检索结果-内蒙古大学图书馆

2024 IEEE Students Conference on engineering and Systems, SCES 2024

作者： Arora, Gautam Bhavadharini, R.M. School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350374711

This study presents an innovative technique that leverages convolutional neural networks (CNNs), an advanced computer vision methodology, to enhance the timely detection and classification of natural disasters. The objective is to develop a dependable model capable of categorizing various disaster- related photos and videos, such as cyclones, earthquakes, floods, and wildfires, by employing extensive datasets and sophisticated CNN architectures like Visual Geometry Group (VGG) including VGG16 and VGG19. A significant advancement introduced in this research is the seamless integration of robotics, enabling autonomous data collection and real-time decision-making at disaster sites. Through a technique encompassing model development and data preprocessing, the effectiveness of our approach in disaster scene classification is demonstrated. The findings exhibit remarkable performance: post 48 training epochs, the VGG19 model achieved an impressive 97% accuracy, while the VGG16 model achieved a commendable 93% accuracy. These outcomes underscore the potential of CNNs to revolutionize disaster management strategies and pave the way for swifter and more efficient responses to mitigate the impact of natural disasters on society. © 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

Image recognition of insect pests in Jingmen with YOLOv10 24

Image recognition of insect pests in Jingmen with YOLOv10

引用

7th International Conference on Machine Learning and Machine Intelligence, MLMI 2024

作者： Gao, Zheng-Ming Zhou, Qiqi Zhao, Juan Wang, Xiaoyu School of Computer Engineering Jingchu University of Technology Hubei Jingmen China

ISBN: (纸本)9798400717833

Along with the development of science and technology, intelligent agriculture has been popular and the computer vision (CV) was widely used in insect pest detection in order to prevent the flooding and help the pleasant. Considering the situation of low income and less education of Chinese pleasant, the latest YOLOv10 model was introduced to detect the insect pests in Jingmen in order to find a cheap, efficient, and real-time way to identify the insect pests. Five smaller YOLOv10 model variants were involved in evaluation with a revised version of Pest24 database, which includes five more species of insect pests dominating in Jingmen. Results were obtained with Adam optimizer and 200 epochs, and confirmed that the YOLOv10 variants models could all working efficient in recognition of insect pests. Considering the better performance and the real-time metrics, the YOLOv10n variants model could be selected for future application and serve pleasant efficiently. © 2024 Copyright held by the owner/author(s).

关键词： YOLO

来源：评论

学校读者我要写书评

暂无评论

Mean Field Analysis of Serverless Edge Computing for Smart Vehicle Applications 4

Mean Field Analysis of Serverless Edge Computing for Smart V...

引用

4th International Conference on Electronic Information engineering and computer Communication, EIECC 2024

作者： Yao, Yuan He, Rong Wuhan Institute of Technology School of Computer Science and Engineering Wuhan China

ISBN: (纸本)9798331534622

Smart cities and vehicles generate numerous time sensitive tasks, making edge computing a key solution for reducing latency. However, using serverless models at the edge faces challenges like dynamic city traffic and resource constraints. This study analyzes serverless edge computing for smart vehicles through modeling and experiments. we develop a mean field model captures steady-state system behavior under stochastic job arrivals, enabling efficient analysis of metrics like mean sojourn time and service degradation probability. Through experiments and simulations, we demonstrate the feasibility of serverless edge servers for low-latency offloading, providing insights for optimizing these systems in urban environments. © 2024 IEEE.

关键词： Edge Computing Mean field Model Performance Analysis Serverless

来源：评论

学校读者我要写书评

暂无评论

Green Edge Computing Sustainability using Game Theoretic Approach 15

Green Edge Computing Sustainability using Game Theoretic App...

引用

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

作者： Swain, Sujata Chakravarty, Krishna Jena, Ajay Kumar Dansana, Jayanti Gourisaria, Mahendra Kumar Bandyopadhyay, Anjan Kalinga Institute of Industrial Technology School of Computer Engineering Bhubaneswar India

ISBN: (纸本)9798350370249

increasing significance of the edge computing paradigm highlights the need to emphasize how important it is to incorporate sustainable principles into its implementation. This philosophy is best summed up by green edge computing, which outlines a dedication to running systems and services with efficient energy use and low environmental impact. Forward-thinking research projects, like the academic paper mentioned above, analyze the subtleties of green edge computing sustainability through an advanced game-theoretic framework. This groundbreaking work provides stakeholders in edge computing ecosystems with crucial insights by using game theory frameworks to clarify complex stakeholder dynamics and decision-making processes. By carefully examining tactics to improve sustainability, such as resource distribution, energy efficiency optimization, and environmental impact reduction, this academic discussion not only highlights issues but also offers practical ways to encourage sustainable behavior among participants. As a result, the integration of these sophisticated analyses sparks a paradigm change that leads to the achievement of Green Computing goals and has a revolutionary effect on the state of technology. © 2024 IEEE.

关键词： Ecological footprint Edge computing Energy efficiency Game theory Green edge computing Sustainable computing

来源：评论

学校读者我要写书评

暂无评论

Congestion Based Adaptive Association Mechanism for IEEE 802.11ah Based Large IoT Network 5th

Congestion Based Adaptive Association Mechanism for IEEE 80...

引用

5th EAI International Conference on Cognitive Computing and Cyber Physical Systems, IC4S 2024

作者： R, Nandhini R, Radha School of Computer Science and Engineering Vellore Institute of Technology–Chennai Chennai India

ISBN: (纸本)9783031770807

The IEEE 802.11 ah standard is the prominent protocol for medium range communication in the domain of Internet of Things (IoT), facilitating interaction between wireless sensor nodes and access points. Supporting up to approximately 8192 nodes connected to a single access point through single hop strategies, IEEE 802.11 ah employs CSMA/CA for the authentication and association process of sensor nodes with access point. However, the standard encounters challenges such as significant collisions and prolonged network setup times when attempting to associate an excessive number of wireless sensor nodes with a single access point, primarily due to authentication thresholds set at intervals. In this research, we propose a dynamic adjustment of the authentication threshold based on network congestion status. Learning parameters including the number of requests served successfully by the access point in the past, present and a congestion threshold are leveraged to adapt to current network congestion levels. Through evaluation using the LILD method in the ns-3 simulator, our approach demonstrates considerable enhancements in terms of collision reduction and network setup efficiency. This research endeavours to promote responsible network management practices for improving the performance and reliability of IEEE 802.11 ah based IoT deployments. © ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Forecasting Software Modules with Known Defects through the Quadratic Discriminant Analysis Feature Reduction Technique 4

Forecasting Software Modules with Known Defects through the ...

引用

4th International Conference on Emerging Systems and Intelligent Computing, ESIC 2024

作者： Rajvardhan Anand, Kunal Jena, Ajay Kumar School of Computer Engineering Kalinga Institute of Industrial Technology Bhubaneswar India

ISBN: (纸本)9798350349856

Software validation is crucial in software advancement to ensure defect-free software. Software Defect Prediction aims to identify defect-prone modules at an early stage. Machine learning techniques with SDP have recently gained traction, offering the potential to reduce maintenance costs. Feature reduction can improve the efficiency of an SDP model. Selecting a suitable FR method can be challenging. This paper proposes a novel FR technique based on Quadratic Discriminant Analysis (QDAFR) to achieve the best features. The proposed technique was implemented on four supervised learning classifiers: Naive Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) on six public NASA datasets. The conduct of the recommended technique was correlated with extant FR techniques: Principal Component Analysis (PCAFR), Linear Discriminant Analysis (LDAFR), and Kernel Principal Component Analysis (KPCAFR). Our experimental findings exhibited that the proposed technique gave higher accuracy and lower error rates with SVM. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sentiment Analysis of Customer Reviews Using Deep Learning, Data Augmentation and Explainable AI 4

Enhancing Sentiment Analysis of Customer Reviews Using Deep ...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Gokul Ram, K. Rajakumar, R. Ilavendhan, A. Padmanaban, R. Vijayaprabakaran, K. School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529635

Sentiment analysis of customer reviews is crucial for understanding consumer feedback and improving business strategies in the e-commerce sector. This study proposes an enhanced deep learning framework for sentiment analysis, utilizing Data Augmentation to improve prediction accuracy. Additional layers are integrated into the sentiment analysis model to better differentiate emotions in customer feedback. Furthermore, Explainable AI (XAI) techniques, specifically LIME, enhance transparency and provide clear insights into the model's predictions, thereby increasing trust in the results. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Securing Patient Health Records Using Blockchain

Securing Patient Health Records Using Blockchain

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Geethan, Daniel Anandha Arjun, P. Sanjay, K.S. Kanniga Devi, R. Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350378092

Traditional Electronic Health Records (EHRs) raise red flags about data privacy, security, and patient control. This research tackles these issues by proposing a new system where patients call the shots on their medical information. Our blockchain and InterPlanetary File System (IPFS) system puts patients in the driver's seat, granting them complete ownership and oversight of their health data. Patients securely submit their formatted medical history through a dedicated website, where it's stored on IPFS using a decentralized platform like Pinata. A unique code (Content Identifier or CID) acts like a key, linking the data to the patient's blockchain address via a smart contract (coded rules) for guaranteed accuracy and tracking. Our design prioritizes patient-controlled access. Healthcare providers can't access the data without the patient's explicit go-ahead. Access requests are sent directly to the patient, who has the final say on approval, ensuring their data privacy is always protected. Approved requests include the CID, allowing authorized physicians to retrieve the patient's data directly from IPFS storage. But patient control goes beyond just reacting to access requests. Our system empowers patients to be proactive. Using their unique login credentials, they can grab their CID directly from the blockchain. This retrieval process can be integrated into a secure patient portal or mobile app. With their CID in hand, patients can directly share it with chosen physicians, fostering collaboration in care without relying on intermediary platforms. This streamlined data exchange empowers patients and fosters a more collaborative healthcare environment where they actively manage their health information. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Classification of Healthy and Unhealthy Leaf Disease Using Modified MobileNetV2 5

Classification of Healthy and Unhealthy Leaf Disease Using M...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Kumar, E. Sudheer Kumar, Aakash Vardhan, Harsha Prasanth, Rajaratnam Sai, Pindi Punith Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350389609

A study employing Convolutional Neural Network (CNN) architectures, specifically MobileNetV2 band ResNet-50, compares their performance in classifying tomato leaf diseases, aiming to address the substantial challenges faced by farmers due to these diseases. Previously, various kinds of diseases belonging to tomatoes were identified using the model, which leads to lesser accuracy and would require more computational energy. The dataset utilized for the research consists of 1900 healthy and 1800 unhealthy tomato plant images which includes all the diseases, with an additional 500 healthy and 1080 unhealthy plant images set aside for validation. MobileNetV2, renowned for its lightweight design, achieves an impressive accuracy of 95.3% after customizing the model with various layers makes it unique from the other existing models. While ResNet-50, known for its deeper architecture, attains a lower accuracy of 51%. The selection of MobileNetV2 as the preferred model is based on its superior accuracy and computational efficiency. The study includes analysis utilizing backpropagation to understand weight update trends within the chosen models. These results highlight the potential of deep learning approaches, specifically MobileNetV2 and ResNet-50, in automated disease diagnosis in agriculture, offering solutions to mitigate crop losses and enhance productivity in tomato cultivation. Overall, the study contributes significantly to advancing the field of automated disease diagnosis in agriculture by leveraging deep learning techniques, particularly MobileNetV2 and ResNet-50, for the classification of tomato leaf diseases. The insights gained from this research have profound implications for improving crop yield and sustainability in tomato cultivation practices, ultimately aiding in the advancement of agricultural technology and practices. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

A Multi-AGV Routing Planning Method Based on Deep Reinforcement Learning and Recurrent Neural Network

引用

IEEE/CAA Journal of Automatica Sinica 2024年第7期11卷 1720-1722页

作者： Yishuai Lin Gang Hu Liang Wang Qingshan Li Jiawei Zhu the School of Computer Science and Technology Xidian UniversityXi’an 710000China Suzhou Mingyi Intelligence Warehousing Information Technology Co. Ltd.Kunshan 215300China the School of Information Engineering Chang’an UniversityXi’an 710000China

Dear Editor,This letter presents a multi-automated guided vehicles(AGV) routing planning method based on deep reinforcement learning(DRL)and recurrent neural network(RNN), specifically utilizing proximal policy optimi... 详细信息

关键词： network AGV Deep

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：