检索结果-内蒙古大学图书馆

Load Balancing Routing Algorithm for LEO Satellite Networks Based on Ant Colony Optimization

Internet technology Letters 2025年第3期8卷

作者： Zhi, Ruxin Wang, Jiahui Xu, Zhan Key Laboratory of Information and Communication Systems Ministry of Information Industry Beijing Information Science and Technology University Beijing China Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing China School of Information and Communication Engineering Beijing Information Science and Technology University Beijing China

To address the problem of the unbalanced load and optimize the traffic distribution of large-scale low earth orbit (LEO) satellite networks, this paper proposes a load-balancing routing algorithm for LEO satellite networks based on ant colony optimization. The algorithm establishes the global optimal initial path through the improved ant colony algorithm to bypass the network bottleneck, makes local adjustments to cope with burst traffic changes to avoid congestion, and optimizes the "inferior" paths through regular rerouting to improve the overall network performance. The results show that the algorithm performs well in terms of packet loss rate, throughput, and load balancing, which can effectively alleviate the link utilization imbalance problem and provide a more stable and efficient service for the satellite network. Among them, the packet loss rate is reduced by 7.8%, and the load distribution index is improved by 30%. © 2025 The Author(s). Internet technology Letters published by John Wiley & Sons Ltd.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Edge-Driven Industrial Computing Power Networks: Digital Twin-Empowered Service Provisioning by Hybrid Soft Actor-Critic

引用

IEEE Transactions on Vehicular technology 2025年第5期74卷 8095-8109页

作者： Zhang, Long Song, Deng-Ao Zhang, Hongliang Tian, Ni Zhuang, Zirui Niyato, Dusit Han, Zhu Hebei University of Engineering School of Information and Electrical Engineering Handan056038 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

With the proliferation of data-intensive industrial applications, the collaboration of computing powers among standalone edge servers is vital to provision such services for smart devices. In this paper, we propose an edge-driven industrial computing power network (CPN) by orchestrating the computing and network resources of edge servers through the centralized resource scheduling and decentralized task computing. However, efficient task offloading and collaborative processing is challenging, which requires higher degrees of network automation and intelligence. Therefore, we incorporate digital twins (DTs) into the edge-driven CPN architecture, where the DTs are created as the digital replicas to assist both the computation offloading and collaborative processing. A joint optimization problem of the computing power assignment, service association, task partition, and transmit power control is formulated for maximizing the system average weighted utility. Due to the temporal-spatial variability of tasks and the resulted dynamic environment, we transform the original problem as a Markov decision process aiming at maximizing the long-term average weighted utility. To efficiently handle the high-dimensional discrete-continuous action space, a hybrid soft actor-critic based deep reinforcement learning algorithm is developed for optimizing the joint design. Simulation results validate the superiority of our proposed algorithm over the benchmarks, showing the significant gains obtained by integrating DTs into the edge-driven CPN. © 1967-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Toward Understanding Federated Learning over Unreliable Networks

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2025年 3卷 80-97页

作者： Feng, Chenyuan Arafa, Ahmed Chen, Zihan Zhao, Mingxiong Quek, Tony Q. S. Yang, Howard H. EURECOM Department of Communication Biot06410 France University of North Carolina at Charlotte Department of Electrical and Computer Engineering CharlotteNC28223 United States Singapore University of Technology and Design Information Systems Technology and Design Pillar Tampines487372 Singapore Yunnan University Engineering Research Center of Cyberspace National Pilot School of Software Kunming650106 China Zhejiang University ZJU-UIUC Institute Haining314400 China Zhejiang University College of Information Science and Electronic Engineering Hangzhou310007 China University of Illinois at Urbana-Champaign Department of Electrical and Computer Engineering ChampaignIL61820 United States

This paper studies the efficiency of training a statistical model among an edge server and multiple clients via Federated Learning (FL) - a machine learning method that preserves data privacy in the training process - over wireless networks. Due to unreliable wireless channels and constrained communication resources, the server can only choose a handful of clients for parameter updates during each communication round. To address this issue, analytical expressions are derived to characterize the FL convergence rate, accounting for key features from both communication and algorithmic aspects, including transmission reliability, scheduling policies, and momentum method. First, the analysis reveals that either delicately designed user scheduling policies or expanding higher bandwidth to accommodate more clients in each communication round can expedite model training in networks with reliable connections. However, these methods become ineffective when the connection is erratic. Second, it has been verified that incorporating the momentum method into the model training algorithm accelerates the rate of convergence and provides greater resilience against transmission failures. Last, extensive empirical simulations are provided to verify these theoretical discoveries and enhancements in performance. © 2023 CCBY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive neural finite-time self-triggered control for nonstrict-feedback nonlinear systems with sensor faults

Robotic Intelligence and Automation

引用

Robotic Intelligence and Automation 2025年第3期45卷 373-385页

作者： Zhang, Wenxin Xu, Ning Zhao, Ning Al-Barakati, Abdullah A. College of Control Science and Engineering Bohai University Jinzhou China Department of Information Systems Faculty of Computing and Information Technology Communication Systems and Networks Research Group King Abdulaziz University Jeddah Saudi Arabia

Purpose: This paper aims to investigate the problem of adaptive neural finite-time self-triggered tracking control for interconnected large scale nonlinear systems in nonstrict-feedback forms with sensor faults. Design/methodology/approach: To begin with, by combining backstepping techniques and neural networks (NNs), an adaptive NN controller is designed to compensate for sensor faults. Then, command filters are introduced to deal with the complexity explosion problem in backstepping design processes. Moreover, to reduce unnecessary data transmissions, a self-triggered control strategy is presented. Findings: Based on self-triggered strategy, an adaptive neural finite-time control scheme for interconnected large-scale systems with sensor faults is proposed. Originality/value: This article considers sensor faults in interconnected large-scale nonlinear systems with nonstrict-feedback forms. Moreover, the introduction of command filters not only effectively avoids the complexity explosion problem arising from the repetitive differentiation of virtual control inputs, but also simplifies the controller design process. Besides, this paper proposes a self-triggered mechanism that calculates the next trigger point based on current system data, overcoming the need for continuous monitoring of measurement errors in event-triggered mechanisms. Furthermore, the controller guarantees the finite-time stability of interconnected large-scale systems, with the tracking error converging to a small neighborhood of the origin within a finite time frame. © 2025, Emerald Publishing Limited.

关键词： Large scale systems

来源：评论

学校读者我要写书评

暂无评论

Viscoelastic Cluster-Constrained PBD-Based Soft Tissue Behavior and Interactive Media Applications for Surgical Simulation

引用

IEEE Transactions on Multimedia 2025年 27卷 2206-2220页

作者： Wang, Zijun Li, Shijie Peng, Jun Tai, Yonghang Yu, Zhengtao Yunnan Normal University Yunnan Key Lab Optoelectronic Information Technology Kunming650000 China Institute of The First People's Hospital of Yunnan Province Department of Thoracic Surgery Kunming650000 China Yunnan Normal University Engineering Research Center of Photoelectric Detection and Perception Technology Kunming650000 China Kunming University of Science and Technology Yunnan Key Laboratory of Artificial Intelligence Kunming650500 China

The virtual surgery engine represents a crucial research domain within biomedical and information sciences. To address the real-time and realistic demands of virtual surgical robots for soft tissue deformation and cutting, the surface information and internal structure of organ models have been redefined. An enhanced Three-Parameter Mass-Ogden model, which incorporates nonlinearity and viscoelasticity in soft tissues, has been developed based on extended position dynamics. Cluster constraints for filling particles were introduced to improve the smoothness of surgical procedures. The relaxation and creep characteristics of real soft tissues were accounted for by evaluating the responses of various biological tissues to external stress and loads using the HY-0580 high-performance mechanical testing machine. Eight experiments were conducted for each tissue type, and five sets of valid data were averaged and fitted using the Three-Parameter Mass-Ogden mixed model. Surgical simulations were conducted using Abaqus, incorporating Young's modulus, stress-strain relationships, cutting depth, pressure distribution, real-time feedback, and comprehensive visualization. The model's effectiveness was further validated. The surgical platform was integrated into a virtual reality-based digital twin robot simulator for minimally invasive surgery, achieving a surgical operation refresh rate of 78.5 Hz, a visual refresh rate of 60 Hz, and a haptic feedback refresh rate of 1000 Hz. Comparative analysis with the Mass-Spring Model (MSM) and Finite Element Method (FEM) shows our model's superior balance of accuracy and efficiency. MSM is fast but imprecise, while FEM is accurate but computationally intensive. © 1999-2012 IEEE.

关键词： ABAQUS

来源：评论

学校读者我要写书评

暂无评论

Assortativity attention based Multi-Dim Graph neural Architecture Search under distribution shifts

引用

Neurocomputing 2025年 639卷

作者： Shao, Yinning Wang, Jingwei Wang, Qiyi Zhao, Yukai Ma, Yunlong Liu, Min Chen, Yufeng College of Electronic and Information Engineering Tongji University Shanghai201804 China College of Computer Science and Technology Tongji University Shanghai201804 China Institute of Systems Engineering Macau University of Science and Technology 999078 China

Graph neural architecture search (GraphNAS) has demonstrated significant advantages in automatically designing graph neural network architectures for graph classification tasks. However, a major limitation of GraphNAS is its vulnerability to distribution shifts, where the optimal architectures searched for training graphs may not generalize well to unseen testing graphs. Recent approaches have addressed this issue by tailoring neural architectures for each graph through differentiable search and weight sharing. Nevertheless, these methods are constrained by the number of candidate operations and neglect the importance of extracting node link patterns to distinguish different distributions. In this paper, we propose Assortativity-attention-based Multi-Dim Graph neural Architecture Search (AMDGAS), which tailors architectures end-to-end for each graph with unknown distribution from multiple search dimensions. Specifically, we extend the vertical depth of the architecture search space, defining multiple parallel search dimensions. Different dimensions share an operation-embedding mapping, enabling the model to conduct a multi-dimension search within single-dimension complexity. In addition, we model node link patterns and propose assortativity attention, which captures the regularities of graph distributions and guides architecture search across different dimensions while cutting off architecture subspaces that may have negative impacts under particular distributions. Experimental results on synthetic and real-world datasets with distribution shifts demonstrate that our proposed method surpasses state-of-the-art algorithms and achieves excellent out-of-distribution generalization. Our code is available at https://***/networkanddatasciencelab/AMDGAS. © 2025

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

EraW-Net: Enhance-Refine-Align W-Net for Scene-Associated Driver Attention Estimation

引用

IEEE Transactions on Multimedia 2025年

作者： Zhou, Jun Liu, Chunsheng Chang, Faliang Wang, Wenqian Hao, Penghui Huang, Yiming Yang, Zhiqiang Shandong University School of Control Science and Engineering Jinan250061 China Singapore University of Technology and Design Pillar of Information Systems Technology and Design 487372 Singapore

Associating driver attention with driving scene across two fields of view is a challenging cross-domain perception problem, which requires comprehensive consideration of cross-view mapping, dynamic driving scene analysis and driver status tracking. Previous methods typically analyze a single view or map attention to the scene through a two-step projection, failing to exploit their implicit connections and establish accurate associations. Moreover, simple fusion modules are inadequate for modeling the complex relationships between the two views, making information integration complicated. To address these issues, we propose EraW-Net, a novel end-to-end framework for scene-associated driver attention estimation by aggregating information from dual views. This method enhances the most discriminative dynamic cues, refines feature representations, and facilitates semantically aligned cross-domain integration through a W-shaped architecture, termed W-Net. Specifically, a Dynamic Adaptive Filter Module (DAF-Module) is proposed to address the challenges of frequently changing driving environments by extracting vital regions. It suppresses the indiscriminately recorded dynamics and highlights crucial ones by innovative joint frequency-spatial analysis, enhancing the model's ability to parse complex dynamics. Additionally, to track driver states during non-fixed facial poses, we propose a Global Context Sharing Module (GCS-Module) to construct refined feature representations by capturing hierarchical features that adapt to various scales of head and eye movements. Finally, W-Net achieves systematic cross-view information integration through its unique two-stage decoding strategy, addressing semantic misalignment in heterogeneous data integration. Experiments demonstrate that the proposed method robustly and accurately estimates scene-associated driver attention on large public datasets. © 1999-2012 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Automatic speaker identification system based on MLP network and deep learning in the presence of severe interference

引用

Multimedia Tools and Applications 2025年 1-42页

作者： Shafik, Amira Sedik, Ahmed El-Shafai, Walid Khalaf, Ashraf A. M. El-Rabaie, El-Sayed M. El-Samie, Fathi E. Abd Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Electrical Engineering Faculty of Engineering Minia University Minia61519 Egypt Smart Systems Engineering Laboratory College of Engineering Prince Sultan University Riyadh11586 Saudi Arabia Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafr Elsheikh University Kafr El‑Shaikh Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Automatic Speaker Identification (ASI) is so crucial for security. Current ASI systems perform well in quiet and clean surroundings. However, in noisy situations, the robustness of an ASI system against additive noise and interference is a crucial factor. An investigation of the impact of interference on ASI system performance is presented in this paper, which introduces algorithms for achieving high ASI system performance. The objective is to resist the interference of various forms. This paper presents two models for the ASI task in the presence of interference. The first one depends on Normalized Pitch Frequency (NPF) and Mel-Frequency Cepstral Coefficients (MFCCs) as extracted features and Multi-Layer Perceptron (MLP) as a classifier. In this model, we investigate the utilization of a Discrete Transform (DT), such as Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT) and Discrete Sine Transform (DST), to increase the robustness of extracted features against different types of degradation through exploiting the sub-band decomposition characteristics of DWT and the energy compaction property of DCT and DST. This is achieved by extracting features directly from contaminated speech signals in addition to features extracted from discrete transformed signals to create hybrid feature vectors. The enhancement techniques, such as Spectral Subtraction (SS), Winer Filter, and adaptive Wiener filter, are used in a preprocessing stage to eliminate the effect of the interference on the ASI system. In the second model, we investigate the utilization of Deep Learning (DL) based on a Convolutional Neural Network (CNN) with speech signal spectrograms and their Radon transforms to increase the robustness of the ASI system against interference effects. One of this paper goals is to introduce a comparison between the two models and build a more robust ASI system against severe interference. The experimental results indicate that the two proposed models lead to satisfa

关键词： Additive noise

来源：评论

学校读者我要写书评

暂无评论

A dynamic simulation model to improve the livability of transportation systems

引用

Public Transport 2025年第1期17卷 177-220页

作者： Suryani, Erma Hendrawan, Rully Agus Adipraja, Philip Faster Eka Widodo, Basuki Chou, Shuo-Yan Az-Zahra, Alifia Department of Information Systems Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia Department of Informatics Engineering Institut Teknologi Dan Bisnis Asia Malang Surabaya65113 Indonesia Department of Mathematics Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia Department of Industrial Management National Taiwan University of Science and Technology Taipei Taiwan Department of Civil Engineering Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia

Transportation users often face shortcomings, such as unreliable service causing uncertainty in transit, low quality of service, and loss of time due to road and highway congestion. This study aims to improve the livability of the transportation system by considering several factors. System dynamics is used as a model development method to analyze the relationship between complex and nonlinear variables affecting the livability of the transportation system. The system structure of a valid model can be modified by adding multiple feedback loops, new parameters, and changing the feedback loop structure to see how it affects other variables. The scenario model is built from a valid model by changing the model structure to improve the livability of the transportation system through improvements in the perception, safety, security, and health level of public transport, land use accessibility, and mitigation of air pollution. These strategies are expected to increase the livability of the transportation system by 71%, driven by the improvement in perception, safety, security level, and health level of public transport, land use accessibility, and decreased air pollution. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Land use

来源：评论

学校读者我要写书评

暂无评论

Machine Learning in Higher Education using RF and SVM for Pedagogical Enhancement 3

Machine Learning in Higher Education using RF and SVM for Pe...

引用

3rd International Conference on Integrated Circuits and Communication systems, ICICACS 2025

作者： Kunwar, Fateh Bahadur Srivastava, Satyajee Dhivya, R. Gulati, Monika Anand, Taruna Raj, D. Antony Arul Geetanjali Institute of Technical Studies Department of Computer Science and Engineering Udaipur India School of Engineering and Technology Manav Rachna International Institute of Research and Studies Department of Computer Science and Engineering Faridabad India M.Kumarasamy College of Engineering Department of Information Technology Karur India Ambala India University Department of Humanities and Social Sciences Dehradun India Psg College of Arts & Science Department of Software Systems Coimbatore India

ISBN: (纸本)9798331508456

AI's revolutionary potential in higher education is examined in this proposal, including how it could revolutionize teaching, learning, administration, and research. Adaptive learning platforms, intelligent tutoring systems, and virtual learning assistants may change how students learn by improving engagement, providing quick feedback, and enabling tailored learning. The suggested process includes preprocessing, feature extraction, and model training. Preprocessing involves de-anonymizing, tokenizing, and removing punctuation, spaces, and numbers before analysis. The linear transformation method PCA extracts features. Training the systems uses the RF -SVM approach, which combines the advantages of RF and SVM. The suggested RF -SVM model beats two RF and SVM models with an average accuracy of 90.39 *** improves resource use, strategic decision-making, and research capacity in university management. The RF-SVM model's success in academia highlights the practicality of AI-driven solutions. © 2025 IEEE.

关键词： Teaching

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：