检索结果-内蒙古大学图书馆

3rd International Conference on electronics and Sustainable communication Systems, ICESC 2022

作者： Vijayakarthik, P. Nithiyanandam, N. Dhanasekaran, S. Kumar, A. Sivanesh Gobinath, D. Maheswari, S. Sir M Visvesvaraya Institute of Technology Department of Information Science and Engineering Bengaluru India Bharath Institute of Higher Education and Research Department of Computer Science and Engineering Chennai India Kalasalingam University Department of Information Technology Tamilnadu Srivilliputtur India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Sri ManakulaVinayagarEngineering College Department of Information Technology Puducherry India St.Joseph's College of Engineering Department of Electronics and Communication Engineering Chennai India

ISBN: (数字)9781665479714

ISBN: (纸本)9781665479714

To gather the most relevant data as well as information for a given activity, this paper looks at the challenge of focusing our attention on subsets of video streams. This is a foraging problem, which is how the challenge of monitoring is classified. Observer attentiveness may be modeled as foraging behavior using the developed probabilistic framework. The forager changes its focus from one stream or camera to the next based on what it sees, whether it's fascinating items or activity. Multi-stream video summary can benefit from the technique shown here. Furthermore, it may be used in conjunction with advanced video surveillance, such as activity and behavior analysis, as a first stage in the process. As a demonstration of the suggested technique's utility, findings from an experiment using a publicly available data set are offered. © 2022 IEEE.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Phase Optimization and Relay Selection for Joint Relay and IRS-Assisted communication 100

Phase Optimization and Relay Selection for Joint Relay and I...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Uyoata, Uyoata E. Akinsolu, Mobayode Obayiuwana, Enoruwa Sangodoyin, Abimbola Adeogun, Ramoni Aalborg University Wireless Communication Network Section Aalborg Denmark Wrexham University Faculty of Arts Computing and Engineering WrexhamLL11 2AW United Kingdom Obafemi Awolowo University Department of Electronic and Electrical Engineering Ife Nigeria University of Lincoln School of Computer Science LincolnLN6 7TS United Kingdom

ISBN: (纸本)9798331517786

The use of Intelligent Reflecting Surfaces (IRSs) is considered a potential enabling technology for enhancing the spectral and energy efficiency of beyond 5G communication systems. In this paper, a joint relay and intelligent reflecting surface (IRS)-assisted communication is considered to investigate the gains of optimizing both the phase angles and selection of relays. The combination of successive refinement and reinforcement learning is proposed. Successive refinement algorithm is used for phase optimization and reinforcement learning is used for relay selection. Experimental results indicate that the proposed approach offers improved achievable rate performance and scales better with number of relays compared to considered benchmark approaches. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

TernaryVote: Differentially Private, communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data

arXiv

引用

arXiv 2024年

作者： Jin, Richeng Gu, Yujie Yue, Kai He, Xiaofan Zhang, Zhaoyang Dai, Huaiyu Department of Information and Communication Engineering Zhejiang University China Department of Electrical and Computer Engineering North Carolina State University RaleighNC United States Electronic Information School Wuhan University China

Distributed training of deep neural networks faces three critical challenges: privacy preservation, communication efficiency, and robustness to fault and adversarial behaviors. Although significant research efforts have been devoted to addressing these challenges independently, their synthesis remains less explored. In this paper, we propose TernaryVote, which combines a ternary compressor and the majority vote mechanism to realize differential privacy, gradient compression, and Byzantine resilience simultaneously. We theoretically quantify the privacy guarantee through the lens of the emerging f-differential privacy (DP) and the Byzantine resilience of the proposed algorithm. Particularly, in terms of privacy guarantees, compared to the existing sign-based approach StoSign, the proposed method improves the dimension dependence on the gradient size and enjoys privacy amplification by mini-batch sampling while ensuring a comparable convergence rate. We also prove that TernaryVote is robust when less than 50% of workers are blind attackers, which matches that of SIGNSGD with majority vote. Extensive experimental results validate the effectiveness of the proposed algorithm. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: Enhancing low latency and high performance in clustered-based wireless sensor network routing using genetic algorithm for 5G networks

引用

Optical and Quantum electronics 2024年第11期56卷 1-2页

作者： Banu, Firdouse Udhayamoorthi, M. Ramana Gupta Nallagattla, Venkata Phaneendra Maguluri, Lakshmana Mahesh Kumar, N. B. Jayachitra, S. Department of Applied Information System Applied College King Khalid University Khamis Mushaiyt Saudi Arabia Department of Computer Science and Design Karpagam College of Engineering (Autonomous) Coimbatore India Department of CSE Prasad V. Potluri Siddhartha Institute of Technology Vijayawada India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram India Department of Computer Science and Engineering Hindusthan Institute of Technology Coimbatore India Department of Electronics and Communication Engineering PSNA College of Engineering and Technology Dindigul India

来源：评论

学校读者我要写书评

暂无评论

Exploring Efficient BCD to Binary Conversion Architecture Alternatives on FPGA

Exploring Efficient BCD to Binary Conversion Architecture Al...

引用

IEEE International Conference on High Performance Computing Workshops (HiPCW)

作者： Santosh Kumar Ayan Palchaudhuri Department of Electronics & Communication Engineering School of Electrical and Computer Sciences Indian Institute of Technology Bhubaneswar Khordha Odisha India

ISBN: (数字)9798331509118

ISBN: (纸本)9798331509125

BCD operands are used in embedded systems and human-centric applications due to their ease of interpretation. To optimize arithmetic operations on hardware designed for binary inputs, BCD inputs must be converted to binary. This paper explores FPGA-specific logic primitives, such as dual output look-up tables (LUTs) and carry chains, to implement efficient parallel, serial, and pipelined architectures for BCD-to-binary conversion. Primitive instantiation was employed to directly configure FPGA elements, enhancing design efficiency and performance. Multiple adder tree implementations were examined which suggested trade-off between speed and area.

关键词： Embedded systems High performance computing Conferences computer architecture Hardware Table lookup Logic Field programmable gate arrays Adders Arithmetic

来源：评论

学校读者我要写书评

暂无评论

Hybrid Optimization for Enhanced Retinal Image Classification Using Neural Networks

Hybrid Optimization for Enhanced Retinal Image Classificatio...

引用

Innovative Computing, Intelligent communication and Smart Electrical Systems (ICSES), International Conference on

作者： Anwar Basha H Deepak R Babu M Shaik Thasleem Bhanu B Amutha R. Madhavan Department of Computer Science and Engineering Rajalakshmi Institute of Technology Chennai Tamilnadu India Department of Computer Science and Engineering NITTE Meenakshi Institute of Technology Bengaluru Karnataka India Department of Electronics and Communication Engineering Rajalakshmi Engineering College Chennai Tamilnadu India Department of Mathematics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamilnadu India Department of Computer Science and Business Systems Jeppiaar Institute of Technology Chennai Tamilnadu India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

The present study proposes a hybrid optimization algorithm that involves the integration of Neural Networks (NN), Genetic Algorithms(GA), and Particle Swarm Optimization(PSO) to improve the accuracy and efficiency of retinal image analysis. First, a wide range of features are extracted from retinal images and normalized. Then a NN is constructed with its weights and biases initialized to process these features. The fitness of each feature subset is measured with the help of a network's output, quantified by a Mean Squared Error(MSE)-based fitness function. Receiving fitness values, the GA component picks out the most important subsets of features, which are refined with crossover and mutation operations to retain diversity and improve the search process. In a parallel process, PSO dynamically adjusts the position of particles representing subsets of features through modification of velocity and position vectors under the influences of cognition and society. With the proposed integrated approach, iteratively, an optimal feature subset is generated by minimizing error and maximizing classification performance. Finally, after convergence, this last optimized subset of features is used in the final tuning of the NN to achieve a far-reaching improvement in the accuracy of classification. This method takes advantage of the complementary strengths of NN, GA, and PSO; therefore, it is able to provide an effective solution for the optimization of features within medical image analysis.

关键词： Accuracy Artificial neural networks Retina Feature extraction Vectors Classification algorithms Particle swarm optimization Optimization Tuning Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

An IoT-based Smart Waste Management System for Efficient Waste Segregation and Collection

An IoT-based Smart Waste Management System for Efficient Was...

引用

International Conference on Innovations in Science, engineering and Technology (ICISET)

作者： Md Jiabul Hoque Sanzid Hossain Tayef Abdullah Al Noman Md Emdadul Hoque Bhuiyan Md. Razu Ahmed Md. Abdul Kader Zilani Department of Computer and Communication Engineering International Islamic University Chittagong Chittagong Bangladesh Department of Computer Science and Engineering International Islamic University Chittagong Chittagong Bangladesh Department of Electronics and Telecommunication Engineering International Islamic University Chittagong Chittagong Bangladesh Department of Electrical and Electronic Engineering International Islamic University Chittagong Chittagong Bangladesh

ISBN: (数字)9798350355499

ISBN: (纸本)9798350355505

Rapid urbanization in densely populated countries like Bangladesh presents significant challenges for traditional waste management systems. This inefficiency leads to environmental degradation and increased costs. Daily waste generation in urban areas is substantial, yet collection methods remain outdated, relying on fixed schedules and neglecting waste segregation. These practices contribute to soil and groundwater contamination from plastics and polythene. Modernizing waste collection necessitates the adoption of intelligent waste management systems. This paper proposes an Internet of Things (IoT)--based waste monitoring and management solution. Our system promotes waste segregation, reduces collection frequency, and optimizes bin placement. We introduce an intelligent bin that integrates with a central administration system. This bin monitors fill levels and analyzes data to inform bin placement strategies and collection route optimization. The resulting benefits include reduced workforce costs, lower fuel consumption, and minimized air pollution from waste collection vehicles. Additionally, the system alleviates traffic congestion and fosters a healthier living environment.

关键词： Waste management Cloud computing Costs Sensor systems Real-time systems Recycling Plastics Internet of Things Intelligent sensors Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Switched Capacitor Based Single-Switch Ultrahigh Step-Up DC-DC Converter

A Switched Capacitor Based Single-Switch Ultrahigh Step-Up D...

引用

China International Electrical and Energy Conference (CIEEC)

作者： Yu Fu Zepei Ren Shicheng Hao Shouxiang Li Wenhao Xie School of Automation Beijing Institute of Technology Beijing China School of Computer and Communication Engineering Northeastern University at Qinhuangdao Qinhuangdao China College of Electrical and Electronic Engineering Wenzhou University Wenzhou China

ISBN: (数字)9798350359558

ISBN: (纸本)9798350359565

This paper proposes a switched capacitor based step-up DC-DC converter with the advantages of single-switch, continuously adjustable ultrahigh voltage gain and low input current ripple. To achieve high gain characteristics, the converter utilizes a quadratic boost converter on the input side to ensure continuous input current. Additionally, it implants the second winding of a coupled inductor within it, connecting it to the first winding of the coupled inductor and a voltage multiplier. The analysis includes a discussion of the operating principle, the derivation of the steady-state key equations, the voltage and current stress on the components, and the boundary condition. A functional prototype is built to confirm the theoretical analysis.

关键词： Windings Capacitors Prototypes Voltage Switches DC-DC power converters Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

Home Automation Using Wi-Fi: ESP32-Based System for Remote Control and Environmental Monitoring

Home Automation Using Wi-Fi: ESP32-Based System for Remote C...

引用

Distributed Computing and Electrical Circuits and electronics (ICDCECE), IEEE International Conference on

作者： Abdul Lateef Haroon P S Mohammed Shafiulla Shaik Mohammed Naveed Suhail Ahmed Shaik Mohammed Nawaz Utkarsh Kumar Department of Electronics and Communication Engineering Ballari Institute of Technology & Management Ballari India Department of Computer Science and Engineering Ballari Institute of Technology and Management Ballari India Department of Computer Science and Engineering Ballari Institute of Technology & Management Ballari India Department of Artificial Intelligence and Machine Learning Ballari Institute of Technology & Management Ballari India

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318616

This project introduces a comprehensive home automation system leveraging Wi-Fi connectivity and ESP32 micro controllers, aimed at enhancing modern living through seamless automation and user-centric design. The background emphasizes the fusion of IoT technology with home automation, highlighting Wi-Fi's significance in enabling remote monitoring and control of household devices. Methodologically, the project integrates relay modules and DHT11 sensors, orchestrated through a user-friendly smartphone application. Results demonstrate successful implementation and testing, showcasing functionality, reliability, and user-friendliness. Real-time environmental monitoring and remote appliance control fulfill the objectives of enhancing home comfort, convenience, and energy efficiency. The conclusion underscores the project's contribution to advancing smart home technologies, offering users a scalable and customizable solution. Future research opportunities include enhancing system capabilities and addressing security and privacy concerns.

关键词： Energy efficiency Sensor systems Real-time systems Environmental monitoring Reliability Relays Wireless fidelity

来源：评论

学校读者我要写书评

暂无评论

Combining Fuzzy Logic and Reinforcement Learning for Resource Management in Edge Computing

Combining Fuzzy Logic and Reinforcement Learning for Resourc...

引用

electronics and Sustainable communication Systems (ICESC), 2020 International Conference on

作者： S. Ram Prasath M. Selvi R. Santhana Krishnan Ezhil E. Nithila P. Stella Rose Malar G. Ram Sankar Computer Science and Engineering SCAD College of Engineering and Technology Cheranmahadevi India Computer Science and Engineering Rajarajeswari College of Engineering Bangalore India Electronics and Communication Engineering SCAD College of Engineering and Technology Chranmahadevi India Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India Electronics and Communication Engineering J.P. College of Engineering Thenkasi India Department of Computer Science and Engineering Velammal College of Engineering and Technology Madurai India

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

With the wide spread of Internet of Things (loT) devices, edge computing plays a decisive part in meeting the computational demands of loT applications. Efficient resource allocation in such networks is essential to ensure optimal utilization of resources and meet the quality of service (QoS) necessities of loT applications. This research addresses the challenge of dynamic resource allocation in edge computing networks for loT applications through a novel hybrid AI approach, “FledegeRL.” By integrating fuzzy logic and reinforcement learning, FledegeRL aims to optimize resource utilization and enhance system performance. The proposed framework is evaluated through simulation analysis and compared with existing algorithms, including Q-Iearning, Fuzzy Logic Control, and Ant Colony Optimization, using metrics such as resource allocation accuracy, average throughput, and network overhead. The results demonstrate that FledegeRL consistently outperforms these algorithms, achieving higher accuracy, greater throughput, and lower network overhead. This highlights the potential of FledegeRL as an effective solution for dynamic resource allocation in edge computing environments.

关键词： Fuzzy logic Measurement Accuracy Heuristic algorithms Reinforcement learning Quality of service Throughput Dynamic scheduling Resource management Edge computing

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：