检索结果-内蒙古大学图书馆

Swarm Sparse Range Profile Recovery From Fewer Measurements of FMCW Radar

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2024年第5期60卷 7056-7074页

作者： Wang, Longhui Ai, Zhanyang Wang, Qiexiang Wang, Jian Zhang, Xudong Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Dept Space Microwave Remote Sensing Syst Beijing 100190 Peoples R China

In this article, we propose an algorithm for recovering swarm sparse range profiles from fewer measurements of frequency-modulated continuous-wave (FMCW) radar. First, we give the FMCW radar signal model and show the drawbacks of existing algorithms for the swarm sparse range profile recovery. Next, we propose an algorithm, called swarm orthogonal matching pursuit (sOMP), which recovers swarm sparse signals by exploiting the cluster feature of swarm targets in radar scenes. The highlights of sOMP lie in the two element index selection modes and the likelihood-ratio-based mode selection strategy. The probability distributions involved in the likelihood ratio are derived from the Gaussian approximation of the sensing matrix taken from the complex uniform spherical ensemble or the complex Gaussian ensemble. For the application of sOMP in FMCW radar, we propose two schemes to address the issue of Gaussian approximation of the sensing matrix taken from the Fourier ensemble. Then, the performance of sOMP is analyzed theoretically. In particular, under equivalent parameter settings, the sufficient conditions derived for sOMP can also be regarded as those for generalized orthogonal matching pursuit (gOMP). Compared with latest sufficient conditions for gOMP, our results are looser in terms of the constraint of the minimum magnitude of nonzero elements. Numerical simulations confirm that sOMP in both schemes outperforms the state-of-the-art recovery algorithms. Moreover, real FMCW radar experiments with drone swarms also demonstrate the superior performance of sOMP.

关键词： Radar Matching pursuit algorithms Drones signal processing algorithms Radar signal processing Radar measurements Airborne radar Drone swarm frequency-modulated continuous-wave (FMCW) radar orthogonal matching pursuit (OMP) range profile swarm sparse recovery

来源：评论

学校读者我要写书评

暂无评论

Sparsity and Periodicity-Induced Symplectic Geometry Decomposition for Incipient Fault Diagnosis of Wind Turbine Gearbox

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Zhang, Bo Teng, Wei Bai, Honghua Huang, Weiling Peng, Dikang Liu, Yibing North China Elect Power Univ Minist Educ Key Lab Power Stn Energy Transfer Convers & Syst Beijing 102206 Peoples R China Zhejiang Zhenxing Axiang Grp Co Ltd Huzhou 313008 Zhejiang Peoples R China

When incipient faults of gears or bearings occur in the wind turbine gearbox, their fault information will be readily masked by intensive background noise, which may postpone the fault detection and maintenance schedule. Specifically, the phenomenon manifested in the time domain is that the fault impulse is not obvious, while in the frequency domain, it is manifested that the fault frequency is prone to submerge in other interference frequency components. However, conventional signal processing methods and matrix factorization algorithms make it difficult to intuitively characterize fault features. Complex algorithms often require some manually adjusted parameters, which is difficult to be applied in engineering practice. To balance the performance and complexity of algorithms, a sparsity and periodicity-induced symplectic geometry decomposition (SPSGD) method is proposed. The initial components are obtained by the symplectic geometry mode decomposition method. Stem from the periodicity of gear faults in the time domain and the sparsity in the frequency domain, a periodicity-induced Bayesian clustering method is proposed as a novel iteration termination condition to pursue the fault-related components in the time domain. Then, a sparsity and periodicity-induced inverse filter is designed by the Laplace operator to weigh the faulty components to reduce the noise influence. The proposed SPSGD is validated by three cases, which indicate that the noise can be reduced adaptively as well as enhance the useful fault components effectively.

关键词： Noise reduction Noise Geometry Feature extraction Time-domain analysis signal processing algorithms Gears Vectors Bayes methods Wind turbines Fault diagnosis noise reduction sparsity and periodicity wind turbine

来源：评论

学校读者我要写书评

暂无评论

The WQN Algorithm for EEG Artifact Removal in the Absence of Scale Invariance

引用

IEEE TRANSACTIONS ON signal processing 2024年 72卷 2663-2676页

作者： Dora, Matteo Jaffard, Stephane Holcman, David Ecole Normale Super IBENS UMR8197 PSL F-75005 Paris France Univ Paris Est Creteil Univ Gustave Eiffel CNRS LAMA UMR8050 F-94010 Creteil France

Electroencephalogram (EEG) signals reflect brain activity across different brain states, characterized by distinct frequency distributions. Through multifractal analysis tools, we investigate the scaling behaviour of several classes of EEG signals and artifacts. We show that brain states associated to sleep and general anaesthesia are not in general characterized by scale invariance. The lack of scale invariance motivates the development of artifact removal algorithms capable of operating independently at each scale. We examine here the properties of the wavelet quantile normalization (WQN) algorithm, a recently introduced adaptive method for real-time correction of transient artifacts in EEG signals. We establish general results regarding the regularization properties of the WQN algorithm, showing how it can eliminate singularities introduced by artefacts, and we compare it to traditional thresholding algorithms. Furthermore, we provide evidence that the algorithm performance is independent of the wavelet basis. We finally examine its continuity and boundedness properties and illustrate its distinctive non-local action on the wavelet coefficients through pathological examples.

关键词： Art Electroencephalography Time-frequency analysis signal processing algorithms Transient analysis Transforms Task analysis Artifact replacement EEG real-time algorithm regularity property transport wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Quickest Change Detection in (Hidden) Markov Models

引用

IEEE TRANSACTIONS ON signal processing 2024年 72卷 5567-5580页

作者： Zhang, Qi Sun, Zhongchang Herrera, Luis C. Zou, Shaofeng Arizona State Univ Sch Elect Comp & Energy Engn Tempe AZ 85281 USA Univ Buffalo Dept Elect Engn Buffalo NY 14228 USA

The paper investigates the problems of quickest change detection in Markov models and hidden Markov models (HMMs). Sequential observations are taken from a (hidden) Markov model. At some unknown time, an event occurs in the system and changes the transition kernel of the Markov model and/or the emission probability of the HMM. The objective is to detect the change quickly while controlling the average running length (ARL) to false alarm. The data-driven setting is studied, where no knowledge of the pre- or post-change distributions is available. Kernel-based data-driven algorithms are developed, which can be applied in the setting with continuous state, can be updated in a recursive fashion, and are computationally efficient. Lower bounds on the ARL and upper bounds on the worst-case average detection delay (WADD) are derived. The WADD is at most of the order of the logarithm of the ARL. The algorithms are further numerically validated on two practical problems of fault detection in DC microgrid and photovoltaic systems.

关键词： Hidden Markov models Kernel signal processing algorithms Fault detection Photovoltaic systems Microgrids Computational modeling Sun Numerical models Electrical fault detection Maximum mean discrepancy kernel method fault detection non-iid

来源：评论

学校读者我要写书评

暂无评论

Marginalized Beam Search algorithms for Hierarchical HMMs

引用

IEEE TRANSACTIONS ON signal processing 2024年 72卷 3013-3027页

作者： Xu, Xuechun Jalden, Joakim Royal Inst Technol Div Informat Sci & Engn KTH SE-10044 Stockholm Sweden

Inferring a state sequence from a sequence of measurements is a fundamental problem in bioinformatics and natural language processing. The Viterbi and the Beam Search (BS) algorithms are popular inference methods, but they have limitations when applied to Hierarchical Hidden Markov Models (HHMMs), when the primary interest lies in the outer state sequence. The Viterbi algorithm can not infer outer states without inner states, while the BS algorithm requires marginalization over prohibitively large state spaces. We propose two new algorithms to overcome these limitations: the greedy marginalized BS algorithm and the local focus BS algorithm. We show that they approximate the most likely outer state sequence with higher performance than the Viterbi algorithm, and we evaluate the performance of these algorithms on an explicit duration HMM with simulated and real nanopore base calling data.

关键词： signal processing algorithms Decoding Hidden Markov models Viterbi algorithm Search problems RNA Complexity theory hidden Markov models Viterbi beam search

来源：评论

学校读者我要写书评

暂无评论

Adaptive-Wavelet-Threshold-Function-Based M2M Gaussian Noise Removal Method

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第20期11卷 33177-33192页

作者： Li, Shuang Liu, Shuai Wang, Jingjing Yan, Shefeng Liu, Jiahao Du, Zehua Qingdao Univ Sci & Technol Sch Informat Sci & Technol Qingdao 266061 Peoples R China Univ Chinese Acad Sci Inst Acoust Beijing 100190 Peoples R China Ocean Univ China Fac Informat Sci & Engn Qingdao 266100 Shandong Peoples R China Ocean Univ China Fac Informat Sci & Engn Qingdao Peoples R China

With little or no human intervention, almost every object in Internet of Things (IoT) has ability to communicate, sense, and process information to make everything connected. Noise in complex environment has a great impact on machine-to-machine (M2M) interaction in IoT. Adaptive wavelet threshold function (AWTF)-based M2M Gaussian Noise Removal Method is proposed in this article. First, a bilateral enhanced wavelet threshold function is derived based on the adjustable zeroing window. Further, threshold is used to construct a bilateral enhanced wavelet threshold function, which can eliminate the oscillations in the existing wavelet threshold function. This ensures that there is no break in wavelet coefficients during the reconstruction process and that stable wavelet decomposition and reconstruction can be achieved. The signal-to-noise ratio (SNR) of a signal is estimated based on the variance of the noise-containing signal, and the zeroing window parameters are adjusted adaptively according to the SNR value to eliminate the noisy wavelet coefficients and improve the denoising performance. In addition, when the wavelet coefficients are reconstructed, the proposed algorithm can select a suitable threshold function according to a particular threshold value, which improves the robustness of the algorithm. "Doppler" and "Bumps" standard test signals are used as interactive signals to simulate the proposed algorithms. For "Doppler" signals, the SNR, root mean square error (RMSE), and noise suppression ratio (NSR) of AWTF increased by 8.48%, 42.59%, and 1.69%, respectively, compared with the GDES+ABC algorithm. For "Bumps" signal, the SNR, RMSE, and NSR of AWTF are improved by 11.67%, 24.46%, and 2.99%, respectively, compared with GDES+ABC algorithm. In addition, we also use different modulated signals to carry out real field experiments in Qingdao cruise ship home port, which proves the effectiveness of the proposed algorithm.

关键词： Noise reduction signal processing algorithms Internet of Things Gaussian noise Wavelet transforms signal to noise ratio Wavelet domain Adaptive algorithm machine-to-machine interaction threshold function wavelet transform (WT)

来源：评论

学校读者我要写书评

暂无评论

algorithms for Non-Negative Matrix Factorization on Noisy Data With Negative Values

引用

IEEE TRANSACTIONS ON signal processing 2024年 72卷 5187-5197页

作者： Green, Dylan Bailey, Stephen Univ Calif Irvine Dept Phys & Astron Irvine CA 92697 USA Lawrence Berkeley Natl Lab Berkeley CA 94720 USA

Non-negative matrix factorization (NMF) is a dimensionality reduction technique that has shown promise for analyzing noisy data, especially astronomical data. For these datasets, the observed data may contain negative values due to noise even when the true underlying physical signal is strictly positive. Prior NMF work has not treated negative data in a statistically consistent manner, which becomes problematic for low signal-to-noise data with many negative values. In this paper we present two algorithms, Shift-NMF and Nearly-NMF, that can handle both the noisiness of the input data and also any introduced negativity. Both of these algorithms use the negative data space without clipping or masking and recover non-negative signals without any introduced positive offset that occurs when clipping or masking negative data. We demonstrate this numerically on both simple and more realistic examples, and prove that both algorithms have monotonically decreasing update rules.

关键词： Noise Noise measurement signal processing algorithms Solids Vectors Standards Fluctuations Fitting Contracts Codes Non-negative matrix factorization (NMF) dimension reduction noisy data weighted NMF negative data

来源：评论

学校读者我要写书评

暂无评论

Sparse Training for Federated Learning With Regularized Error Correction

引用

IEEE JOURNAL OF SELECTED TOPICS IN signal processing 2024年第6期18卷 1085-1099页

作者： Greidi, Ran Cohen, Kobi Bengur Univ Negev Sch Elect & Comp Engn IL-8410501 Beer Sheva Israel

Federated Learning (FL) is an emerging paradigm that allows for decentralized machine learning (ML), where multiple models are collaboratively trained in a privacy-preserving manner. However, training DNN models in FL systems face challenges such as elevated computational and communication costs in complex tasks. Sparse training schemes gain increasing attention in order to scale down the dimensionality of each client transmission. Specifically, sparsification with error correction methods is a promising technique, where only important updates are sent to the parameter server (PS) and the rest are accumulated locally. While error correction methods have shown to achieve a significant sparsification level without harming convergence, pushing sparsity further remains unresolved due to the staleness effect. In this paper, we propose a novel algorithm, dubbed Federated Learning with Accumulated Regularized Embeddings (FLARE), to overcome this challenge. FLARE presents a novel sparse training approach via accumulated pulling of the updated models with regularization on the embeddings in the FL process, providing a powerful solution to the staleness effect, and pushing sparsity to an exceptional level. Our theoretical analysis demonstrates that FLARE not only matches state-of-the-art performance in terms of convergence rate with time, but also achieves significant improvements in scalability with sparsity parameter. The empirical performance of FLARE is validated through extensive experiments on diverse and complex models, achieving a remarkable sparsity level (10 times and more beyond the current state-of-the-art) along with significantly improved accuracy. Additionally, an open-source software package has been developed for the benefit of researchers and developers in related fields.

关键词： Optimization Training Computational modeling Data models Error correction Convergence signal processing algorithms Deep learning deep neural network (DNN) communication-efficiency federated learning (FL) sparse training

来源：评论

学校读者我要写书评

暂无评论

Main-Lobe Beamwidth Constrained Target Localization Using Bistatic Range Measurements

引用

IEEE TRANSACTIONS ON signal processing 2024年 72卷 289-304页

作者： Mao, Zhi Su, Hongtao Shen, Lu Jing, Xinchen Jia, Congyue Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China

This paper addresses the localization of a target in 3D scenarios using bistatic range measurements with a single passive receiver and multiple transmitters. The main-lobe beamwidth of the receiving antenna contains valuable a-priori information about the target position but is commonly overlooked. This study introduces an angular constraint to incorporate the beamwidth information into the elliptic localization, resulting in a Quadratically Constrained Quadratic Programming (QCQP) problem. A novel Two-Stage Main-lobe beamwidth Constrained Estimation (TSMCE) algorithm is proposed to solve this challenging localization problem. Theoretical analysis demonstrates that the algorithm can converge to the candidate solutions that satisfy the Karush-Kuhn-Tucker (KKT) optimality conditions. The corresponding covariance can achieve the Cramer-Rao Lower Bound (CRLB) under a small noise assumption. Numerical simulations confirm that the proposed algorithm achieves superior localization accuracy compared to other methods, particularly in the low signal to Noise Ratio (SNR) regime. Additionally, the algorithm demonstrates fast convergence and robustness to variations in localization geometry.

关键词： Location awareness signal processing algorithms Antenna measurements Receiving antennas Mathematical models Three-dimensional displays signal to noise ratio Passive localization bistatic range main-lobe beamwidth angular constraint two-stage algorithm

来源：评论

学校读者我要写书评

暂无评论

Iterative Closest Point via MultiKernel Correntropy for Point Cloud Fine Registration

引用

IEEE signal processing LETTERS 2025年 32卷 766-770页

作者： Yi, Hao Hu, Limei Chen, Feng Ren, Xiaoping Duan, Shukai Southwest Univ Coll Artificial Intelligence Chongqing 400715 Peoples R China

The Iterative Closest Point (ICP) method, primarily used for transformation estimation, is a crucial technique in 3D signal processing, especially for point cloud fine registration. However, traditional ICP is prone to local optima and sensitive to noise, especially when there is no good initialization. Based on the observation that registration errors typically exhibit a multimodal distribution under large rotational offsets and noisy environments, the MultiKernel Correntropy (MKC), which can estimate the registration error distribution, is introduced to provide global information for ICP. Moreover, since MKC consists of multiple Gaussian kernels, it can effectively resist most of the noise. A MultiKernel Correntropy based Iterative Closest Point (MKCICP) is proposed. Extensive experiments on both simulated and real-world datasets show that MKCICP achieves better performance compared to other related methods in challenging scenarios involving large rotational angles, low partial overlap, and high noise levels.

关键词： Point cloud compression Noise Iterative methods Optimization Kernel Vectors signal processing algorithms Mathematical models Loss measurement Linear programming MultiKernel Correntropy (MKC) Iterative Closest Point (ICP) transformation estimation signal processing global optimum point cloud registration

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：