检索结果-内蒙古大学图书馆

Communication-Efficient Distributed Bayesian Federated Learning Over Arbitrary Graphs

IEEE TRANSACTIONS ON signal processing 2025年 73卷 1351-1366页

作者： Wang, Sihua Guo, Huayan Zhu, Xu Yin, Changchuan Lau, Vincent K. N. Beijing Univ Posts & Telecommun Beijing Lab Adv Informat Network Beijing 100876 Peoples R China Beijing Univ Posts & Telecommun Beijing Key Lab Network Syst Architecture & Conver Beijing 100876 Peoples R China Hong Kong Univ Sci & Technol Dept Elect & Commun Engn Hong Kong 999077 Peoples R China Harbin Inst Technol Sch Informat Sci & Technol Shenzhen 518055 Peoples R China Guangdong Prov Key Lab Aerosp Commun & Networking Shenzhen 518055 Peoples R China Shenzhen Municipal Key Lab AIoT Commun Shenzhen 518055 Peoples R China

This paper investigates a fully distributed federated learning (FL) problem, in which each device is restricted to only utilize its local dataset and the information received from its adjacent devices that are defined in a communication graph to update the local model weights for minimizing the global loss function. To incorporate the communication graph constraint into the joint posterior distribution, we exploit the fact that the model weights on each device is a function of its local likelihood and local prior and then, the connectivity between adjacent devices is modeled by a Dirac Delta distribution. In this way, the joint distribution can be factorized naturally by a factor graph. Based on the Dirac Delta-based factor graph, we propose a novel distributed approximate Bayesian inference algorithm that combines loopy belief propagation (LBP) and variational Bayesian inference (VBI) for distributed FL. Specifically, VBI is used to approximate the non-Gaussian marginal posterior as a Gaussian distribution in local training process and then, the global training process resembles Gaussian LBP where only the mean and variance are passed among adjacent devices. Furthermore, we propose a new damping factor design according to the communication graph topology to mitigate the potential divergence and achieve consensus convergence. Simulation results verify that the proposed solution achieves faster convergence speed with better performance than baselines.

关键词： Bayes methods Training Convergence Inference algorithms Damping Brain modeling Approximation algorithms Optimization signal processing algorithms Federated learning Bayesian federated learning decentralized consensus optimization message passing

来源：评论

学校读者我要写书评

暂无评论

Fast Converging Algorithm for Blind Equalization With Gaussian and Impulsive Noises

引用

IEEE TRANSACTIONS ON signal processing 2025年 73卷 372-385页

作者： Li, Jin Zheng, Wei Xing Yang, Long Xidian Univ State Key Lab Integrated Serv Networks Xidian 710071 Peoples R China Western Sydney Univ Sch Comp Data & Math Sci Sydney NSW 2751 Australia

This paper proposes a blind equalization algorithm for dispersive wireless communication systems that employ high throughput quadrature amplitude modulation signals under both Gaussian and impulsive noise environments. A novel cost function that combines the modulus match error function with the negative Gaussian kernel function is established to efficiently obtain the weight vector associated with the blind equalizer. Some preferable properties of the novel cost function are presented. Intensive studies show that the proposed cost function efficiently reduces the maladjustment caused by the modulus mismatch error and efficiently suppresses the negative influence resulting from large errors. Moreover, an efficient successive approximation method for minimizing the established cost function is proposed for fast searching of the optimal weight vector. Very importantly, it is proved that the proposed successive approximation method possesses superlinear convergence. Finally, extensive simulations are provided to demonstrate that the proposed blind equalizer has better performances than the existing methods under both Gaussian and impulsive noise circumstances in terms of equalization quality and equalization efficiency.

关键词： Noise Blind equalizers Convergence signal processing algorithms Gaussian noise Equalizers Vectors Steady-state Cost function Symbols Blind equalization modulus match error negative Gaussian kernel successive approximation method fast converging speed

来源：评论

学校读者我要写书评

暂无评论

Diffusion Stochastic Optimization for Min-Max Problems

引用

IEEE TRANSACTIONS ON signal processing 2025年 73卷 259-274页

作者： Cai, Haoyuan Alghunaim, Sulaiman A. Sayed, Ali H. Ecole Polytech Fed Lausanne EPFL Sch Engn CH-1015 Lausanne Switzerland Kuwait Univ Dept Elect Engn Kuwait 12037 Kuwait

The optimistic gradient method is useful in addressing minimax optimization problems. Motivated by the observation that the conventional stochastic version suffers from the need for a large batch size on the order of O(epsilon(-2)) to achieve an epsilon-stationary solution, we introduce and analyze a new formulation termed Diffusion Stochastic Same-Sample Optimistic Gradient (DSS-OG). We prove its convergence and resolve the large batch issue by establishing a tighter upper bound, under the more general setting of nonconvex Polyak-Lojasiewicz (PL) risk functions. We also extend the applicability of the proposed method to the distributed scenario, where agents communicate with their neighbors via a left-stochastic protocol. To implement DSS-OG, we can query the stochastic gradient oracles in parallel with some extra memory overhead, resulting in a complexity comparable to its conventional counterpart. To demonstrate the efficacy of the proposed algorithm, we conduct tests by training generative adversarial networks.

关键词： Convergence Optimization Training Gradient methods Stability criteria signal processing algorithms Noise Complexity theory Accuracy Wireless communication Minimax optimization nonconvex Polyak-Lojasiewicz distributed stochastic optimization stochastic optimistic gradient diffusion strategy

来源：评论

学校读者我要写书评

暂无评论

Pulse Diversity Phase-Coded Waveform and Mismatched Filter Bank Design Via Periodic Ambiguity Function Shaping

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2025年第2期61卷 3440-3455页

作者： Liu, Lipeng He, Chuan Cao, Fei Lyu, Yan Xu, Jianfeng Rocket Force Univ Engn Xian 710025 Peoples R China

Pulse diversity phase-coded (PDPC) waveform has received considerable attention recently because of its applications to obtain synthetic bandwidth, mitigate range-Doppler ambiguity, or suppress artificial repeat jamming and clutter. However, when applied to pulse-Doppler (PD) radar, high range-Doppler sidelobes will occur at the receiver, which cannot be improved by classical ambiguity function (AF) shaping methods. To address this problem, we first derive the discrete periodic AF (PAF) to characterize the range-Doppler processing of the PD radar. On this basis, we formulate a joint design problem for PDPC waveform and mismatched filter bank over the range-Doppler bins of interest under signal-to-noise ratio (SNR) loss and constant modulus constraints, which can be used to simultaneously suppress strong sidelobe interference and artificial repeat jamming. To solve the PAF shaping problem, which contains high-order polynomial constraints, we generalize and apply the maximum block improvement type algorithm with the help of the alternating direction method of multipliers and introducing auxiliary variables. In particular, a time-varying step-size strategy based on the dual theory is presented to enhance the convergence performance and refine the optimal solution. Several simulations are performed to show the effectiveness of the presented approach in improving the detection performance of PD radar, especially under low SNR scenarios.

关键词： Radar Jamming Filter banks Spaceborne radar Interference Doppler effect Diversity methods signal to noise ratio Doppler radar signal processing algorithms Artificial repeat jamming maximum block improvement (MBI) mismatched filter bank periodic ambiguity function (PAF) pulse diversity phase coded (PDPC) waveform sidelobe interference waveform design

来源：评论

学校读者我要写书评

暂无评论

Robust Range Super-Resolution Imaging With Multicriteria Joint Constraints via Double Smoothed l0-Norm Under Limited Resources

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2025年第2期61卷 5145-5165页

作者： Liu, Zhexian Shao, Shuai Liu, Hongwei Su, Tao Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China

The radar's high-resolution range profile (HRRP) contains rich physical structural features of targets, making it of great value for target recognition and classification. However, in practical applications, the effective bandwidth of radar signals is limited due to the nonideal factors such as spectrum control, limited hardware equipment capabilities, and spectrum electromagnetic interference. Thus, it is difficult to reach the requirement of high-resolution and accurate target characterization in range profiles under limited resources, which will reduce subsequent detection, imaging, and recognition performance. To address the problem, this article proposes a robust range profile super-resolution method with multicriteria joint constraints of sparsity, low-rank, and Doppler under a multiple measurement vector model. In this technique, based on compressed sensing theory and adaptive filtering framework, a sparse reconstruction algorithm via double smoothed l(0)-norm is proposed, which constructs a continuously differentiable Gaussian class function to approximate the l(0)-norm. It combines accelerated gradient algorithm and zero attractor to optimize the multicriteria cost function and iteratively reconstruct the super-resolution range profile. The algorithm improves the super-resolution performance of range profiles, enhances the robustness against noise and complex range profile configurations, and can obtain high-precision HRRP of targets with limited radar resources. Extensive simulation and real data experiments demonstrate that it not only improves the average reconstruction accuracy of super-resolution range profile sequence, but effectively reduces the fluctuation of reconstruction errors. In addition, it does not require high azimuth resolution, and is also highly effective with a small number of sequence echoes.

关键词： Image reconstruction Superresolution Radar Accuracy Target recognition signal processing algorithms Scattering Radar imaging Vectors Doppler effect Compressed sensing (CS) double smoothed l(0) -norm (DSL0) high-resolution range profile (HRRP) limited resource multicriteria joint constraints super-resolution imaging

来源：评论

学校读者我要写书评

暂无评论

Gait Symmetry Analysis With FMCW MIMO Radar

引用

IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES 2025年

作者： Lopez-Delgado, Ignacio E. Wang, Dingyang Fioranelli, Francesco Grajal, Jesus Univ Politecn Madrid Informat Proc & Telecommun Ctr Madrid 28040 Spain Delft Univ Technol Microwave Sensing Signals & Syst Grp MS3 NL-2628 CD Delft Netherlands

Monitoring gait symmetry reliably is crucial, as it is an early indicator of Parkinson's disease (PD). In this work, a method is presented to analyze gait asymmetries using a 24-GHz frequency-modulated continuous-wave (FMCW) multiple-input-multiple-output (MIMO) radar in a nonclinical environment. The proposed method is validated by analyzing the gait of 60 people recorded in an environment that presents multiple challenges such as multipath, gait interruption events, and different trajectories, which cause aspect angle variability. This article presents algorithms to address these challenges to extract useful gait information from the radar data and discusses the performance of the proposed system, analyzing the ratio of correct feet identifications and the accuracy of the asymmetry gait parameters. It achieved a mean absolute error of the symmetry ratio below 8% for all gait parameters. This shows that the proposed system and algorithms are robust for both clinical and in-home implementations.

关键词： Radar Foot MIMO radar Azimuth signal processing algorithms Diseases Data mining Accuracy Transmitters Receivers Frequency-modulated continuous-wave (FMCW) radar gait analysis gait symmetry multiple-input-multiple-output (MIMO) radar Parkinson's disease (PD)

来源：评论

学校读者我要写书评

暂无评论

Deterministic Maximum Likelihood Algorithm for Sky-Ground Waves Recognition in ELoran Systems

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第4期74卷 6685-6690页

作者： Li, Yuzhou Xia, Xing Liu, Di Dong, Yan Sheng, Min Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China Key Lab Smart Earth Beijing 100029 Peoples R China Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China

It is crucial to recognize the sky and ground waves, i.e., to determine the delays of the waves, in enhanced long-range navigation (eLoran) systems. However, the performance of most existing algorithms sharply decreases when the delay differences Delta tau between the sky and ground waves are small or the signal-to-noise ratios (SNRs) are low. In this paper, after transforming the originally time-domain sky-ground waves recognition problem to the frequency domain, we interestingly find that it can be effectively addressed by the deterministic maximum likelihood (DML). Thus, we design a DML-based sky-ground waves recognition algorithm. The verification results based on both the simulated and the realistic data show that the DML outperforms the four representative algorithms, including the IFFT, the FOC-MUSIC, the WRELAX, and the LM, in terms of the success rate in recognizing the groundwave, particularly in situations with small Delta tau or low SNRs. Numerically, compared to the IFFT, the LM, and the FOC-MUSIC, the success rate achieved by the DML is improved by 67.11%, 66.67%, and 64.19% respectively, and the WRELAX fails to work, in a challenging situation of SNR =0 dB and Delta tau=37 mu s.

关键词： Delays Time-domain analysis signal processing algorithms Direction-of-arrival estimation Multiple signal classification Global navigation satellite system Discrete Fourier transforms Accuracy Vectors Time-frequency analysis Sky-ground waves recognition DML eLoran

来源：评论

学校读者我要写书评

暂无评论

Synchronous Acquisition Control System and Coordinate Correction Algorithm for Subway Tunnel Comprehensive Detection Equipment

引用

IEEE SENSORS JOURNAL 2025年第1期25卷 1440-1451页

作者： Sun, Minghao Xu, Xianlei Zhou, Donglin Li, Jinglin He, Xinyao China Univ Min & Technol Sch Earth Sci & Surveying & Mapping Beijing 100083 Peoples R China State Key Lab Fine Explorat & Intelligent Dev Coal Beijing 100083 Peoples R China

Crack, cavity, and leakage defects in subway tunnels significantly threaten tunnel operational safety. Due to the limited detection time window, the trend in the tunnel detection has shifted toward using multiple types of devices for comprehensive and rapid detection. However, the varying working methods and data structures of these devices present a significant challenge in achieving synchronous acquisition control and obtaining high-precision positioning data. The author's team proposed a comprehensive detection vehicle equipped with multiple devices. A synchronous acquisition control system was designed and developed based on the devices mounted on the detection vehicle. This system includes pulse signal processing, acquisition circuits, and corresponding software, enabling synchronous acquisition control and data association storage for different types of devices. To address the challenge of high-precision positioning of multisource heterogeneous data, a coordinate correction algorithm based on tunnel ring seam information was introduced. This algorithm significantly improves upon conventional tunnel positioning methods by positioning across different detection data, enhancing accuracy to the millimeter level. Through simulation experiments and field experiments in tunnels, the effectiveness of the synchronous acquisition control system and coordinate correction algorithm was verified. This method is particularly effective in long-distance detection, as it reduces cumulative mileage error and improves positioning accuracy. This study can provide effective technical support for the precise positioning of subway tunnel detection results and enhances the overall operational safety of subway tunnels.

关键词： Sensors Accuracy Public transportation Laser radar signal processing algorithms Cameras Point cloud compression Synchronization Sensor systems Control systems Comprehensive detection coordinate correction subway tunnel synchronous acquisition control

来源：评论

学校读者我要写书评

暂无评论

Broad Critic Deep Actor Reinforcement Learning for Continuous Control

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年 PP卷 PP页

作者： Thalagala, Shiron Wong, Pak Kin Wang, Xiaozheng Sun, Tianang Univ Macau Dept Electromech Engn Zhuhai Macau Peoples R China

In the domain of continuous control, deep reinforcement learning (DRL) demonstrates promising results. However, the dependence of DRL on deep neural networks (DNNs) results in the demand for extensive data and increased computational cost. To address this issue, a novel hybrid actor-critic reinforcement learning (RL) framework is introduced. The proposed framework integrates the broad learning system (BLS) with DNN, aiming to merge the strengths of both distinct architectural paradigms. Specifically, the critic network employs BLS for rapid value estimation via ridge regression, while the actor network retains the DNN structure to optimize policy gradients. This hybrid design is generalizable and can enhance existing actor-critic algorithms. To demonstrate its versatility, the proposed framework is integrated into three widely used actor-critic algorithms-deep deterministic policy gradient (DDPG), soft actor-critic (SAC), and twin delayed DDPG (TD3), resulting in BLS-augmented variants. The experimental results reveal that all BLS-enhanced versions surpass their original counterparts in terms of training efficiency and accuracy. These improvements highlight the suitability of the proposed framework for real-time control scenarios, where computational efficiency and rapid adaptation are critical.

关键词： Training Learning systems Accuracy Computational efficiency Zinc signal processing algorithms Optimization Artificial neural networks Stochastic processes Real-time systems Broad critic deep actor (BCDA) broad learning system (BLS) broad reinforcement learning (BRL) continuous control deep reinforcement learning (DRL)

来源：评论

学校读者我要写书评

暂无评论

Why AI: A Comparative Study for Detection Methods in DC Series Arc Fault

引用

IEEE ACCESS 2025年 13卷 42703-42722页

作者： Mao, Yufei Safa, Sadaf Smith, Gianni Wurth, Leon Weiss, Roland Hagemeyer, Jens Siemens AG D-91058 Erlangen Germany Bielefeld Univ Cognitron & Sensor Syst D-33619 Bielefeld Germany Univ Toronto Dept Biomed Engn Toronto ON M5S 1A1 Canada Univ Rhode Isl Dept Elect Comp & Biomed Engn Kingston RI 02881 USA Nuremberg Inst Technol Fac Elect Engn Precis Engn Informat Technol D-90489 Nurnberg Germany

With the advancement of direct current (DC) power grids, ensuring reliable fault detection for safety has become increasingly critical. DC series arc faults, in particular, remain challenging to detect accurately. Although artificial intelligence (AI)-based methods have shown promising performance in recent years, questions have arisen within the industry regarding the necessity of AI algorithms, especially when rule-based methods have also demonstrated strong results in previous studies. This study aims to identify a highly generalizable solution for industrial applications, especially for resource-constrained devices that operate with low sampling rates and limited computational power. Through a comparative analysis of AI-based and rule-based approaches, supported by a comprehensive review of the literature and experimental validation, this research provides statistical evidence highlighting the strengths and weaknesses of both methods. It is demonstrated that AI-based methods are more adaptable to varying conditions, and that integrating pre-feature extraction with domain knowledge can enhance general performance, particularly in such physical problems with considerable prior research.

关键词： Circuit faults Time-frequency analysis Artificial intelligence Feature extraction Reliability Data models Analytical models Accuracy Solid modeling signal processing algorithms DC series arc fault AI-based signal processing deep learning dc power grid safety

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：