检索结果-内蒙古大学图书馆

Deep Learning-based Image Classification Framework for Rice Leaf Disease Detection: A Systematic Implementation Approach with Comparative Analysis 8

Deep Learning-based Image Classification Framework for Rice ...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Bortty, Joy Chakra Chakraborty, Gouri Shankar Ahmed, Tamjid Polok, Sourav Das Taki, Tanvir Ahmed Saha, Partha Westcliff University Department of Computer Science IrvineCA United States Lovely Professional University Dept. of Computer Science and Engineering Punjab Phagwara India

ISBN: (纸本)9798350367904

Approximately half of the population of the world consumes rice every day as their daily diet. In Asia, rice is the main ingredient of the meal. However, various diseases influence the production of rice being harmed. Many factors are responsible for the issue such as climate change, pathogens and excessive usage of pesticides. Varieties of leaf diseases are there that may harm quality of rice production. To protect the crop from diseases, farmers are relying on their eyes to identify diseases. Most often human eye can possibly make mistake identifying the disease. In consequence, harvested rice gets harmed both in quality and in quantity as well. To prevent those diseases, researchers have found cutting-edge techniques such as deep neural network with image processing based frameworks to detect and classify rice plant diseases to increase crops production and to reduce losses. Recent works present all the possible techniques related to rice plant disease classification and detection. This work represents a state-of-art in disease identification approach for rice leaf that can efficiently classify several types of diseases analyzing the leaf images. By adopting the efficiency of deep learning models with hyperparameter tuning, the methodology achieved accuracy of 97.10% with ResNet50. Importantly, the experimental outcomes of the proposed framework highlight the remarkable performance comparing the results with existing state-of-the-art technique. The aim of this research is to provide a more promising future for crop management through increased productivity while addressing the urgent problem of rice plant disease detection. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Detection of Multiple Plant Diseases by Leaf Diagnosis Using Deep Learning

Detection of Multiple Plant Diseases by Leaf Diagnosis Using...

引用

2024 International Conference on Artificial Intelligence and Emerging Technology, Global AI Summit 2024

作者： Mohd, Noor Mehta, Saransh Mehta, Prajjuwal Ghazi, Mohd. Rehan Chaturvedi, Narayan Martha, Sheshikala Dept. of Cse Dehradun India Department of Computer Science and Engineering Dehradun India Sr University Department of Computer Science and Artificial Intelligence Warangal India

ISBN: (纸本)9798350379716

India is a land of agriculture, and it has a deep impact in the economic growth of our country. Around 10-20% crops in India, suffer from various diseases that can lead to those crops getting wasted therefore this is one of the major concerns for the farmers to protect their crops from such diseases. To prevent the plants from getting wasted the disease should be detected as soon as possible so that the farmer can take the necessary steps to save the crops from getting wasted. Farmers have been using their conventional methods for years to identify diseases, but it is hard for them to identify various diseases with high accuracy. Now with the advancement in Artificial Intelligence and computer vision, we can use various techniques to solve this problem of disease detection in different plants with more accurate results. This will lead to a fast and early diagnosis of the disease and will help to decrease crop wastage making it more beneficial for the farmer and for the whole country. In this research paper, we have made use of Deep Learning a very popular technology nowadays as it provides various models and functionalities to work with images. We have used the Convolutional Neural Network (CNN) model for this research paper as it is one of the best in image classification and is also good at extracting smaller details from the image which will work well for the detection of disease in a plant by diagnosing the images of its leaf. We have made use of Plant Village dataset for our model which contains more than 60,000 RGB images of both healthy and unhealthy leaves as well. © 2024 IEEE.

关键词： CNN Deep Learning Plant Disease Plant Village dataset

来源：评论

学校读者我要写书评

暂无评论

Advancements in Environmental data Analysis for Climate-Resilient Agriculture Using Remote Sensing and Deep Learning

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 670-680页

作者： Nirmal, Khyati R. Reddy, Chilukala Mahender P, Jose Tulasi, Rajesh Maheswari, G. Uma Sapthami, I. SNJB’S Late Sau KBJ CoE Maharashtra Nashik India Department of Artificial Intelligence and Data Science GITAM Deemed to Be University Hyderabad India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R & amp D Institute of Science and Technology Chennai Avadi India Dept. of Computer Science and Engineering Koneru Lakshmaiah Education Foundation A.P Vaddeswaram Guntur Dist. India Department of Computer Science and Engineering RMK College of Engineering and Technology Chennai Pudhuvoyal India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Weather significantly influences agricultural productivity. Plant biotic and abiotic stressors are primarily induced by climate change, resulting in a detrimental effect on worldwide agricultural productivity. These two components are closely interconnected. This paper presents an innovative approach in smart agriculture for climate change combining remote sensing and a deep learning algorithm. The input is obtained as a multispectral environmental image and then subjected to noise reduction and normalisation processing. The image has been retrieved using a primary convolutional component with a stacked encoder model. The retrieved features are identified using ResNet graph reinforcement neural networks. The resulting classification output displays environmental imagery depicting climate variations. The agriculture sector has been analysed based on the classified climate analysis. The experimental results have been conducted on diverse farm datasets related to climate change, evaluating the detection accuracy, recall, mean average precision, normalized correlation, and F-1 score. The proposed method achieved a detection accuracy of 98%, a normalised correlation of 95%, a mean average precision of 92%, a recall of 97%, and an F-MEASURE of 94%. Machine learning can assist in monitoring and predicting the impact of climate change on food security, as indicated by the findings. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Climate change Deep learning model Remote sensing Smart agriculture Stacked encoder model

来源：评论

学校读者我要写书评

暂无评论

Heart Abnormality Detection Through Neural Network

Heart Abnormality Detection Through Neural Network

引用

2023 International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023

作者： Sarada, B. Smitha Chowdary, Ch. Babu, Jampani Satish Kavitha, K. Dept. of Data Science Secunderabad India Koneru Lakshmiah Education Foundation Dept. of Cse Guntur India P.B.Siddhartha College of Arts and Science Dept. of Computer Science Vijayawada India

ISBN: (纸本)9798350300857

This research study aims to develop an algorithm using phonocardiograms and Deep learning to differentiate between normal and abnormal heart sounds. The increase in cardiovascular diseases (CVD's), primarily caused by unhealthy habits, necessitates efficient diagnosis. The study utilized 1055 data samples, with 833 being normal and 182 abnormal, each lasting 5 seconds. Logistic regression and a three-layered neural network were initially applied, yielding accuracies of 42% and 63%, respectively. By extracting features using spectral roll-off and reapplying the models, accuracies improved to 79% and 86%. Up sampling the data further increased the accuracies to 86% for logistic regression and 89% for the three-layered neural network. The findings demonstrate the potential of audio-based algorithms in diagnosing cardiovascular diseases accurately. © 2023 IEEE.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Medication Management Application for Directly Observed Treatment of TB Patients 6

Medication Management Application for Directly Observed Trea...

引用

6th International Conference on Electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Tania, Marzia Hoque Rahman, Md. Asib Ahmed, Kadir Uddin Centre for Big Data Research in Health Unsw Sydney Sydney Australia Buet Dept. Computer Science and Engineering Dhaka Bangladesh Independent Researcher Sydney Australia

ISBN: (纸本)9798350385779

Tuberculosis (TB) poses global health challenges, requiring efficient management and monitoring of patients undergoing Directly Observed Therapy (DOT). This paper introduces TB-meds, a proposed software application to automate essential aspects of TB patient management. TB-meds aims to optimize resource utilization, improve patient care, and enhance TB control efforts. The application streamlines medication distribution, facilitates medication adherence monitoring, sends timely clinical test requirement's notifications, and enables convenient treatment status updates. By automating these processes, TB-meds has the potential to enhance efficiency, improve treatment outcomes, and reduce transmission rates. Its user-friendly interface promotes seamless communication among healthcare providers and TB patients. With tasks automation, the workload of DOT providers can be reduced, and more time can be dedicated to patient education, nutrition counseling, and lifestyle guidance. Additionally, TB-meds proposes to revolutionize TB surveillance by enhancing data collection and analysis capabilities, enabling informed decision-making and targeted interventions. The implementation of TB-meds holds promise for transforming TB patient management, contributing to better health outcomes, and advancing TB control efforts. © 2024 IEEE.

关键词： Telemedicine

来源：评论

学校读者我要写书评

暂无评论

Advancements in Cricket Shot Detection: Integrating Human Pose Estimation and Deep Learning for Automated Analysis 15

Advancements in Cricket Shot Detection: Integrating Human Po...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Datta, K.S. Sreekar Naidu, G. Narasimha Dasari, Rahul Jayakumar, T.V. Dept. Of Computer Science and Engineering Amrita School Of Computing Amrita Vishwa Vidyapeetham Amritapuri India Dept. Of Computer Science and Applications Amrita School Of Computing Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (纸本)9798350370249

Cricket, a sport loved worldwide, often presents challenges for aspiring players due to limited access to infrastructure and coaching resources. Cricket’s automated learning solutions are still largely unexplored, despite its popularity. By concentrating on the application of cricket shot detection, a crucial component of the game, this research fills this gap. One essential component of computer vision that becomes apparent in deciphering the subtleties of cricket shots is human stance estimate. Pose estimate provides a detailed examination of batting skills and footwork by tracking important areas on the batsman’s body, such as joints and limbs. MoveNet is a significant framework in this domain that has garnered accolades for its real-time performance and lightweight architecture, which enable accurate identification of human poses, which is a crucial requirement in the dynamic world of cricket. This study explores the combination of deep learning techniques and human pose estimate for cricket shot recognition. More precise and reliable cricket shot identification and classification are made possible by the model’s ability to extract complex patterns and features from the input data by utilizing deep learning techniques. Our goal is to automatically identify and classify cricket shots based on players’ minor motions through theoretical investigation, empirical validation, and real-world applications. Through the integration of cutting-edge technologies, such as deep learning, with traditional cricket analysis, our goal is to gain a deeper understanding of the game and discover new avenues for sports analytics, coaching, and broadcasting. ©2024 IEEE.

关键词： Cricket (Sports)

来源：评论

学校读者我要写书评

暂无评论

Less is More: Deep Learning Framework for Digital Forensics in Resource-Constrained Environments 11

Less is More: Deep Learning Framework for Digital Forensics ...

引用

11th International Symposium on Digital Forensics and Security, ISDFS 2023

作者： Rath, Suman Das, Tapadhir Astaburuaga, Ignacio Sengupta, Shamik University of Nevada Reno Dept. of Computer Science & Engineering Reno United States University of the Pacific Dept. of Computer Science Stockton United States

ISBN: (纸本)9798350336986

Machine learning (ML)-enabled tools and techniques are an unavoidable necessity for modern digital forensics. However, the performance of such tools often requires extensive training using powerful computing environments that may expend thousands of dollars and several training hours for a single model. Further, this process necessitates using high-volume datasets that are generally unavailable due to court-mandated restrictions. To overcome these problems, this paper proposes using a two-layered strategy that fuses several features of transfer learning and knowledge distillation-based techniques to build lightweight neural networks that can be trained using low-volume datasets to achieve high accuracy. Experimental results highlight we achieved an accuracy of 98.5% and 97.5% during training and testing of the heavier ML model, and an accuracy of 97.08% and 97.2% on the lightweight ML model (during training and testing respectively), therefore demonstrating the robustness and validity of the proposed technique. © 2023 IEEE.

关键词： Digital forensics

来源：评论

学校读者我要写书评

暂无评论

Object Detection Framework Using OpenCV for Low Cost and High Performance 11th

Object Detection Framework Using OpenCV for Low Cost and Hig...

引用

11th International Conference on Intelligent Computing and Applications, ICRTC 2023

作者： Bhardwaj, Sarthak Soni, Pratyaksh Ul Haq, Furqan Masih, Alvin Precious Sharma, Puneet Dept. of Computer Science & Engineering Amity University Uttar Pradesh Noida India School of Computer Science & AI SR University Telangana Warangal India

ISBN: (纸本)9789819717231

In contemporary times, advancements in technology have led to a renewed interest in the development of autonomous vehicles, commonly referred to as self-driving cars. These vehicles are equipped with sensors and computer vision tools that enable them to detect and respond to their environment, reducing the need for human intervention in the navigation process. Given the transformative potential of this technology, there has been a growing emphasis on researching and developing autonomous vehicles as a way of revolutionizing the transportation industry. The goal of this research work is to code highly optimized plus parameterized Python algorithms that would drive the object detection systems like Canny edge, pedestrian, vehicle, etc., with the help of pre-existing object models with greater emphasis on reducing the cost-performance trade-off. Various object models like EfficientNet, YOLOv4, R-CNN, etc. were deployed and tested for creating comparison in terms of ease of deployment, efficiency, accuracy, computational, and hardware costs to filter out the most efficient model for the coded computer vision tools. These innovative systems will possess the capability to detect lane markings, accurately identify pedestrians and other vehicles, and continually monitor the vehicle's immediate surroundings, thereby providing real-time information to the autonomous driving system through highly customizable parameters that can be changed according to the needs. By default, the codes in the research work will be customized for Indian roads, which are known for their unique challenges, such as lack of lane markings, heavy traffic, and poor road conditions. However, challenges remain, including legal and regulatory issues, code robustness, hardware integration, public perception, acceptance, and ensuring the safety and security of the autonomous driving system. Despite these challenges, the potential of autonomous vehicles to revolutionize transportation is significant. © The A

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Smart Attendance Management System Using Face Recognition 1

Smart Attendance Management System Using Face Recognition

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Rawat, Shivam Goyal, Shweta Rawat, Nikita Graphic Era Hill University Dept. Computer Science & Engineering Dehradun India Graphic Era deemed to be University Dept. of Electrical Engineering Dehradun India

ISBN: (纸本)9798331518578

Managing attendance in educational institutions is often a time-consuming and error-prone task, with traditional methods like roll calls or sign-in sheets being inefficient and susceptible to proxy attendance. This paper presents a Smart Attendance Management System that leverages facial recognition technology to automate the attendance process. By using cameras to capture images of students, the system recognizes their faces and marks their attendance in real time. Developed in Python, the system employs the K-Nearest Neighbours (KNN) algorithm for accurate face recognition. Once attendance is recorded, it is stored in a CSV file and can be visualized using the flask web application. The proposed system significantly reduces manual effort, ensures accuracy, and operates efficiently in real-time environments. © 2025 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

LightNN: An Optimized Deep Learning Framework for Enhanced Fruit Classification

LightNN: An Optimized Deep Learning Framework for Enhanced F...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Afroj, Maharin Jahan, Israt Islam, Md Polash Saifur Rahman, Md. Bangladesh University of Business and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh Stockholm University Dept. of Computer and Systems Sciences Stockholm Sweden

ISBN: (纸本)9798331529765

The crucial field of fruit classification in computer vision and deep learning brings about breakthroughs that have broad applications in the retail and agricultural industries. By automating the identification and sorting of various fruit types, these technologies enhance efficiency, accuracy, and scalability, benefiting processes from farm production to market distribution. The integration of sophisticated algorithms and neural networks not only improves the speed and reliability of fruit classification but also offers the potential for real-time quality control and inventory management, revolutionizing traditional methods and paving the way for more innovative, data-driven approaches in these sectors. This study introduces LightNN, a novel and effective paradigm with a lightweight architecture that tackles the complex problems related to computational efficiency. Combining a small classifier with a simplified feature extractor, LightNN achieves the ideal balance between simplicity and accuracy. The feature extractor is capable of extracting hierarchical features from RGB images by using convolutional layers with ReLU activations and max-pooling procedures. The flattened output is then processed by the classifier, which consists of fully connected layers with ReLU activations and dropout regularisation. Remarkably, LightNN, with just 298,835 parameters, manages to get a respectable 96.37% test accuracy in fruit categorization tasks. The results highlight LightNN's promise as an effective and efficient fruit classifying method, particularly in situations with constrained computational resources. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：