检索结果-内蒙古大学图书馆

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Kavitha Dasari Asha V. Lavish Kansal Praveen Ashish Kumar Parashar Adil Abbas Alwan Institute of Aeronautical Engineering Dundigal Hyderabad Department of Master of Computer Applications New Horizon College of Engineering Bangalore Lovely Professional University Phagwara Lloyd Institute of Engineering & Technology Greater Noida Uttar Pradesh Lloyd Institute of Management and Technology Greater Noida Uttar Pradesh India College of Engineering Technology National University of Science and Technology Dhi Qar Iraq

In the realm of high-power photovoltaic (PV) systems, ensuring efficient and reliable performance demands precise thermal management. This study delves into the intricacies of thermal management and control strategies for interleaved boost converters (IBC), pivotal components in these systems. Interleaved topology, though recognized for its capability to reduce ripple currents and enhance efficiency, presents unique thermal challenges due to uneven current distribution among the parallel converters. This research introduces a smart thermal control methodology that amalgamates real-time temperature monitoring with adaptive control strategies, ensuring optimal thermal performance and preventing hotspot formation. Employing a combination of advanced sensors and sophisticated algorithms, the proposed system autonomously adapts to varying solar irradiances and ambient conditions, thereby ensuring consistent thermal stability. Experimental results demonstrate a significant reduction in temperature deviations among parallel converters and an overall enhancement in system reliability and efficiency. The findings from this research set the groundwork for future designs of PV systems, ensuring their sustainable and efficient operation under diverse conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Component Fault Diagnosability of Hierarchical Cubic Networks

引用

ACM Transactions on Design Automation of Electronic Systems 2021年第3期28卷 1-19页

作者： Huang, Yanze Wen, Kui Lin, Limei Xu, Li Hsieh, Sun-Yuan Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology No. 3 Xueyuan Road Fujian Fuzhou China College of Computer and Cyber Security Fujian Normal University No. 8 Xuefu South Road Fujian Fuzhou350117 China Department of Computer Science and Information Engineering National Cheng Kung University No. 1 University Road Tainan70101 Taiwan

The fault diagnosability of a network indicates the self-diagnosis ability of the network, thus it is an important measure of robustness of the network. As a neoteric feature for measuring fault diagnosability, the r-component diagnosability ctr(G) of a network G imposes the restriction that the number of components is at least r in the remaining network of G by deleting faulty set X, which enhances the diagnosability of G. In this article, we establish the r-component diagnosability for n-dimensional hierarchical cubic network HCNn, and we show that, under both PMC model and MM∗model, the r-component diagnosability of HCNn is rn-½(r-1)r+1 for n≥ 2 and 1≤ r≤ n-1. Moreover, we introduce the concepts of 0-PMC subgraph and 0-MM∗subgraph of HCNn. Then, we make use of 0-PMC subgraph and 0-MM∗subgraph of HCNn to design two algorithms under PMC model and MM∗model, respectively, which are practical and efficient for component fault diagnosis of HCNn. Besides, we compare the r-component diagnosability of HCNn with the extra conditional diagnosability, diagnosability, good-neighbor diagnosability, pessimistic diagnosability, and conditional diagnosability, and we verify that the r-component diagnosability of HCNn is higher than the other types of diagnosability. © 2023 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Development of Machine Learning Framework for the Protection of IoT Devices

Development of Machine Learning Framework for the Protection...

引用

International Conference on Computing Methodologies and Communication (ICCMC)

作者： R. Mohandas N. Sivapriya A. Sanyasi Rao K. Radhakrishna Madona B Sahaai Department of Electronics and Communication Engineering Balaji Institute of Technology & Science Warangal Telangana India Department of Computer Applications Cauvery College of Women Trichy Tamil Nadu India Department of Electronics and Communication Engineering Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai Tamil Nadu India

Internet of Things (IoT) has a wide range of threats to businesses, according to security experts. Organizations need an intelligent system that can automatically detect suspicious IoT devices linked to their networks. This study introduces a unique security framework powered by machine learning (ML) that automatically adapts to the growing security needs of the IoT sector. There should be a way to identify IoT devices that aren't on a trusted white list. In this article, a machine learning method has been used to recognize IoT device types from a white list by using network traffic data. Seventeen separate IoT devices, each representing one of nine different categories of IoT devices, were manually tagged to train and assess multi-class classifiers. The majority rule was used to classify block listed devices accurately using unidentified in 86% of trial forms, while authorized expedient categories stayed appropriately identified through the real kinds with 88% of forms. The detection times varied for different types of IoT devices. In addition, it shows how the machine learning-based IoT white-listing system can defend itself against hostile attacks.

关键词： Wireless communication Accesslists System performance Machine learning Telecommunication traffic Media Routing

来源：评论

学校读者我要写书评

暂无评论

EmT: A Novel Transformer for Generalized Cross-subject EEG Emotion Recognition

arXiv

引用

arXiv 2024年

作者： Ding, Yi Tong, Chengxuan Zhang, Shuailei Jiang, Muyun Li, Yong Liang, Kevin Lim Jun Guan, Cuntai College of Computing and Data Science Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore Wilmar International Singapore School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing210096 China

Integrating prior knowledge of neurophysiology into neural network architecture enhances the performance of emotion decoding. While numerous techniques emphasize learning spatial and short-term temporal patterns, there has been limited emphasis on capturing the vital long-term contextual information associated with emotional cognitive processes. In order to address this discrepancy, we introduce a novel transformer model called emotion transformer (EmT). EmT is designed to excel in both generalized cross-subject EEG emotion classification and regression tasks. In EmT, EEG signals are transformed into a temporal graph format, creating a sequence of EEG feature graphs using a temporal graph construction module (TGC). A novel residual multi-view pyramid GCN module (RMPG) is then proposed to learn dynamic graph representations for each EEG feature graph within the series, and the learned representations of each graph are fused into one token. Furthermore, we design a temporal contextual transformer module (TCT) with two types of token mixers to learn the temporal contextual information. Finally, the task-specific output module (TSO) generates the desired outputs. Experiments on four publicly available datasets show that EmT achieves higher results than the baseline methods for both EEG emotion classification and regression tasks. The code is available at https://***/yi-ding-cs/EmT. Copyright © 2024, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Developing Robust Cybersecurity Policies and Governance Frameworks in Response to Evolving Legal and Regulatory Landscapes

Developing Robust Cybersecurity Policies and Governance Fram...

引用

Emerging Trends in Industry 4.0 (ETI 4.0)

作者： Radhika Pandey Shaik Anjimoon V Asha Atul Singla Irfan Khan Zain Alabdeen Hasan Abed DoCSE GyanGanga Institute of Technology and Science Jabalpur M.P India Institute of Aeronautical Engineering Dundigal Hyderabad Department of Computer Applications New Horizon College of Engineering Bangalore Lovely Professional University Phagwara Knowledge Park II Lloyd Institute of Engineering & Technology Greater Noida Uttar Pradesh College of Health and Medical Technology National University of Science and Technology Dhi Qar Iraq

ISBN: (数字)9798350373783

ISBN: (纸本)9798350373790

This research introduces a comprehensive cybersecurity framework consisting of five interlinked algorithms: Threat Intelligence Integration, Risk Assessment and Management, Compliance Mapping, Incident Response Planning, and Employee Training and Awareness. Through comparative performance evaluation and ablation study, the framework demonstrates consistent superiority across key parameters. Visual representations, including bar charts, line charts, and pie charts, provide intuitive insights into effectiveness, adaptability, compliance, and overall performance. The ablation study underscores the synergistic importance of each algorithm, emphasizing the framework’s holistic nature. This research contributes to advancing cybersecurity methodologies, offering a dynamic and adaptive approach to safeguarding against evolving cyber threats.

关键词： Training Performance evaluation Visualization Technological innovation Law Heuristic algorithms Planning

来源：评论

学校读者我要写书评

暂无评论

Research on Majorization Algorithm and Application of Geotechnical engineering Structure Based on Granule Swarm Majorization

Research on Majorization Algorithm and Application of Geotec...

引用

International Conference on Smart Technologies For Smart Nation (SmartTechCon)

作者： A. Gnana Soundari Arun Balaji N Mohammed Hussien Al-Fatlawy Suseela D Jamvant Omkar V. Asha Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai Tamil Nadu India New Prince Shri Bhavani College of Engineering and Technology Tamil Nadu India College of Technical Engineering The Islamic University Najaf Iraq Department of Artificial Intelligence and Machine Learning Bannari Amman Institute of Technology Sathyamangalam Tamil Nadu India Department of Electronics & Communication IES College Of Technology Bhopal MP India Department of Master of Computer Applications New Horizon College of Engineering Bengaluru

The traditional majorization design method makes too many restrictions on the objective function to be optimized and its constraints, which brings a lot of inconvenience to solving majorization problems in practical projects. A new stochastic Optimization algorithm based on swarm intelligence - granule swarm algorithm (PSO) was put forward in, and it has been widely concerned by researchers. When the algorithm is initialized, the granules are randomly divided into several sub-granule groups, each sub-granule group evolves independently according to a given strategy, and random migration and adaptive mutation of granules are carried out in the specified period of evolution to maintain the diversity of the entire population., to avoid premature convergence. The inverse analysis of geotechnical engineering majorization is essentially a typical majorization problem of complex nonlinear functions. The use of global majorization algorithm is an ideal way to solve this problem. low productivity. The new algorithm is applied to the elastic-plastic parameter inversion of geotechnical materials. The results show that compared with the conventional granule swarm majorization algorithm, the improved algorithm significantly improves the search efficiency of parameters, and the results that meet the accuracy requirements can be obtained with less iterations, which reduces the amount of calculation of elastic- plastic back analysis of geotechnical engineering. It is a feasible parameter inversion method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ADHERENT-Net: An Adaptive Health Risk Estimation Network for Real-Time Environmental Tracking

ADHERENT-Net: An Adaptive Health Risk Estimation Network for...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： M. Priyadharshini V. Murugesh Subrata Chowdhury Bibhuti Bhusan Dash Utpal Chandra De Sudhansu Shekhar Patra Department of Computer Science and Engineering Faculty of Science and Technology(Icfai Tech) ICFAI Foundations for Higer Education Hyderabad India Department of CSE Koneru Lakshmaiah Education Foundation Vaddeswaram AP India Department of CSE Sreenivasa Institute of Technology and Management Studies Chittoor Anthra Pradesh India School of Computer Applications Kalinga Institute of Industrial Technology (KIIT) Deemed to be University Bhubaneswar Odisha India

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Air borne pollutants greatly affect people’s well-being, so more accurate predictions are essential for the assessment of urban risks. Adaptive Health Risk Estimation Network is proposed in this paper as ADHERENT-Net to predict immediate health risks from environmental data. The model uses LSTM networks for temporal patterns discovery and Dense Neural Network for general feature learning and an additional meta-learner that combines both branches for an enhanced prediction capability. This one is prevented by a particular choice of its loss function where underestimations of threats to health are punished severely enough to prompt timely actions. ADHERENT-Net has a good predictive accuracy: the coefficient of determination, R 2 , is equal to 0,90 and the mean absolute error (MAE) is equal to 0,15. The dual branch structure is capable of handling time-dependent and non-time-dependent data from each other and the meta-learner also increases flexibility in changing conditions such as air quality, and seasonality. Training employed miscellaneous environmental data set with the pre-processing of data completeness and normalized data. ADHERENT-Net creates a reliable foundation for real-time health risk prediction, which has substantial potential to enhance the efficiency of program interventions in urban areas. Future work will concern tuning of the elaborated model parameters, the validation in various scenarios, and the generalization of the framework in other healthcare settings.

关键词： Adaptation models Accuracy Adaptive systems Urban areas Neural networks Estimation Water quality Predictive models Real-time systems Long short term memory

来源：评论

学校读者我要写书评

暂无评论

A Lightweight CNN Based on Transfer Learning for COVID-19 Diagnosis

引用

computers, Materials & Continua 2022年第7期72卷 1123-1137页

作者： Xiaorui Zhang Jie Zhou Wei Sun Sunil Kumar Jha Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing 210044 China IT Fundamentals and Education Technologies Applications University of Information Technology and Management in RzeszowRzeszow Voivodeship100031Poland

The key to preventing the COVID-19 is to diagnose patients quickly and *** have shown that using Convolutional Neural Networks(CNN)to analyze chest Computed Tomography(CT)images is helpful for timely COVID-19 ***,personal privacy issues,public chest CT data sets are relatively few,which has limited CNN’s application to COVID-19 ***,many CNNs have complex structures and massive *** if equipped with the dedicated Graphics Processing Unit(GPU)for acceleration,it still takes a long time,which is not conductive to widespread *** solve above problems,this paper proposes a lightweight CNN classification model based on transfer *** the lightweight CNN MobileNetV2 as the backbone of the model to solve the shortage of hardware resources and computing *** order to alleviate the problem of model overfitting caused by insufficient data set,transfer learning is used to train the *** study first exploits the weight parameters trained on the ImageNet database to initialize the MobileNetV2 network,and then retrain the model based on the CT image data set provided by *** results on a computer equipped only with the Central Processing Unit(CPU)show that it consumes only 1.06 s on average to diagnose a chest CT *** to other lightweight models,the proposed model has a higher classification accuracy and reliability while having a lightweight architecture and few parameters,which can be easily applied to computers without GPU ***:***/ZhouJie-520/paper-codes.

关键词： Convolutional neural networks chest computed tomography image COVID-19 transfer learning mobileNetv2

来源：评论

学校读者我要写书评

暂无评论

An elliptic curve cryptography based enhanced anonymous authentication protocol for wearable health monitoring systems

An elliptic curve cryptography based enhanced anonymous auth...

引用

作者： Sowjanya, K. Dasgupta, Mou Ray, Sangram Department of Computer Applications National Institute of Technology Raipur Raipur India Department of Computer Science and Engineering National Institute of Technology Sikkim Ravangla India

The innovations in the field of wearable medical devices, wireless communication and low cost cloud computing aid the wireless body area network (WBAN) to become a prominent component of future healthcare systems. WBAN consists of medical sensors, which continuously monitor the patients’ vital signs and transfers this data to the remote medical server via the cloud. The continuous monitoring of the patients’ health data improves the quality of the medical service and also provides the source for future medical diagnosis. The medical information collected from WBAN is generally transmitted through wireless channel and therefore vulnerable to various information attacks. In this context, medical data security and privacy are key issues;hence there is a requirement of lightweight end-to-end authentication protocol to ensure secure communication. Recently, Li et al. presented a lightweight end-to-end authentication protocol for WBAN based on elliptic curve cryptography (ECC). However, through cryptanalysis, some security loopholes are found in this protocol. In this paper, an enhanced lightweight ECC based end-to-end authentication protocol is proposed to overcome the security vulnerabilities of Li et al.’s scheme. Further, the formal security analysis of the proposed scheme is done using BAN logic and AVISPA tool. The comparative analysis shows that the proposed scheme not only removes the security loopholes of Li et al.’s scheme but also reduces the overall complexity. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Interacting Data for Maintaining URLLC Requirements in 5G

Interacting Data for Maintaining URLLC Requirements in 5G

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： P Siva Satya Prasad Azizbek Khurramov Shivani Goyal Vinay Kumar Deolia Hassan M. Al-Jawahry R. Gunasundari Department of Information Technology Aditya Engineering College Surampalem India International School of Finance and Technology Tashkent Uzbekistan Department of Electrical and Communication Engineering Chandigarh Engineering College Chandigarh Group of Colleges Jhanjeri Mohali Punjab India Department of Electronics and Communication Engineering GLA University Mathura Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Computer Applications Karpagam Academy of Higher Education Coimbatore

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

The tactile web is the evolution of this global product network — machine-to-machine communications and human-to-machine interactions. Focused on interactive real-time applications, TI is available in technology, business and society. The fifth generation of technology does this by awful fast able ultra-reliable low latency... technologies. TI applications required high latency and reliability. Under 3rd generation consortium's URLLC (Ultra Reliable Low Latency Communications), it is expected to target as low latency of less than one millisecond and above the dependability should be greater/ equal 99.9949% for a single packet delivery transfer of size up to maximum=32 bytes[htmlspecialchars] 3GPPa s new radio access method and recommend 5g new air interfaces, band split diagonal multiplexed in adjustable frequency mode. However, the introduction of a RAT based around distinct physical layer technology results in some game-changing future technologies; largely surrounding network intelligence. It is expected that machine learning techniques will be necessary to design complex algorithms for QoS-aware radio resource management exploiting network resources and meeting 5G NR URLLC requirements in these scenarios. Therefore in this work we provide the adaptation of federated reinforcement learning machine learning approach with respect to 5G NR URLLC and also brief-out the relevant achievements for that. In this NR we deliver a detailed analysis of the TI-supporting Top layer signal access schemes for URL LC. Moreover, we define seven important potential future uses cases for Falkland Islands NR URL LC accelerators in 5G applications..

关键词： Uniform resource locators Surveys 5G mobile communication Wireless networks Reinforcement learning Tutorials Ultra reliable low latency communication Telecommunication computing Reliability Resource management

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：