2023-24 (Autonomous)

Permanent URI for this collection

http://192.168.75.5:4000/handle/123456789/19158

Browse

Now showing 1 - 20 of 25

CNN based implementation of crowd detection using raspberry pi
(NHCE, 2024) Dhimant R S 1NH20CE011; Ganya P R 1NH20CE013; Grishma S G 1NH20CE014
There is a lot of population numbers in the world and India is one among them. So, it is very common to expect crowded events with many number of people participating in the events like cart festivals-, strikes-, protests and any other sort of event where people gathering is too common in these days but these gatherings will be confronted to multiple security issues. To get free from such issues, security cases are majorly involved to handle the crowd and provide security to the people surrounded in the gatherings. But at last the security provided to people is limited with the technology, the security forces can easily become tired and remain unsuccessful in maintaining the crowd. Due to the negligence and poor managed system this might be problematic issue to the people like people get injured and it might also lead to loss of lives accordingly crowd also increases. So that’s the reason we are here with the solution for crowd detection by using Raspberry Pi Model 4B and by implementing the concept of deep learning and machine learning on AI, by training a model based on it. And at last this model will be deployed on our Raspberry Pi board. This will help us to identify the crowd on a real time scenario. The crowd can be categorized under one person, two people, three people, four people, crowd or protest crowd. The crowd can then be detected by CCTV or by drones for betterment view of the crowd. To achieve this the process is divided into three parts, firstly we will identify pedestrian using the collected data set. Secondly, we will try the same thing on people. Thirdly, we will try this on real time crowd detection.
FUSIONLEX: Brigging GAP with Real Time Hybrid Bilingualism
(NHCE, 2024) Ankit Oli 1NH20CE002; Krishnam 1NH20CE024; Pranay 1NH20CE032; Rahul 1NH20CE035
Real-time speech translation has become a transformative technology, enabling instantaneous communication across language barriers. This survey provides an in-depth overview of the current landscape, advancements, challenges, and future directions in real-time speech translation systems. The foundational concepts and methodologies include Automatic Speech Recognition (ASR), which converts spoken language into text: Machine Translation (MT), which translates text from one language to another, and Natural Language Processing (NLP), which facilitates the understanding and processing of human language by computers. These components have evolved significantly, contributing to the progress of real-time speech translation. ASR has transitioned from Hidden Markov Models (HMMs) and Gaussian Mixture Models (GMMs) to deep learning models such as Long Short-Term Memory (LSTM) networks and Convolutional Neural Networks (CNNs), improving accuracy and robustness. MT has shifted from rule-based and statistical models to neural machine translation (NMT) systems, with transformer architectures like BERT and GPT significantly enhancing translation quality. Model optimization and adaptation strategies, such as transfer learning and fine-tuning on specific datasets, enhance performance for particular languages and contexts. Despite significant progress, several challenges remain. Limited training data for many languages hinders the development of accurate translation models. Background noise, accents, and speech variability can affect ASR performance. Ensuring real-time processing without significant delays is a technical challenge, and maintaining high translation accuracy across complex linguistic nuances is difficult. Real-time speech translation is being applied in various fields, including healthcare. business, education, and international diplomacy. In healthcare, it facilitates communication between patients and providers who speak different languages. In business, it enables multinational companies to conduct meetings and negotiations more effectively. In education, it supports learning in multilingual classrooms and access to educational resources in different languages.
Disease Prediction using Machine Learning
(NHCE, 2024) Kammara Trivikram 1NH20CE022; Manobhi Ram Reddy B 1NH20CE026; Shashank S 1NH20CE045; Sushmitha H 1NH20CE053
In contemporary healthcare systems, the timely and accurate diagnosis of diseases represents a critical pillar for effective treatment and the containment of healthcare costs. Addressing this imperative, our project endeavors to develop a sophisticated web application that harnesses the power of machine learning algorithms to anticipate diseases based on user-provided symptoms. By doing so, we aim to facilitate prompt medical intervention and improve healthcare outcomes. Central to our solution is the implementation of an ensemble model that combines multiple machine learning classifiers, including Logistic Regression, Random Forest, KNN, MLP, and SVM, with XGBoost serving as the meta-learner. This ensemble approach capitalizes on the diverse strengths of these algorithms to achieve an exceptional accuracy rate of 97%. Through meticulous testing and validation procedures, we have ensured the reliability and efficacy of our predictive model. The core functionality of our Flask-based web application revolves around providing users with a seamless and intuitive platform for disease prediction and access to tailored healthcare recommendations. Key features include user authentication mechanisms to safeguard personal data, a user-friendly interface for inputting symptoms, and integration with the Google Maps API to offer personalized recommendations of nearby medical specialists. This integration enhances user experience by facilitating convenient access to healthcare services. One of the distinguishing aspects of our project is its emphasis on proactive healthcare management through early disease detection. By leveraging machine learning algorithms to analyze symptom datta, our application enables users to receive timely alerts regarding potential health risks. This proactive approach empowers individuals to take proactive measures to safeguard their health and seek medical assistance when needed, ultimately contributing to improved health outcomes
BinancePy: Python - Powered Crypto Trading
(NHCE, 2024) Aravind Aripaka 1NH20CE004; Tundiya Krish J 1NH20CE055; Harshchand Aravind Aripaka 1NH20CE004
Fingerprint images in crime scene are important clues to solve serial cases. Crime scene fingerprint identification system using deep machine learning with Convolutional Neural Network (CNN). Images are acquired from crime scene using methods ranging from precision photography to complex physical and chemical processing techniques and saved as the database. The images collected from the crime scene are usually incomplete and hence difficult to categorize. The fingerprint recognition system is divided into three stages that are fingerprint image pre-processing, feature extraction and matching. Suitable enhancement methods are required for pre-processing the fingerprint images. The output of this stage will be passed to feature extraction stage which is extract the minutiae point (ridge ending, Bifurcation) from thinning fingerprint image, then the false minutiae removal is applied to extract real minutiae. The features of pre- processed data are fed into the CNN as input to train and test the network.
Student Analyzer and Recommender
(NHCE, 2024) S Heena Kouser 1NH20CE044; Namitha G K 1NH21CE400
Student analysis and recommendation systems are becoming crucial in aiding individuals to make well-informed decisions regarding their educational and professional trajectories. The integration of machine learning techniques presents a promising advancement in enhancing the effectiveness of these systems. In our data-driven era, machine learning algorithms offer significant potential to transform how student analysis and recommendation systems operate. This project aims to explore the methodologies involved in utilizing machine learning to improve student analysis and recommendations. It will specifically address the selection of appropriate machine learning algorithms, the procedures for collecting and preprocessing data relevant to student guidance, and the identification of metrics to evaluate the performance of the recommendation models developed through machine learning. By focusing on these essential aspects, the study aims to contribute to the broader discourse on how technology can be leveraged to provide more personalized and precise guidance to students navigating the complexities of modern education and career planning.
Improvising Voice Recognition technique Using AIML
(NHCE, 2024) Anand Kumar 1NH20CE001; Shivam Anand 1NH20CE046; V Lalith 1NH20ME060; Krishna 1NH20ME057
Voice recognition technology has witnessed significant advancements in recent years, becoming an integral part of various applications such as virtual assistants, smart home devices, and voice-activated systems. This project focuses on enhancing voice recognition techniques through the integration of Artificial Intelligence Markup Language (AIML), aiming to overcome existing challenges and elevate the accuracy and efficiency of voice recognition systems.
Fitness Tracker
(NHCE, 2024) Akash Kumar Sen 1NH20IS009; Partha Pratim Sem 1NH20IS108; Sandeep Hukum Dhanai 1NH20CEO66; Chaitanya Bharadwaj 1NH201S201
Access to an affordable and working healthcare system is one of the aspects by which a country can be classified upon. Today, healthcare in India has become of the fastest growing sectors with respect to both employment and revenue. Everyone has started doing physical, mental and breathing exercises to be fit but one's goal towards fitness starts with what they eat. Most of them doesn't know about keeping a track of the food they are eating and the workouts they are doing to burn calories. As, they are not able to distinguish between healthy and unhealthy food items they are consuming and are not able to see results of their hard work and patience. So, we decided to make this project on "FITNESS TRACKER" for such people to keep a track of the food they are consuming and the exercises they are performing. For this they have to know the proper amount of protein, fibre, carbohydrates and fats they are eating in their daily meals and the calories exhausted in doing a particular workout. As a proper balance of these substances in one's body and some good daily workout plans results in good health and is able to fight diseases very efficiently. In our project we've made a sincere attenmpt to make a calculator for counting our daily calories and show user, the amount of carbohydrates, fats, proteins and fibre they have taken in their meals. User can track out calories burned in their workout plans and are also able to make changes and add new workout and diet plans. Our project is based on the python development environment and code is easy and clear to be understood by anyone. We have selected and refined a huge dataset of food items and workout plans using various data refining and data cleaning processes by using Pandas. We also provided the admin to modify the dataset so that new food items and workouts can be constantly added in the dataset as per the user requirement. Our focus has been constantly on keeping the functioning of the application very simple and accurate so that anyone can use our application easily without any challenge. Various python modules have been used to support the backend of the application and is merged with HTML, CSS and Django for its frontend designing and web implementation.
Sing Language Translation Using LSTM
(NHCE, 2024) Raksha Holla A 1NH20CE036; P Sai Kiran 1NH20CE064; Adnan Azam 1NH20CE065
In This research presents an innovative methodology aimed at facilitating real-time communication for individuals with hearing impairments by skillfully detecting sign language actions, leveraging the power of Long Short-Term Memory (LSTM) deep learning models. The primary objective is to bridge the communication gap between the hearing-impaired community and the general public, enhancing inclusivity and accessibility in interpersonal interactions. Central to this endeavor is the development of a Sign Language Detection system meticulously crafted to achieve high accuracy and efficiency in interpreting sign language gestures. The utilization of LSTM architecture, renowned for its adeptness in capturing temporal dependencies-a pivotal aspect of sign language interpretation-underscores the sophistication of the proposed system. The research workflow commences with the assembly of a comprehensive dataset encompassing a wide spectrum of sign language actions. This dataset undergoes meticulous preparation to ensure optimal quality and eliminate extraneous noise that could impede accurate recognition. Preprocessing, feature extraction, model training, and video capture constitute the foundational stages in the workflow for sign language detection. During preprocessing, video data is segmented into individual frames, laying the groundwork for subsequent processing stages. These frames undergo refinement using various image-processing techniques, enhancing clarity and eliminating aberrations to facilitate accurate interpretation. The feature extraction, employing sophisticated approaches such as optical flow or deep learning-based algorithms, further refines the data, extracting meaningful features crucial for effective sign language interpretation. The extracted features serve as inputs for training the Long Short Term Memory model, which excels in capturing the nuanced temporal movements inherent in sign language gestures. Analogous to the human brain, the Long Short Term Memory neural network harnesses a multitude of inputs, including weights, and biases to execute diverse tasks, including categorization and identification. The abundance of data comprising the training set optimally primes the deep learning system for accurate interpretation.
Voice Based Stress Analysis and Detection Using Machine Learning
(NHCE, 2024) Darshna V 1NH20CE009; M kumar Venkat 1NH20ME075; Omini rao N 1NH20CE029; Prajwal 1NH20ME085
Artificial intelligence, particularly machine learning, is revolutionizing numerous fields by either supplementing or replacing human efforts, leading to enhanced efficiency and autonomy in systems. Healthcare stands as a notable domain ripe for collaboration with Al and machine learning, offering smoother and more efficient operations. Stress is a pervasive issue in modern society, affecting individuals' mental and physical health. Traditional stress detection methods often rely on self-reporting and physiological measurements, which can be intrusive and impractical for continuous monitoring. The proposed system utilizes vocal biomarkers to identify stress levels in real-time. By analysing various acoustic features of speech, such as pitch, tone, rhythm, and speech rate, the system can detect subtle changes indicative of stress. A comprehensive dataset comprising speech samples from individuals under varying stress conditions was collected and used to train a neural network model. This model was then validated against established stress measurement techniques to ensure its accuracy and reliability. This voice-based approach offers a promising solution for early stress detection and intervention, contributing to better mental health management and improved overall well-being.
Deep Reinforcement Learning for Image Hashing
(NHCE, 2024) Athira Musaliyath Dinesh 1NH20CE005; Dhanush Y J 1NH20CE010; Anusha Sai 1NH20CE019
The rapid increase in digital images necessitates efficient retrieval and storage methods, where traditional hashing techniques struggle with scalability and accuracy. This project introduces Deep Reinforcement Learning (DRL) for Image Hashing (DRLIH), leveraging DRL's sequential decision-making to enhance hashing function learning and retrieval performance. Traditional hashing methods like Locality-Sensitive Hashing (LSH) and spectral hashing treat hashing functions independently, ignoring correlations between them and leading to suboptimal accuracy. Deep learning methods using convolutional neural networks (CNNs) for hash code generation also lack mechanisms to refine hashing functions sequentially based on previous errors. DRLIH models the hashing process as a Markov Decision Process (MDP), incorporating state representation from recurrent neural networks (RNNs) and CNNs, an action space of possible hashing functions, and a reward function providing feedback on hash code accuracy. The DRL agent, which features an RNN-based architecture with Long Short-Term Memory (LSTM) units, is trained using the policy gradient method to maximize cumulative rewards through iterative interactions. By iteratively correcting errors and leveraging historical context, DRLIH offers a robust, scalable solution for large-scale image retrieval, setting a new standard in the field. Future work will explore advanced RL techniques to further enhance performance.
Machine Learning for Predictive Analytics in Finance
(NHCE, 2024) G Gopi Krishna 1NH20CE015; Harshvardhan G N 1NH20CE016; K Koushik Sai 1NH20CE020; V Jayanth Kumar Reddy 1NH20CE060
Fraud has become a trillion-dollar industry today. Some finance companies have separate domain expert teams and data scientists who are working on identifying fraudulent activities. Data Scientists often use complex statistical models to identify frauds. However, there are many disadvantages to this approach. Fraud detection is not real-time and therefore, in many cases fraudulent activities are identified only after the actual fraud has happened. These methodologies are prone to human errors. In addition, it requires expensive, highly skilled domain expert teams and data scientists. Nevertheless, the accuracy of manual fraud detection methodologies is low and due to that, it is very difficult to handle large volumes of data. More often, it requires time-consuming investigations into the other transactions related to the fraudulent activity in order to identify fraudulent activity patterns.
Design and development of Multi-Purpose Quad copter
(NHCE, 2024) Sanjay Saheel 1NH20CE041; Sudar P 1NH20CE050; Ravi B 1NH21CE401
The Earth offers a supply of clean air and drinkable water, with a wealth of undiscovered components hidden beneath the surface. One of the main issues facing emerging nations like India is the extreme pollution of their waterways. There is pollution in the air. Chemicals are often used as raw materials in industrial operations. A few of them cause pollution and are really dangerous. As a result, there is an increase in the release of dangerous substances into the land, water, and air. Two crucial natural resources—air and water—determine future wealth and stability. at order to assist the authorities at crisis management centers in identifying and foreseeing water and air pollution, we have built the Water and Air Monitoring System. It takes work to keep farmland productive and healthy. It necessitates an understanding of various training and care techniques that have been refined over countless years. In many areas, synthetic fertilizers have supplanted natural fertilizers in recent years, giving farmers more options when it comes to sophisticated land management that maximizes yields. Achieving the soil's natural balance is still crucial for sustainable production, though, and farmers need to be proactive in keeping an eye on the composition of their soil. Technological developments in agriculture assist farmers in obtaining precise information about their farms to enable them to make better decisions. Drone-enabled multispectral remote sensing for soil mapping is one instance of this kind of technology; it can assess acres of farmland utilizing sophisticated. Sampling soil is a crucial method for obtaining data in order to make informed judgments about field fertilizer. Soil sampling may be required every 10 hectares, depending on country regulations. However, this is not enough for precision farming. To collect soil samples from consistent locations while minimizing the number of samples required, the field is divided into smaller areas called management zones.. In this paper, a unique method for autonomously locating soil sample locations is presented.
Transformative Potential of Care Compass
(NHCE, 2024) Pallavi Sharma 1NH20AI074; Shadab Khan N A 1NH20CE043 ;Prasanna Kotyal 1NH20AI079; Smirna Paul1NH20AI099
Care Compass, a revolutionary Doctor GPT system, reshapes the healthcare landscape by harnessing advanced AI technologies. Beyond traditional symptom diagnosis, this platform pioneers emotional intelligence evaluation, providing a nuanced understanding of users' well-being. It seamlessly integrates health resources, self-care regimens, and acknowledging the holistic connection between emotional and physical health. The system comprises four sections: symptom diagnosis, calorie tracker, emotional intelligence support chatbot, and healthy meal planner using custom food recommendation. Through API endpoints, machine learning models have been seamlessly integrated into an interactive Streamlit-based web application. Firebase is seamlessly integrated into the web app, to employ Firebase Authentication for user sign-in methods like email/password or social logins. The platform's Realtime Database offer scalable NoSQL databases, enabling real-time data synchronization and collaboration. This comprehensive approach signifies a transformative leap in healthcare management, where Care Compass not only diagnoses and treats ailments but also empowers individuals to proactively manage their well-being. The platform's multifaceted capabilities hold the potential to significantly impact the industry, fostering a paradigm of patient engagement in their healthcare journey, ultimately leading to enhanced health outcomes and an elevated standard of overall well-being.
P2P Machine Learning Serverless Architecture
(NHCE, 2024) TOSHIT G 1NH20CE054; SARTHAK RAI 1NH20CE042; ABHISHEK SAHOO 1NH20CS008; APEKSHA SAWARN 1NH20CE003
Within the rapidly developing field of deep learning, this work presents a novel architecture for safe and efficient asynchronous training in serverless peer-to-peer (P2P) networks. The serverless paradigm combined with a peer-to-peer architecture offers a fault-tolerant and scalable environment for cooperative deep learning. In order to determine the most effective way to divide and distribute data among serverless nodes, the study delves deeply into the complexity of data management. By utilizing asynchronous communication protocols to process data asynchronously, nodes can take part in the training process without the central server. In addition to improving scalability, this decentralized strategy reduces the possibility of bottlenecks that come with conventional centralized structures. A high priority is given to security, with end-to-end encryption being implemented to guarantee the confidentiality of data transfer and model changes. Distributed logging makes it easier to monitor and debug in real time, enabling problems to be found and fixed as they happen. This all-inclusive architecture not only addresses the particular difficulties presented by P2P networks and serverless computing, but it also offers a flexible solution suitable for a broad spectrum of deep learning applications.
Detection of Autism Spectrum Disorder Using Machine Learning
(NHCE, 2024) Darshna V 1NH20CE009; M kumar Venkat 1NH20ME075; Omini rao N 1NH20CE029; Prajwal 1NH20ME085
The exponential disorder known as autism spectrum disease has a profound impact on how individuals behave and engage in their communities. Children diagnosed with autism spectrum disorder may find it difficult to interact socially and learn new words. Unusual behavior that parents observe in their autistic children includes poor motor skills and repetitive movements of their hands and head, as well as violent head and body jerks. While there is no known cure for ASD, many children's lives can be greatly enhanced by early intervention. For this reason, ASD is called a lifelong illness. Depending on the illness's complexity, severity, and symptoms, multiple factors can contribute to ASD. Environment and genetics play important roles. Early autism prediction has become effortless because of artificial intelligence and machine learning (ML). Even though several studies have been carried out utilizing diverse methodologies, these inquiries have not produced any definitive results regarding the capacity to anticipate autism characteristics across different age groups. Although the model can be applied to both toddlers and adults, the primary focus of this project is the early detection of autism disorder in toddlers. ASD symptoms typically appear between the ages of 12 and 18 months, so when they are identified early on, a toddler's communication skills can be improved through therapy.
Tuberculosis and Pneumonia Detection Using Chest X-Ray
(NHCE, 2024) Pavana M 1NH20CE031; K Harshith 1NH20IS190; R Manasa 1NH20CE034; Shridhar Gavadi 1NH21IS415
Artificial intelligence, particularly machine leaming, is revolutionizing numerous fields by either supplementing or replacing human efforts, leading to enhanced efficiency and autonomy in systems. Healthcare stands as a notable domain ripe for collaboration with AI and machine learning, offering smoother and more efficient operations. In the context of the modern era, characterized by a searcity of quality radiologists, the demand for AI-driven solutions in chest X-ray-based disease detection has become increasingly imperative. This paper focuses on the classification of two major chest diseases, Pneumonia and Tuberculosis, through the implementation of advanced neural network architectures, specifically VGG19 and Convolutional Neural Network (CNN). The system provides diagnostic opinions to users, aiding medical professionals in making prompt and informed decisions about the presence of diseases. In comparison to prior research, this proposed model showcases the capability to detect two types of abnormalities, accurately disceming whether an X-ray is normal or exhibits abnormalities associated with pneumonia and tuberculosis. The VGG19-based CNN achieves remarkable accuracy of 93.75% for Tuberculosis, surpassing previous models. This advancement underscores the potential of leveraging state-of-the-art neural network architectures for precise and efficient disease classification, addressing the critical need for accurate diagnostic tools in the medical field
A Novel based approach of home automation system for constrained edge IOT devices
(NHCE, 2024) Priyanshu Roy 1NH20CE033; Vinay Krishnan 1NH20AI138; Tarun S 1NH20AI108; Kavya Sivakumar 1NH20AI047
In the context of contemporary living, existing smart home systems exhibit limitations in offering a comprehensive, tailored experience. Our forthcoming home automation project, leveraging BluFi Mesh and Matter OS integration, seeks to address these shortcomings. Focused on rectifying the deficiencies in current systems, our initiative aims to create an intelligent, adaptable ecosystem that emphasizes user preferences, robust security, seamless entertainment integration, energy efficiency, and real-time responsiveness. Our novel approach merges BluFi Mesh networking with the advanced Matter OS platform, establishing a robust infrastructure for a home server that operates discrectly, resourcefully, and securely, granting occupants control while safeguarding their privacy. Distinguishing our system integrates Al-powered features recognizing occupants, their preferences, and prioritizing safety. When entering the house, the occupant is instantly identified, customizing ambiance based on preferences, and ensuring security through face recognition and radar-based classifications. Beyond this, our system also aims to integrate popular entertainment services offering effortless access and control via simple voice commands or device taps. Additionally, our project emphasizes on power usage visualization that empowers users to monitor and optimize energy consumption, contributing to environmental sustainability while reducing utility costs. Our project aims for low-latency operations, guaranteeing instant, seamless interactions.
Two Wheeler Helmet and License Plate Detection
(NHCE, 2024) Himanshu Prasad 1NH20CE017; Ishita Chauhan 1NH20CE018; Sumeetkumar Savadatti 1NH20CE051; Vishwathika M 1NH20CE062
Road safety is a pressing global concern due to the substantial human and economic losses resulting from traffic accidents. As the world's population continues to grow, urbanize, and embrace diverse modes of transportation, there is an increasing demand for innovative solutions to address road safety challenges. Technology integration into road safety strategies holds significant potential for reducing accident rates, saving lives, and enhancing transportation efficiency. The convergence of cutting-edge innovations and road safety initiatives remains a cornerstone in building a safer and more sustainable future for our global road networks as technology advances. By integrating license plate recognition with two-wheeler helmet detection, this intelligent system aims to provide a comprehensive solution for enhancing law enforcement and traffic safety. The presented work showcases an innovative and highly efficient two-wheeler helmet and license plate detection system that leverages the synergistic integration of three cutting-edge technologies: YOLOv8 for object detection, k-means clustering for character segmentation, and optical character recognition (OCR) for text interpretation. This system represents a significant leap forward in the realm of helmet and license plate recognition, elevating road safety standards while simultaneously enhancing transportation efficiency. The proposed solution plays a crucial role in ensuring compliance with critical traffic regulations, particularly the mandatory requirement for two-wheeler riders to wear protective helmets. By autonomously detecting violations, such as riders operating without helmets, the system can generate fines automatically, alleviating the manual workload on traffic enforcement personnel. This technology-driven enforcement approach not only promotes responsible riding behaviors but also contributes to the broader mission of mitigating road accidents and preserving lives. Overall, this innovative solution represents a significant stride towards cultivating safer roadways, fostering a culture of road safety and law-abiding practices among all road users nationwide, while simultaneously paving the way for continued technological advancements in the field of automated license plate recognition.
FINGERPRINTINSIGHT: Unveiling Crime Pattern Through Deep Fingerprint Analysis
(NHCE, 2024) Revappa 1NH20CE037; Sachin B Handiganur 1NH20CE038; Sachin Y M 1NH20CE052; Sumit S Purandare 1NH20CE052
Fingerprint images in crime scene are important clues to solve serial cases. Crime scene fingerprint identification system using deep machine learning with Convolutional Neural Network (CNN). Images are acquired from crime scene using methods ranging from precision photography to complex physical and chemical processing techniques and saved as the database. The images collected from the crime scene are usually incomplete and hence difficult to categorize. The fingerprint recognition system is divided into three stages that are fingerprint image pre-processing, feature extraction and matching. Suitable enhancement methods are required for pre-processing the fingerprint images. The output of this stage will be passed to feature extraction stage which is extract the minutiae point (ridge ending, Bifurcation) from thinning fingerprint image, then the false minutiae removal is applied to extract real minutiae. The features of pre- processed data are fed into the CNN as input to train and test the network.
Detecting Dangerous Pests in Farms Using Deep Learning
(NHCE, 2024) E Vanija 1NH20CE012; Yuvaraj K M 1NH20IS170; Sivani Reddy K 1NH20CE049; Sudharshan R 1NH20IS188
This work offers a comprehensive approach that makes use of the YOLO v8 algorithm to effectively detect and manage agricultural pests. The system, embedded in a Streamlit application, allows farmers to upload crop images for real-time pest identification. Lever-aging the YOLO v8 model's accuracy, the system recommends organic pesticides tailored to the identified pests, promoting sustainable agriculture practices. To enhance user ac-cessibility, language translation and audio features are integrated, accommodating di-verse linguistic backgrounds and addressing literacy challenges. Results demonstrate the system's efficacy in pest detection and its potential to empower farmers with advanced technology for informed decision-making in crop protection. Agriculture plays a pivotal role in sustaining human life, but its productivity is consistently threatened by the adverse impact of pests on crops. As the global population grows, ensuring food security becomes an increasingly challenging task. Traditional pest management approaches often fall short in terms of efficiency, precision, and sustainability. This paper addresses this critical issue by proposing an innovative solution that leverages the YOLO v8 algorithm for robust pest detection and an Integrated Pest Management (IPM) system for sustainable agricultural practices. Pest infestations pose a significant threat to global food production, resulting in substantial economic losses and environmental consequences. Conventional pest management methods, often reliant on chemical interventions, raise concerns about environmental sustainability and the long-term health of agricultural ecosystems. Additionally, there exists a need for rapid and accurate pest detection methods to enable timely and targeted responses, minimizing the impact on crop yields.

Browse

Browsing 2023-24 (Autonomous) by Issue Date

Results Per Page

Sort Options