检索结果-内蒙古大学图书馆

IEEE Transactions on Green Communications and networking 2024年

作者： Asif, Muhammad Bao, Xu Ali, Zain Ihsan, Asim Ahmed, Manzoor Li, Xingwang Jiangsu University School of Computer Science and Communication Engineering Zhenjiang China University of California Department of Electrical and Computer Engineering Santa CruzCA United States University of Cambridge Department of Engineering CambridgeCB3 0FA United Kingdom Hubei Engineering University School of Computer and Information Science The Institute for AI Industrial Technology Research Xiaogan432000 China Henan Polytechnic University School of Physics and Electronic Information Engineering China Jiaozuo Key Laboratory of Crow-Sensing Network Jiaozuo454003 China

This manuscript introduces an efficient resource allocation framework for a transmissive reconfigurable intelligent surface (T-RIS) assisted Low Earth Orbit (LEO) satellite non-orthogonal multiple access (NOMA) system under residual hardware impairments (RHIs) resulting from imperfect transceiver hardware design. In particular, the goal is to maximize the sum rate of the considered multi-cluster based T-RIS assisted LEO-satellite NOMA network. This is achieved by optimizing the power-allocation of users, time-allocation for each cluster, and transmit passive beamforming of T-RIS node, while adhering to quality-of-service (QoS), time-allocation, and power-budget constraints. Moreover, the presented optimization algorithm tackles the considered highly non-convex problem in three steps. Firstly, the power-allocation of NOMA users is computed by exploiting Lagrange duality and sub-gradient methods. Secondly, the time-allocation for each cluster is determined based on the interior point method by exploiting Mosek-assisted CVX toolbox. Thirdly, the computation of passive beamforming employs semi-definite programming (SDP) and successive convex approximation (SCA) techniques, where a rank-1 solution is achieved by incorporating the Gaussian randomization method. Finally, numerical simulations affirm the effectiveness of the proposed optimization strategy, highlighting its superior performance in comparison to benchmark techniques. Notably, it proves to be highly effective in achieving fast convergence with only a few iterations. © 2017 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

An Efficient Approach for Load balancing in Software-Defined networks 6

An Efficient Approach for Load balancing in Software-Defined...

引用

6th International Conference on Computing, Communication and Security, ICCCS 2021

作者： Ali, Jehad Roh, Byeong-Hee Ajou University Department of Computer Engineering Dept. of Ai Convergence Network Suwon Korea Republic of

ISBN: (纸本)9781665440394

Software-Defined networking (SDN) premise sepa-rates the data plane from the control plane. The centralized control plane brings innovation, programmability, and flexibility for managing the underlying networks. In this paper, we propose a hierarchical control plane-based SDN scheme to achieve load balancing in SDN. The hierarchical architecture is composed of a load balancing control plane and a distributed control plane based SDN architecture. To achieve load balancing, we add an analytical network process (ANP)-based module to rank the controllers according to their load status, for which ANP is applied as an enabling module to forward the flows according to the load distribution of the controllers. The ANP module ranks the controllers according to their weights. Hence, it does not send the request to the overloaded controllers in the network. Our proposed scheme surpasses the analytic hierarchy process (AHP), and Default SDN based load balancing schemes. We have demonstrated the results in three Internet topologies i.e. Abilene, Chinanet, and OS3E regrading delay, and Jain's fairness index in Mininet emulator. © 2021 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning based Spectral Efficiency Maximization in STAR-RIS-Assisted Indoor Outdoor Communication

Deep Reinforcement Learning based Spectral Efficiency Maximi...

引用

IEEE Symposium on network Operations and Management

作者： Pyae Sone Aung Loc X. Nguyen Yan Kyaw Tun Zhu Han Choong Seon Hong Department of Computer Science and Engineering Kyung Hee University Yongin-si Republic of Korea Division of Network and Systems Engineering School of Electrical Engineering and Computer Science (EECS) KTH Royal Institute of Technology Brinellvägen 8 Stockholm Sweden Department of Electrical and Computer Engineering University of Houston Houston TX USA

The significant growth in data consumption among mobile users necessitates the development of new architecture to meet the increasing demand. On the other hand, reconfigurable intelligent surface (RIS) has grown in popularity in 6G due to its improved spectral efficiency, simplicity of deployment, and low cost. However, with the constrained limitation of the coverage by conventional RIS, the research direction has turned towards simultaneously transmitting and reflecting RIS (STAR-RIS) to provide 360° coverage alongside the benefits of RIS. In this paper, a STAR-RIS-assisted downlink communication system for both indoor and outdoor users is investigated. Then, the optimization problem to maximize the spectral efficiency while jointly controlling the beamforming power for each user and phase shift values of the STAR-RIS is formulated. Since the formulated problem is NP-hard and challenging to solve in polynomial time, a policy gradient method for reinforcement learning named proximal policy optimization (PPO) is implemented to solve the problem. To demonstrate the effectiveness of our proposed algorithm, extensive simulation results are executed. Numerical results prove that our proposed algorithm outperforms several benchmark schemes in the literature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Noisy Spiking Actor network for Exploration

arXiv

引用

arXiv 2024年

作者： Chen, Ding Peng, Peixi Huang, Tiejun Tian, Yonghong Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Network Intelligence Research PengCheng Laboratory Shenzhen China Department of Computer Science and Technology Peking University Beijing China

As a general method for exploration in deep reinforcement learning (RL), NoisyNet can produce problem-specific exploration strategies. Spiking neural networks (SNNs), due to their binary firing mechanism, have strong robustness to noise, making it difficult to realize efficient exploration with local disturbances. To solve this exploration problem, we propose a noisy spiking actor network (NoisySAN) that introduces time-correlated noise during charging and transmission. Moreover, a noise reduction method is proposed to find a stable policy for the agent. Extensive experimental results demonstrate that our method outperforms the state-of-the-art performance on a wide range of continuous control tasks from OpenAI gym. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Secured and Optimized Clustering Approch in Vehicular Ad-hoc network

A Secured and Optimized Clustering Approch in Vehicular Ad-h...

引用

Electrical, computer and Energy Technologies (ICECET), International Conference on

作者： Imran Khan Fazlullah Khan Asad Ali Bandar Alshawi Ryan Alturki Mohammad Wedyan Computer Science Department Abdul Wali Khan University Mardan KPK Pakistan Faculty of Science and Engineering School of Computer Science University of Nottingham Ningbo China Zhejiang China Department of Computer Science University of Engineering and Technology Peshawar KPK Pakistan Department of Computer and Network Engineering College of Computing Umm Al-Qura University Makkah Saudi Arabia Department of Software Engineering College of Computing Umm Al-Qura University Makkah Saudi Arabia Department of Computer Sciences Faculty of Information Technology and Computer Sciences Yarmouk University (YU) Irbid Jordan

ISBN: (数字)9798350395914

ISBN: (纸本)9798350395921

Vehicular ad hoc networks (VANETs) take vital role in intelligent transportation systems, but they face challenges due to dynamic network topology, impacting communication efficiency, especially with increasing active nodes. Security and privacy concerns are paramount, necessitating authentication to ensure only legitimate vehicles access the network. Secure vehicular clustering offers a solution, yet the number of clusters affects network dependability and efficiency. To tackle this, we present a secure clustering mechanism using Bat optimization algorithm, mimicking echolocation behavior to optimize clusters. We introduce an authentication technique for cluster heads to admit approved members, enhancing vehicular authentication. Simulations using MATLAB evaluate our approach, showing improved performance in end-to-end delay, overhead, and cluster head count compared to similar methods.

关键词： Privacy network topology Authentication Vehicular ad hoc networks Security Vehicle dynamics Optimization Intelligent transportation systems Faces Matlab

来源：评论

学校读者我要写书评

暂无评论

T³Planner: Multi-Phase Planning Across Structure-Constrained Optical, IP, and Routing Topologies

引用

IEEE Journal on Selected Areas in Communications 2025年第5期43卷 1823-1839页

作者： Yijun Hao Shusen Yang Fang Li Yifan Zhang Cong Zhao Xuebin Ren Peng Zhao Chenren Xu Shibo Wang National Engineering Laboratory for Big Data Analytics Xi’an Jiaotong University Xi’an China National Engineering Laboratory for Big Data Analytics and the Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an China School of Computer Science Peking University Beijing China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong China National Engineering Laboratory for Big Data Analytics XiÃan Jiaotong University XiÃan China

network topology planning is an essential multi-phase process to build and jointly optimize the multi-layer network topologies in wide-area networks (WANs). Most existing practices target single-phase/layer planning, and are incapable of satisfying all rigorous topological structure constraints (e.g., dual-homing rings) defined by network standards and operators, especially in large-scale networks. These significantly limit their usability and performance in production networks. We consider a general topology planning problem with typical structure constraints over three essential phases (greenfield, reconfiguration, and site expansion) and topological layers (optical, IP, and routing topologies). We present, T3Planner, a novel practical solver to this problem in production. Specifically, we develop a structure-driven encoder based on graph neural network (GNN) for concise structure encoding, and design a new learning framework with optical-centric layer compression/reconstruction and rule-aided reinforcement learning (RL) for fast convergence and high performance. Extensive experiments on nine real topologies demonstrate that T3Planner scales to large optical networks with hundreds of sites, saves 46.6% cost, and supports $3.12\times $ more demand when compared to related existing approaches.

关键词： Topology network topology Planning IP networks Optical fiber networks Routing Optical fibers Optical feedback Production Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Wi-Fi-based Approach for Recognizing Human-Human Interactions 12

A Wi-Fi-based Approach for Recognizing Human-Human Interacti...

引用

12th International Conference on Information and Communication Systems, ICICS 2021

作者： Alazrai, Rami Awad, Ali Alsaify, Baha A. Daoud, Mohammad I. German Jordanian University Department of Computer Engineering Amman11180 Jordan Jordan University of Science and Technology Department of Network Engineering and Security Irbid22110 Jordan

ISBN: (纸本)9781665433518

This paper presents a new approach for recognizing human activities that involve two humans, referred to as human-human interactions, using Wi-Fi signals. The proposed approach utilizes the Channel State Information (CSI) metric of the Wi-Fi signals to characterize the performed interactions in indoor environment. Specifically, the proposed approach analyzes the CSI data and extracts a set of time-domain and frequency-domain features that comprise salient information to distinguish between the performed interactions. The extracted features are used to construct a multi-class support vector machine classifier that can recognize the classes of the interactions comprised within the CSI data. The performance of the proposed approach was evaluated using our publicly available human-human interaction CSI dataset that contains the CSI data recorded for 40 pairs of participants while performing 13 interactions. The experimental results indicate that our proposed approach achieved an average recognition accuracy of 69.78% computed overall the 13 interactions. The reported results for each pair of participants demonstrate the feasibility of our proposed approach to recognize human-human interactions using the CSI metric of the Wi-Fi signals. © 2021 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

3D Object Detection with Attention:Shell-Based Modeling

引用

computer Systems Science & engineering 2023年第7期46卷 537-550页

作者： Xiaorui Zhang Ziquan Zhao Wei Sun Qi Cui School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringNanjing210044China 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&TechnologyNanjing210044China Department of Electrical and Computer Engineering University of WindsorWindsorN9B 3P4Canada

LIDAR point cloud-based 3D object detection aims to sense the surrounding environment by anchoring objects with the Bounding Box(BBox).However,under the three-dimensional space of autonomous driving scenes,the previous object detection methods,due to the pre-processing of the original LIDAR point cloud into voxels or pillars,lose the coordinate information of the original point cloud,slow detection speed,and gain inaccurate bounding box *** address the issues above,this study proposes a new two-stage network structure to extract point cloud features directly by PointNet++,which effectively preserves the original point cloud coordinate *** improve the detection accuracy,a shell-based modeling method is *** roughly determines which spherical shell the coordinates belong ***,the results are refined to ground truth,thereby narrowing the localization range and improving the detection *** improve the recall of 3D object detection with bounding boxes,this paper designs a self-attention module for 3D object detection with a skip connection *** of these features are highlighted by weighting them on the feature *** training,it makes the feature weights that are favorable for object detection get ***,the extracted features are more adapted to the object detection *** comparison experiments and ablation experiments conducted on the KITTI dataset verify the effectiveness of our proposed method in improving recall and precision.

关键词： 3D object detection autonomous driving point cloud shell-based modeling self-attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Robotics Architectures Based Machine Learning and Deep Learning Approaches 8

Robotics Architectures Based Machine Learning and Deep Learn...

引用

8th International Conference on Mechatronics engineering, ICOM 2022

作者： Alatabani, Lina E. Ali, E.S. Mokhtar, R.A. Khalifa, Othman O. Saeed, Rashid A. Department of Data Communications & Network Engineering Faculty of Telecommunications The Future University Khartoum Sudan port Sudan Sudan Khartoum Sudan Department of Computer Engineering College of Computers and Information Technology Taif University P.O. Box 11099 Taif21944 Saudi Arabia Department of Electrical and Electronics Engineering Faculty of Engineering International Islamic University Malaysia Malaysia The Libyan Center for Engineering Research and Information Technology Bani Walid Libya

ISBN: (数字)9781839538063

ISBN: (纸本)9781839538063

Robotics has been playing a vital role in our daily lives with a wide range of applications to improve the quality of life. With a variety of usable applications in the medical, manufacturing, and transportation industries, there is a continuous need for improving the performance of robotics for the importance of precision in executing commands and tasks. The implementation of precise commands has led to intense research on approaches to improve the performance of robotics. Machine Learning (ML) and Deep Learning (DL) have been drawing attention to applying architectures and algorithms to robotics which imposed a positive impact on the field of robotics. ML and DL applications in robotics include areas of computer vision, imitation learning, self-supervised learning, assistive and medical technologies, multi-agent learning, and manufacturing. This paper provides a comprehensive review of autonomous vs automatic robotics, robotic applications, extreme learning machine methods, and ML for soft robotics applications, in addition, to discussing the challenges, and future trends for AI applications in robotics applications. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Wavelet Convolutional Neural network for Low-Resolution Brain MRI Images 22

Wavelet Convolutional Neural Network for Low-Resolution Brai...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Oh, Soo Min Li, Yifan Chong, Jo Woon Massachusetts Institute of Technology Wireless Information and Network Sciences Laboratory Cambridge 02139 MA United States Massachusetts Institute of Technology Laboratory for Information and Decision Systems Cambridge 02139 MA United States Texas A&m University Department of Statistics College Station 77843 TX United States Texas Tech University Department of Electrical and Computer Engineering Lubbock 79409 TX United States Sungkyunkwan University Department of Electrical and Computer Engineering Suwon 16419 South Korea

ISBN: (纸本)9798331520526

Low-resolution images inherently contain less information, making effective feature extraction more challenging and posing difficulties for training neural networks. However, if neural networks can be trained successfully on low-resolution images, this could significantly reduce memory storage requirements and computational costs. In this study, we address the limitations of low-resolution brain MRI images by enhancing the available information through wavelet transform techniques. Specifically, we leverage the high-frequency coefficients obtained from wavelet transforms and the Hurst exponent to improve feature representation and optimize model training for convolutional neural networks (CNN), which is referred to as the wavelet CNN (WCNN). We demonstrate that WCNN outperforms standard CNNs in multi-class classification tasks, distinguishing among four categories of brain MRI images such as normal, glioma, meningioma, and pituitary tumor images. This approach highlights the potential to achieve high classification accuracy even with low-resolution data, ultimately reducing the memory and computational resources required for data processing and model training. © 2025 IEEE.

关键词： brain MRI images wavelet convolutional neural networks Wavelet transform

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：