检索结果-内蒙古大学图书馆

computationally Efficient Unsupervised Deep Learning for Robust Joint AP Clustering and Beamforming Design in Cell-Free Systems

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2025年第5期24卷 4250-4266页

作者： Chen, Guanghui Wang, Zheng Lin, Hongxin Huang, Yongming Yang, Luxi Southeast Univ Sch Informat Sci & Engn Nanjing 210096 Peoples R China Southeast Univ Natl Mobile Commun Res Lab Nanjing 210096 Peoples R China Purple Mt Labs Pervas Commun Ctr Nanjing 211111 Peoples R China

In this paper, we consider robust joint access point (AP) clustering and beamforming design with imperfect channel state information (CSI) in cell-free systems. Specifically, we jointly optimize AP clustering and beamforming with imperfect CSI to simultaneously maximize the worst-case sum rate and minimize the number of AP clustering under power constraint and the discrete constraint of AP clustering. Through transformations, the intractable simultaneous optimization of continuous and discrete variables is reduced to optimizing only the sparsity of the continuous variables, facilitating a computationally efficient unsupervised deep learning algorithm. In addition, to further reduce the computational complexity, a computationally effective unsupervised deep learning algorithm is proposed to implement robust joint AP clustering and beamforming design with imperfect CSI in cell-free systems. Numerical results demonstrate that the proposed unsupervised deep learning algorithm achieves a higher worst-case sum rate under a smaller number of AP clustering with computational efficiency.

关键词： Array signal processing Clustering algorithms Deep learning Optimization computational efficiency Indexes Wireless communication computational modeling computational complexity Backhaul networks Cell-free systems beamforming access point clustering imperfect channel state information unsupervised deep learning

来源：评论

学校读者我要写书评

暂无评论

Ultra-Lightweight Network for Medical Image Segmentation Inspired by Bio-Visual Interaction

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第4期35卷 3486-3497页

作者： Cai, Zhefei Fan, Yingle Zhu, Minwei Fang, Tao Hangzhou Dianzi Univ Sch Automat Hangzhou 310018 Peoples R China Univ Miami Dept Biomed Engn Miami FL 33124 USA

Computer-aided medical image segmentation helps to assist physicians in locating lesion area for the subsequent diagnosis and treatment. Due to the irregular shape of the target and the uneven sample size between the target and the background area, automatic segmentation of medical images is a challenging task. Many CNN-Based, Transformer-Based models deepen the number of network layers or introduce complex modules in order to improve the segmentation accuracy. Limited by the computational resources, these types of large models are not suitable for the actual clinical environment. Inspired by the rapidity, accuracy, and low consumption characteristics of bio-visual processing, the Ultra-Lightweight Network Inspired by Bio-Visual Interaction (BVI-Net) is constructed in this paper. The Global Pathway is constructed by simulating the dorsal stream, in order to extract global features rapidly, and the Local Pathway is constructed by simulating the ventral stream, in order to process local features finely. At the same time, the skip connection module integrating Graph Convolutional Network (GCN) attention mechanism is constructed to simulate the synchronous integration ability of the visual pathway for multi-level features. The International Skin Imaging Collaboration (ISIC) dataset, the Liver Tumor Segmentation (LiTS) dataset, and the Brain Tumor Segmentation Challenge (BraTS) dataset are used for experiments. The BVI-Net proposed in this paper requires only 0.026M parameters to achieve the excellent performance in three representative medical image segmentation datasets, which has certain advantages over state-of-the-art (SOTA) methods. The biological vision mechanism and the artificial intelligence algorithm are integrated in this paper, which provides new ideas for the construction of biological vision-guided deep learning models and promotes the development of biomimetic computational vision.

关键词： Feature extraction Image segmentation Transformers Kernel Accuracy Visualization computational modeling Biological system modeling Lesions Streaming media Biological visual pathway dual encoder architecture GCN attention mechanism state space models medical image segmentation

来源：评论

学校读者我要写书评

暂无评论

Federated Learning-Based Resource Allocation for V2X Communications

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第1期26卷 382-396页

作者： Bhardwaj, Sanjay Kim, Da-Hye Kim, Dong-Seong Kumoh Natl Inst Technol ICT Convergence Res Ctr Dept IT Convergence Engn Gumi Si 39177 South Korea

In federated learning (FL), devices contribute to global training by uploading only the local model gradients (outcomes), providing connected devices with the ability to learn while preserving privacy. FL-based resource allocation for V2X communications is proposed, referred to as FL-RA-V2X, which optimizes and maximizes the throughput of all vehicle users within the constraints of maximum power and the signal-to-interference-plus-noise ratio (SINR). It ensures fairness in resource allocation, meeting the minimum SINR requirements for cellular users and outage probability constraints for vehicle users. An approximate expression for vehicle users' throughput is derived, eliminating the non-convexity associated with the SINR expression through iterative calculations of auxiliary variables. The resource allocation is designed to allow each vehicle user to share uplink resources with cellular users, maximizing the number of vehicle users while utilizing their maximum power transmission capability. Simulation results demonstrate the fairness and enhanced throughput efficiency of the proposed approach compared to contemporary algorithms, considering vehicle outage ratio, computational complexity, computing time, maximum transmitting power, cumulative distribution function of achievable sum rates, and convergence metrics. Furthermore, the proposed approach addresses critical aspects, including high mobility and distributed V2V communications, asynchronous training issues in cellular V2X networks, and the convergence analysis under different conditions such as varied vehicle densities and mobility patterns. These considerations broaden the applicability and robustness of the FL-RA-V2X method across diverse scenarios. The analysis also explores the impact of vehicle speed, auxiliary variables, interference effects of cellular users, and the dependence of throughput on FL iterations.

关键词： Vehicle-to-everything Resource management Training Privacy Interference Convergence computational modeling Throughput Communication system security Signal to noise ratio Resource allocation federated learning V2X communications throughput SINR error probability fairness

来源：评论

学校读者我要写书评

暂无评论

PipeSFL: A Fine-Grained Parallelization Framework for Split Federated Learning on Heterogeneous Clients

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2025年第3期24卷 1774-1791页

作者： Gao, Yunqi Hu, Bing Mashhadi, Mahdi Boloursaz Wang, Wei Bennis, Mehdi Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China Univ Surrey Inst Commun Syst ICS 5GIC Guildford GU2 7XH England Univ Surrey Inst Commun Syst ICS 6GIC Guildford GU2 7XH England Univ Oulu Ctr Wireless Commun Oulu 90014 Finland

Split Federated Learning (SFL) improves scalability of Split Learning (SL) by enabling parallel computing of the learning tasks on multiple clients. However, state-of-the-art SFL schemes neglect the effects of heterogeneity in the clients' computation and communication performance as well as the computation time for the tasks offloaded to the cloud server. In this paper, we propose a fine-grained parallelization framework, called PipeSFL, to accelerate SFL on heterogeneous clients. PipeSFL is based on two key novel ideas. First, we design a server-side priority scheduling mechanism to minimize per-iteration time. Second, we propose a hybrid training mode to reduce per-round time, which employs asynchronous training within rounds and synchronous training between rounds. We theoretically prove the optimality of the proposed priority scheduling mechanism within one round and analyze the total time per round for PipeSFL, SFL and SL. We implement PipeSFL on PyTorch. Extensive experiments on seven 64-client clusters with different heterogeneity demonstrate that at training speed, PipeSFL achieves up to 1.65x and 1.93x speedup compared to EPSL and SFL, respectively. At energy consumption, PipeSFL saves up to 30.8% and 43.4% of the energy consumed within each training round compared to EPSL and SFL, respectively.

关键词： Servers Training computational modeling Federated learning Processor scheduling Mobile computing Artificial neural networks Scheduling Synchronization Peer-to-peer computing Split learning federated learning client heterogeneity parallel computing artificial intelligence of things (AIoT)

来源：评论

学校读者我要写书评

暂无评论

Training Latency Minimization for Model-Splitting Allowed Federated Edge Learning

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2025年第3期12卷 2081-2092页

作者： Wen, Yao Zhang, Guopeng Wang, Kezhi Yang, Kun China Univ Min & Technol Sch Comp Sci & Technol Xuzhou 221116 Peoples R China Brunel Univ London Dept Comp Sci Uxbridge UB8 3PH Middx England Nanjing Univ State Key Lab Novel Software Technol Nanjing 210008 Peoples R China Nanjing Univ Sch Intelligent Software & Engn Suzhou Campus Suzhou 215163 Peoples R China

To alleviate the shortage of computing power faced by clients in training deep neural networks (DNNs) using federated learning (FL), we leverage the edge computing and split learning to propose a model-splitting allowed FL (SFL) framework, with the aim to minimize the training latency without loss of test accuracy. Under the synchronized global update setting, the latency to complete a round of global training is determined by the maximum latency for the clients to complete a local training session. Therefore, the training latency minimization problem (TLMP) is modelled as a minimizing-maximum problem. To solve this mixed integer nonlinear programming problem, we first propose a regression method to fit the quantitative-relationship between the cut-layer and other parameters of an AI-model, and thus, transform the TLMP into a continuous problem. Considering that the two subproblems involved in the TLMP, namely, the cut-layer selection problem for the clients and the computing resource allocation problem for the parameter-server are relative independence, an alternate-optimization-based algorithm with polynomial time complexity is developed to obtain a high-quality solution to the TLMP. Extensive experiments are performed on a popular DNN-model EfficientNetV2 using dataset MNIST, and the results verify the validity and improved performance of the proposed SFL framework.

关键词： computational modeling Training Artificial intelligence Servers Resource management Edge computing Data models Load modeling Federated learning Minimization split learning edge computing computing task offloading resource allocation

来源：评论

学校读者我要写书评

暂无评论

UDMC: Unified Decision-Making and Control Framework for Urban Autonomous Driving With Motion Prediction of Traffic Participants

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第5期26卷 5856-5871页

作者： Liu, Haichao Chen, Kai Li, Yulin Huang, Zhenmin Liu, Ming Ma, Jun Hong Kong Univ Sci & Technol Guangzhou Robot & Autonomous Syst Thrust Guangzhou 511453 Peoples R China Hong Kong Univ Sci & Technol Div Emerging Interdisciplinary Areas Hong Kong Peoples R China

Current autonomous driving systems often struggle to balance decision-making and motion control while ensuring safety and traffic rule compliance, especially in complex urban environments. Existing methods may fall short due to separate handling of these functionalities, leading to inefficiencies and safety compromises. To address these challenges, we introduce UDMC, an interpretable and unified Level 4 autonomous driving framework. UDMC integrates decision-making and motion control into a single optimal control problem (OCP), considering the dynamic interactions with surrounding vehicles, pedestrians, road lanes, and traffic signals. By employing innovative potential functions to model traffic participants and regulations, and incorporating a specialized motion prediction module, our framework enhances on-road safety and rule adherence. The integrated design allows for real-time execution of flexible maneuvers suited to diverse driving scenarios. High-fidelity simulations conducted in CARLA exemplify the framework's computational efficiency, robustness, and safety, resulting in superior driving performance when compared against various baseline models. Our open-source project is available at https://***/henryhcliu/udmc_***.

关键词： Decision making Autonomous vehicles Vectors Safety Roads Motion control Vehicle dynamics Planning Numerical models computational modeling Autonomous driving decision-making motion control collision avoidance traffic rule optimal control curvy road

来源：评论

学校读者我要写书评

暂无评论

All-Rounder: A Flexible AI Accelerator With Diverse Data Format Support and Morphable Structure for Multi-DNN Processing

引用

IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS 2025年第5期33卷 1264-1277页

作者： Noh, Seock-Hwan Lee, Seungpyo Shin, Banseok Park, Sehun Jang, Yongjoo Kung, Jaeha Daegu Gyeongbuk Inst Sci & Technol DGIST Dept Elect Engn & Comp Sci Daegu 42988 South Korea DGIST Daegu 42988 South Korea Fitogether Seoul 04323 South Korea Samsung Elect Suwon 16677 South Korea Korea Univ Sch Elect Engn Seoul 02841 South Korea

Recognizing the explosive increase in the use of artificial intelligence (AI)-based applications, several industrial companies developed custom application-specific integrated circuits (ASICs) (e.g., Google TPU, IBM RaPiD, and Intel NNP-I/NNP-T) and constructed a hyperscale cloud infrastructure with them. These ASICs perform operations of the inference or training process of AI models which are requested by users. Since the AI models have different data formats and types of operations, the ASICs need to support diverse data formats and various operation shapes. However, the previous ASIC solutions do not or less fulfill these requirements. To overcome these limitations, we first present an area-efficient multiplier, named all-in-one multiplier, which supports multiple bit-widths for both integer (INT) and floating-point (FP) data types. Then, we build a multiply-and-accumulation (MAC) array equipped with these multipliers with multiformat support. In addition, the MAC array can be partitioned into multiple blocks that can be flexibly fused to support various deep neural network (DNN) operation types. We evaluate the practical effectiveness of the proposed MAC array by making an accelerator out of it, named All-rounder. According to our evaluation, the proposed all-in-one multiplier occupies 1.49x smaller area compared to the baselines with dedicated multipliers for each data format. Then, we compare the performance and energy efficiency of the proposed All-rounder with three different accelerators showing consistent speedup and higher efficiency across various AI benchmarks from vision to large language model (LLM)-based language tasks.

关键词： Artificial intelligence Convolution Training Artificial neural networks Arrays Data models computational modeling Internet AI accelerators Electronic mail Deep neural networks hardware acceleration multiple data format support multitenant execution

来源：评论

学校读者我要写书评

暂无评论

OVP-FL: Outsourced Verifiable Privacy-Preserving Federated Learning

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2025年第3期12卷 2057-2068页

作者： Li, Shilong Wei, Xiaochao Wang, Hao Shandong Normal Univ Sch Informat Sci & Engn Jinan 250358 Peoples R China

Federated learning, a prominent method, eliminates the need for users to upload their original data, enabling collaborative model training through the transmission of only the gradient information of their models. However, a deeper exploration of federated learning has uncovered vulnerabilities wherein the gradient information uploaded by users can be exploited by adversaries to reconstruct users' original data. Additionally, ensuring the integrity of the aggregation result remains a primary focus of research to protect users' legitimate interests. To address these issues simultaneously, this study proposes a new framework called Outsourced Verifiable Privacy-Preserving Federated Learning. This framework aims to provide reliable privacy protection to users. Additionally, it includes a validation function to detect malicious aggregation models submitted by the server, providing an almost cost-free solution that accommodates the possibility of dropout. Finally, the paper concludes with a comprehensive security analysis that evaluates the reliability of the scheme using different datasets. In comparison to VerifyNet, our scheme demonstrates a significant advantage, with an approximate 100x improvement in the overall performance. And, the additional drop overhead is negligible. Simulation experiments demonstrate a significant improvement, including a reduction in communication and computation costs, showcasing the efficacy compared to existing verifiable privacy-preserving federated learning methods.

关键词： Servers Training Protocols Privacy Federated learning Data models computational modeling Collaboration Protection Reliability privacy preserving secure aggregation verifiable aggregation outsourced

来源：评论

学校读者我要写书评

暂无评论

A Deep-Learning-Based Traffic Classification Method for 5G Aerial Computing Networks

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第9期12卷 11244-11257页

作者： Chen, Chen Liu, Ziye Yu, Yuejun Jin, Fan Han, Wei Berretti, Stefano Liu, Lei Pei, Qingqi Xidian Univ Sch Telecommun Engn Xian 710071 Peoples R China Xidian Univ Xidian Hangzhou Inst Technol Hangzhou 311231 Peoples R China Xidian Univ Xidian Guangzhou Inst Technol Guangzhou 510555 Peoples R China CAST Natl Key Lab Sci & Technol Space Microwave Xian 710100 Peoples R China Xian Beilin Univ based Innovat Grp Co Ltd Enterprise Innovat Ctr Xian 710100 Peoples R China Univ Florence Dept Informat Engn I-50121 Florence Italy

With the rapid progress made in aerial computing technology and the increased popularity of fifth-generation (5G) networks, uncrewed aerial vehicles (UAVs) have been playing a crucial role in real-time data collection, processing, and transmission. However, due to the diversity in traffic generated by UAVs in various mission scenarios, there is a significant challenge posed in traffic classification. Therefore, a novel traffic classification model is proposed in this article on the basis of the spatial attention-enhanced convolutional neural network (SAE-CNN). This model proves effective in improving classification accuracy and latency, particularly in the context of various 5G services, such as enhanced mobile broadband (eMBB), ultrareliable low-latency communication (URLLC), and Internet service. Also, a 5G heterogeneous network platform is built to collect UAV-related aerial computing data, with extensive experiments performed to verify the superior performance of the SAE-CNN model compared to other state-of-the-art methods. The experimental results demonstrate that the proposed approach enables effective traffic management and classification for the application of UAV in complex 5G environments.

关键词： 5G mobile communication Autonomous aerial vehicles Radio access networks Edge computing computational modeling Ultra reliable low latency communication Real-time systems Accuracy Videos Reliability 5G Network aerial computing deep learning traffic identification uncrewed aerial vehicle (UAV)

来源：评论

学校读者我要写书评

暂无评论

Control-Oriented modeling of Single-Phase Transformers

引用

IEEE TRANSACTIONS ON MAGNETICS 2025年第5期61卷

作者： Schwartze, Nicolai Moschik, Sonja Reichhartinger, Markus Graz Univ Technol Inst Automat & Control A-8010 Graz Austria OMICRON Elect GmbH A-6833 Klaus Austria

A control-oriented mathematical model for single-phase transformers, including the effects of saturation, hysteresis, and classical eddy current losses, is proposed. The model equations are derived by combining the mechanical and electrical properties of the ferromagnetic transformers' core. This approach offers the flexibility for model enhancement by providing a procedure for incorporating additional domain-specific effects. It is shown that the model satisfies well-established properties of systems with hysteresis. The model is mathematically analyzed and experimentally validated on different transformers, confirming the applicability for a wide range of devices. Furthermore, it is demonstrated that the model structure is independent of any specific choice of the input signal form by reproducing experimental results for both sinusoidal and rectangular excitation voltages. The proposed model is compared with a single-phase transformer model based on the well-recognized Jiles-Atherton hysteresis model, which generally highlights the competitiveness in terms of accuracy and required computational effort for simulation studies. Therefore, the model is well suited for model-based controller design tasks and real-time applications.

关键词： Mathematical models Magnetic hysteresis computational modeling Circuit faults Springs Numerical models Magnetic domains Phase transformers Magnetic flux Torque Control-oriented model hysteresis properties loss separation model identification single-phase transformer

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：