- language communication(NHCE, 2025) JASHWANTH S 1NH21A1089 VIGNESH A 1NH21A1118 VISWANANTH KOLLI 1NH21EC189 SELVAMOURIYAND 1NH21EC143The Real-Time Indian Languages Translation Project is an innovative initiative aimed at addressing the linguistic diversity of India by enabling seamless communication across various Indian languages. India, with its complex linguistic landscape, presents significant challenges in cross-linguistic communication, particularly in sectors such as education, healthcare, business, and government. By leveraging advanced technologies in speech recognition, natural language processing (NLP), and machine translation (MT), this project provides real-time translations, aiming to break down communication barriers and promote inclusivity, understanding, and collaboration across diverse linguistic groups. Challenges of Linguistic Diversity in India India is home to over 22 officially recognized languages and hundreds of regional dialects, with each state often having its own unique linguistic and cultural identity. The sheer volume of languages and dialects creates considerable barriers to communication, especially in contexts like education, healthcare, and public administration. In multilingual classrooms, students may struggle to grasp concepts taught in languages they don't speak, which can lead to educational disparities. Similarly, in healthcare, patients from rural areas may face difficulties explaining their symptoms to healthcare professionals who speak a different language, resulting in potential misdiagnoses. Additionally, language can create significant obstacles in government services, legal proceedings, and business transactions, where people often encounter difficulties in accessing crucial services due to language barriers. To address these issues, the Real-Time Indian Languages Translation Project aims to create a system that enables real-time translation between various Indian languages, ensuring effective communication across linguistic divides. This will provide a solution that promotes inclusivity and improves access to services, education, and healthcare for people from diverse linguistic backgrounds.Item Design and Fabrication of Smart Wheelchair-Cum-Bed Equipped with Health Monitoring System(NHCE, 2025) SURESH A 1NH22ME412 BHAGATH MANJUNATH S 1NH22ME402 SWASTITIRTHA DASH 1NH21AI108 SAI KRISHNA KM 1NH22AI409This project focuses on the design and development of a smart Wheelchair-Cum-Bed. capable of seamlesaly transforming into either a wheelchair or a bed at the press of a button. The system incorporates a rack-and-pinion mechanism for smooth transition between modes, ensuring ease of use for individuals with mobility challenges. Additionally, the wheelchair can be moved from one location to another with a simple button press. Integrated health monitoring features, including sensors for heart rate, pulse, humidity, and ECG, provide real-time health data to enhance the user's well-being. This innovative design aims to offer both mobility assistance and healthcare support, improving comfort, independence, and affordability for usersItem SmartCrowd: AI-Powered Real-Time Crowd Management and Communication System(NHCE, 2025)Effective crowd control and monitoring are now crucial for maintaining public safety, resource optimization, and operational efficiency due to the fast urbanization and population growth. Conventional techniques for counting individuals and detecting crowds rely on manual observation, which is laborious, prone to errors, and unsuitable for real-time applications in dynamic settings. The goal of this project is to use cutting-edge computer vision and deep learning techniques to create an automatic real-time crowd recognition and people counting system. The system makes use of the cutting-edge object detection model YOLOv3 (You Only Look Once), which is renowned for its accuracy and speed. Even in congested and complicated surroundings, YOLOv3 reliably detects people in real time by processing the input video feed. The SORT (Simple Online and Realtime Tracking) algorithm, which employs the Hungarian algorithm for object association across video frames and Kalman Filters for motion prediction, is incorporated to preserve continuity and guarantee precise person counting. When combined, YOLOv3 and SORT provide a scalable and resilient system that can manage dense crowds while resolving issues like occlusions, overlapping objects, and changing illumination. Live video streams from webcams, IP cameras, and pre-recorded video are processed by the system. In addition to tracking people's movements and dynamically counting the number of individuals in the screen, it also displays visual cues like tracking IDs and bounding boxes. In order to keep an eye on crowd flow, the system can also recognize line-crossing events, such entry or exit. A user-friendly interface is used to display the results, and HTTP APIs can be used to integrate them with other systems. By automated crowd identification and person counting, this technology helps sectors like public safety, event planning, retail analytics, and transit hubs. It offers accurate, real-time insights while lowering human labor and mistakes. It improves operational efficiency and safety in crowded areas with its great precision and scalability.Item Smart system for automated medical emergency Alerts(NHCE, 2025) AJAY KUMAR R 1NH21AI009 BIPIN GANAPATHY 1NH21AI016 S BHARATH 1NH21ME059 SAI SHANKAR SUDHANVA G 1NH21ME063The "Smart System for Automated Medical Emergency Alerts" aims to address the critical need for timely detection and response to medical emergencies by leveraging cutting-edge technologies such as Artificial Intelligence (AI), the Internet of Things (IoT), and biosensors. This system is designed to provide real-time monitoring, anomaly detection, and automated notifications to caregivers, family members, and emergency responders, thereby reducing delays in medical intervention and enhancing patient outcomes. The system continuously tracks vital parameters like heart rate, blood pressure, oxygen levels, and movement patterns using wearable devices equipped with biosensors. AI algorithms analyze this data to identify emergencies such as cardiac arrests, falls, or strokes. Upon detecting an anomaly, instant alerts are generated and transmitted via smartphones, apps, or other communication channels. Integration with geolocation technologies ensures precise tracking, enabling responders to locate individuals quickly. Key features of the system include real-time health monitoring, high detection accuracy, customizable alert settings, and seamless integration with emergency services. Applications span elderly care, chronic disease management, post-surgical recovery, workplace safety, and remote healthcare, making the system adaptable for diverse environments such as homes, public spaces, and hospitals. Benefits include faster response times, reduced healthcare costs, improved accessibility for vulnerable populations, and peace of mind for users and caregivers. Challenges such as data privacy, system reliability, and adapting to diverse user needs are acknowledged, with plans for continuous improvement through advanced AI algorithms, user feedback, and broader integration with health platforms. The project represents a transformative step in healthcare, enhancing emergency preparedness and ensuring timely, life-saving interventions. This system holds immense potential to revolutionize medical emergency management by bridging the gap between detection and response, ultimately improving healthcare outcomes and quality of life.Item Smart health monitoring system using LLM(NHCE, 2025)In today's fast-paced world, keeping track of personal health is more important than ever. My project, "Smart Health Monitoring System Using LLM," aims to revolutionize healthcare management by combining cutting-edge technology with practical, everyday use. This system uses a smartwatch with advanced sensors to continuously monitor vital health signs. This data is then sent to a mobile app, where users can easily access realtime health insights and personalized advice. The standout feature of this system is the integration of a Large Language Model (LLM). This AI-powered assistant allows users to ask health-related questions and receive customized guidance, making it easier for people to understand and manage their health. Additionally, the app offers special content to help teenagers navigate menstrual health, providing education and support in an accessible way. The smartwatch, which connects to the app via Bluetooth, tracks various health metrics like heart rate, sleep patterns, and physical activity. By analyzing this data, the app can offer valuable insights and alerts, helping users make informed health decisions. This proactive approach encourages a healthier lifestyle and empowers users to take control of their well-being. Developed during my third year of engineering studies, this project showcases how innovative technology can address real-world health challenges. By merging wearable tech with intelligent algorithms, the Smart Health Monitoring System aims to set a new standard for personalized healthcare, making it more accessible and effective for everyone.Item Smart Earthquake Detection with ESP32 and MPU6050: Real- Time Monitoring and Email Alerts(2025) RAKSHITHE 1NH21AI147 RUTHWIK SIDDHARTHA 1NH21EC132 SUMESH R 1NH21EC157 VSHREYAS REDDY 1NH21EC167Earthquakes zre among the worst natural phenomena which damage properties take lives and disturb people. The harm caused by seismic activity can be reduced through their early danaction and surveillance. In principle, the need for such technologies exists all over the world but the resources available to such systems are limited in many developing countries, since maditional earthquake detection systems tend to be expensive. Nevertheless, the emerging technology has provided new opportunities to develop modern approaches and low costs microcontrollers and sensors based systems for reliable and effective detection of earthquakes The Internet of Things (IoT) has significantly changad various fields by allowing for real-time data collection, analysis, and communication bersem devices. In the context of earthquake monitoring. IoT facilitates the use of mnerconnected sensor networks that continuously track ground movement and sand data for analysis. These systems can deliver valuable real-time insights into seismic activities, alerting designated recipients when on sarthquake occurs The proposed sarthquake detection system is built around the ESP32 microcontroller. This microcontroller is recognized for its impressitie performance and energy efficiency, featuring dual-core processors along with integrated Wi-Fi and Bluetooth capabilities, which makes it ideal for IoT applications. Its small size and cost-effectiveness facilitate widespread use without imposing significant financial burdans. The ESP32 is capable of efficiently processing data from sensors, analyzing seismic activity, and communicating with cloud platforma for additional processing and alertItem Exploratory Analysis of Heart Attack and Breast Cancer Early Stage Prediction c(NHCE, 2025) Yashwanth Pavan Kumar K INH21AI124 P Sree Dinesh Reddy 1NH21AI143 Neha Singh 1NH21IS099 M Shivani Kashyap 1NH21IS083Cardiovascular events such as heart attacks and breast cancer rank among the foremost health issues worldwide, substantially influencing mortality statistics and presenting significant challenges for healthcare systems. These ailments are interconnected by the shared opportunity for better prognoses through timely detection and proactive measures. The present research emphasizes the utilization of data-informed strategies to improve comprehension and forecasting of these conditions during their initial phases. This study is set out to find significant patterns, associations, and predictors that may help in earlier detection based on clinical and lifestyle data relating to the risk of heart attacks and tumor- related factors of interest for breast cancer. Heart attacks are mainly caused by cardiovascular conditions; various factors such as age, cholesterol levels, blood pressure, diabetes mellitus, smoking, and a lack of exercise affect them. These parameters often have cross-references, leading to complex configurations, which are not often recognizable with standard diagnostic methods. Analogously, breast cancer is among the leading causes of cancer-related deaths in females, and involves intricate relations between tumor characteristics (size, texture, and margins) with demographic or genetic predispositions. The prompt identification of such factors is essential, because early diagnosis significantly increases the effectiveness of treatment outcomes as well as survival for the patients. This study uses an exploratory data analysis framework to analyze datasets that include clinical and demographic information for both conditions. EDA is crucial in understanding the data structure, recognizing patterns, and detecting potential anomalies. Through statistical summaries and graphical representations such as histograms, scatterplots, and heatmaps, this research reveals vital insights into the relationships among variables. For instance, in the case of forecasting heart attacks, variables such as high levels of cholesterol, obesity, and inactive lifestyle prove to have strong correlations with increased risk. In much the same way, data involving breast cancer highlight the importance of certain tumor features and demographic features in predicting cancer.Item MedPredict(NHCE, 2025) EESHA NAVEEN 1NH21AI031 MUSAB 1NH21AI131 SIDDHARTH KULKARNI 1NH21IS151 VINAY S 1NH21IS177Many of the existing machine learning models for health care analysis are concentrating on one disease per analysis. Like one analysis if for diabetes analysis, one for cancer analysis, one for skin diseases like that. There is no common system where one analysis can perform more than one disease prediction. In this article proposing a system which used to predict multiple diseases by using Flask API. In this article used to analyse Diabetes analysis, Diabetes Retinopathy analysis, Heart disease and breast cancer analysis. Later other diseases like skin diseases, fever analysis and many more diseases can be included. To implement multiple disease analysis used machine learning algorithms, tensorflow and Flask API. Python pickling is used to save the model behaviour and python unpickling is used to load the pickle file whenever required. The importance of this article analysis in while analysing the diseases all the parameters which causes the disease is included so it possible to detect the maximum effects which the disease will cause. For example for diabetes analysis in many existing systems considered few parameters like age, sex, bmi, insulin, glucose, blood pressure, diabetes pedigree function, pregnancies, considered in addition to age, sex, bmi, insulin, glucose, blood pressure, diabetes pedigree function, pregnancies included serum creatinine, potassium, GlasgowComaScale, heart rate/pulse Rate, respiration rate, body temperature, low density lipoprotein (LDL), high density lipoprotein (HDL), TG (Triglycerides). Final models behaviour will be saved as python pickle file. Flask API is designed. When user accessing this API, the user has to send the parameters of the disease along with disease name. Flask API will invoke the corresponding model and returns the status of the patient. The importance of this analysis to analyse the maximum diseases, so that to monitor the patient's condition and warn the patients in advance to decrease mortality ratio.Item Skillquest: gamified learning with strategic hints and timed challenges(NHCE, 2025) ADARSH R 1NH21A1006 AGA ASGHAR MURTHUZA 1NH21A1008 MANAS M 1NH21CS149 MOHAMMAD MURTUZA HUSSAIN 1NH21CS161Online education often struggles with issues like low student engagement, lack of interactivity, and difficulty in personalizing learning experiences to individual needs. Traditional platforms primarily rely on linear content delivery and standardized assessments, often failing to maintain sustained motivation, leading to high dropout rates and reduced learning outcomes. SkillQuest addresses these challenges by integrating immersive gamification techniques with advanced AI technologies, creating a competitive yet collaborative learning environment. Unlike existing systems, SkillQuest incorporates points, leaderboards, badges, and timed challenges while employing a lightweight AI model to dynamically generate multiple-choice questions (MCQs) with hints tailored to user-selected topics. Reinforcement learning (RL) algorithms continuously adapt learning paths, adjusting content complexity based on individual performance and preferences. The platform also features a chatbot powered by Llama models for instant doubt clearing and assistance, enhancing interactivity and support. By blending gamification with AI-driven personalization, SkillQuest aims to revolutionize online education by increasing motivation, providing tailored educational journeys, enabling dynamic content adaptation, and fostering a collaborative yet competitive atmosphere. With the successful development of these features, SkillQuest empowers learners to achieve their educational goals interactively and effectively, setting a new standard for engaging and adaptive online learning experiences.Item Intelligent toll collection system(NHCE, 2025) RESHAB VASANTH 11H214100 SRAVAN OE INH23A1101 SHRUJAN KR 1H2105228This Project presents an enhanced Intelligent Toll Collection System (ITCS) integrating RFID and ANPR technologies to address traffic congestion and operational inefficiencies in conventional toll collection. We propose a novel multi-stage image preprocessing pipeline combined with adaptive thresholding techniques, achieving a 95.8% plate detection rate and mean confidence score of 0.85. Our implementation demonstrates significant performance improvements with average processing times of 0.8 seconds per vehicle and sustained accuracy rates of 92% in daylight conditions. The system maintains robust performance across varying environmental conditions through an optimized bilateral filtering approach (11, 17, 17) and specialized morphological operations. Experimental results show substantial reductions in processing time and enhanced accuracy compared to traditional methods, while maintaining scalability for high-traffic deployments. This implementation advances the field of intelligent transportation systems, providing a foundation for future smart city infrastructure development.Item Crop Sense: An Integrated WebApp for Crop Health Monitoring and Disease Detection(NHCE, 2025) NARJIT LEISHANGTHEM 1NH21AI064 MOHAMMED AFFAN 1NH21AI056 ADRIAN MATHEW ALOYSIUS 1NH21CS011 DAVE PINTO 1NH21CS065The increasing demand for sustainable agriculture necessitates innovative solutions to enhance crop health monitoring and disease detection. This project integrates advanced technologies, including satellite imagery, loT sensors, machine learning, and cloud computing, to address the limitations of traditional farming practices. The proposed system leverages high-resolution satellite data and real-time IoT sensor inputs to monitor environmental conditions and detect early signs of crop diseases. Machine learning models, such as Convolutional Neural Networks (CNNs) and Random Forest classifiers, process these datasets to provide accurate diagnostics and actionable insights. A user-friendly web-based interface ensures that farmers can access real-time data and receive tailored recommendations for efficient resource management. This system offers several key benefits, including improved disease detection accuracy, reduced reliance on chemical inputs, and enhanced agricultural productivity. By enabling precision farming, the system not only optimises resource utilisation but also promotes environmental sustainability. The project represents a significant step towards addressing the challenges of modern agriculture, contributing to food security and the adoption of smart farming practices globally.Item Adaptable Arms: innovations in flexible robotic manipulation(NHCE, 2025) SURESH R 1NH22A1410 VARUN MS 1NH22A1411 SANGAMESH POLICE PATIL 1NH22ME411 SUDEEP 1NH21ME073The problem definition of flexible robotic arm movement in the agriculture field centres around the need for automation solutions that can handle the diverse, unpredictable, and often delicate tasks involved in modern farming. Agriculture presents unique challenges that traditional rigid robotic arms struggle to address due to the variability of the environment, crop types, terrain conditions, and the need for precision in handling perishable goods. Flexible robotic arms offer a promising solution to these challenges, but their design and deployment come with several complex problems that need to be solved.Item Real-time fire and smoke detection and retardation(NHCE, 2025) HEMANTH KUMAR REDDY Ρ 1ΝΗ21Α1127 RAHUL D 1NH21A1128 MANU M 1NH21EC090 NANDEESH GOWDA B 1NH21EC102Fire and smoke detection systems play a vital role in ensuring safety and reducing losses caused by fire-related incidents. However, conventional systems that rely on heat and smoke sensors are often susceptible to false alarms and may fail to detect fires at their earliest stages. This paper presents a modern, cost-effective, and intelligent approach to fire and smoke detection, utilizing the ESP32-CAM microcontroller combined with a Convolutional Neural Network (CNN). The ESP32-CAM, a compact and affordable lot-enabled microcontroller with an integrated camera, serves as a reliable platform for real-time image capture and processing. When paired with CNNs, a cutting-edge deep learning architecture for image recognition, the system provides a robust and highly accurate solution for detecting fire and smoke. By integrating lot and Al technologies, the proposed system bridges the gap between affordability and advanced functionality, ensuring timely and precise alerts The system architecture comprises three core components: the ESP32-CAM for image acquisition, the CNN for image-based analysis, and a communication interface for transmitting alerts. The ESP32-CAM continuously captures images or video streams, which are then preprocessed to enhance detection accuracy. Preprocessing techniques, such as resizing, normalization, and noise reduction, prepare the visual inputs for the CNN. The trained CNN identifies critical features in the data to detect fire and smoke reliably. At the heart of the system lies the CNN, optimized specifically for deployment on resource-constrained devices. Its lightweight design ensures compatibility with the ESP32-CAM's limited computational capabilities while maintaining high accuracy. Optimization techniques like model pruning, quantization, and transfer learning help reduce computational demands without compromising performance.