Signal Processing最新文献_第9页

Fast and efficient implementation of the maximum likelihood estimation for the linear regression with Gaussian model uncertainty 具有高斯模型不确定性的线性回归的最大似然估计的快速有效实现

IF 3.6 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Signal Processing

Pub Date : 2025-11-12 DOI: 10.1016/j.sigpro.2025.110403

Ruohai Guo , Jiang Zhu , Xing Jiang , Fengzhong Qu

The linear regression model with a random variable (RV) measurement matrix, where the mean of the random measurement matrix has full column rank, has been extensively studied. In particular, the quasiconvexity of the maximum likelihood estimation (MLE) problem was established, and the corresponding Cramér–Rao bound (CRB) was derived, leading to the development of an efficient bisection-based algorithm known as RV-ML. In contrast, this work extends the analysis to both overdetermined and underdetermined cases, allowing the mean of the random measurement matrix to be rank-deficient. A remarkable contribution is the proof that the equivalent MLE problem is convex and satisfies strong duality, strengthening previous quasiconvexity results. Moreover, it is shown that in underdetermined scenarios, the randomness in the measurement matrix can be beneficial for estimation under certain conditions. In addition, a fast and unified implementation of the MLE solution, referred to as generalized RV-ML (GRV-ML), is proposed, which handles a more general case including both underdetermined and overdetermined systems. Extensive numerical simulations are provided to validate the theoretical findings.

随机测量矩阵均值为全列秩的随机变量测量矩阵线性回归模型得到了广泛的研究。特别地，建立了极大似然估计（MLE）问题的拟自凸性，并推导了相应的cram - rao界（CRB），从而发展了一种高效的基于二分法的RV-ML算法。相反，这项工作将分析扩展到过确定和欠确定的情况，允许随机测量矩阵的平均值是秩不足的。一个值得注意的贡献是证明了等效MLE问题是凸的并且满足强对偶性，加强了以前的拟凸性结果。此外，在欠确定的情况下，测量矩阵的随机性在一定条件下有利于估计。此外，还提出了一种快速统一的MLE解决方案，称为广义RV-ML (GRV-ML)，它可以处理更一般的情况，包括欠定和过定系统。提供了大量的数值模拟来验证理论结果。

{"title":"Fast and efficient implementation of the maximum likelihood estimation for the linear regression with Gaussian model uncertainty","authors":"Ruohai Guo , Jiang Zhu , Xing Jiang , Fengzhong Qu","doi":"10.1016/j.sigpro.2025.110403","DOIUrl":"10.1016/j.sigpro.2025.110403","url":null,"abstract":"<div><div>The linear regression model with a random variable (RV) measurement matrix, where the mean of the random measurement matrix has full column rank, has been extensively studied. In particular, the quasiconvexity of the maximum likelihood estimation (MLE) problem was established, and the corresponding Cramér–Rao bound (CRB) was derived, leading to the development of an efficient bisection-based algorithm known as RV-ML. In contrast, this work extends the analysis to both overdetermined and underdetermined cases, allowing the mean of the random measurement matrix to be rank-deficient. A remarkable contribution is the proof that the equivalent MLE problem is convex and satisfies strong duality, strengthening previous quasiconvexity results. Moreover, it is shown that in underdetermined scenarios, the randomness in the measurement matrix can be beneficial for estimation under certain conditions. In addition, a fast and unified implementation of the MLE solution, referred to as generalized RV-ML (GRV-ML), is proposed, which handles a more general case including both underdetermined and overdetermined systems. Extensive numerical simulations are provided to validate the theoretical findings.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"241 ","pages":"Article 110403"},"PeriodicalIF":3.6,"publicationDate":"2025-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A non-contact material recognition method using ultrasonic echo signals and deep learning 基于超声回波信号和深度学习的非接触式材料识别方法

IF 3.6 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Signal Processing

Pub Date : 2025-11-12 DOI: 10.1016/j.sigpro.2025.110408

Bo Zhu , Haoxuan Li , Tao Geng , Wenqiang Duan , Boxin Ren

Accurate wall material recognition is essential for robotic operations in extreme environments such as mining tunnels, disaster sites, and search-and-rescue missions, where conventional sensors like cameras and LiDAR often fail due to darkness, dust, smoke, or obstructions. Ultrasonic sensing offers a robust alternative, but its echo signals exhibit complex spatial–temporal patterns that are difficult to model with traditional methods. This study proposes AE-CS-TCN (Attention-Enhanced Cross-Scale Temporal Convolutional Network), a deep learning architecture for non-contact wall material recognition using raw ultrasonic echoes. The model integrates spatial attention, dilated temporal convolutions, cross-scale fusion, and cross-attention to effectively capture and align multi-resolution features. Experiments on both the public LMT dataset and a self-built dataset show that AE-CS-TCN achieves 96% average accuracy, outperforming conventional and deep learning baselines while maintaining strong robustness to noise and distance variations.

准确的墙体材料识别对于机器人在采矿隧道、灾难现场和搜救任务等极端环境中的操作至关重要，在这些环境中，传统传感器（如摄像头和激光雷达）经常因黑暗、灰尘、烟雾或障碍物而失效。超声传感提供了一个强大的替代方案，但其回波信号表现出复杂的时空模式，难以用传统方法建模。本研究提出了AE-CS-TCN（注意增强跨尺度时间卷积网络），这是一种利用原始超声回波进行非接触式墙体材料识别的深度学习架构。该模型集成了空间注意、扩展时间卷积、跨尺度融合和交叉注意，有效地捕获和对齐多分辨率特征。在公共LMT数据集和自建数据集上的实验表明，AE-CS-TCN平均准确率达到96%，优于传统和深度学习基线，同时对噪声和距离变化保持较强的鲁棒性。

引用次数: 0

Semi-supervised non-negative matrix factorization with weighted label propagation for data representation 基于加权标签传播的半监督非负矩阵分解

IF 3.6 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Signal Processing

Pub Date : 2025-11-11 DOI: 10.1016/j.sigpro.2025.110407

Wenjing Jing , Linzhang Lu , Weihua Ou

Label propagation has been widely used to enhance performance for clustering. Many semi-supervised non-negative matrix factorization (NMF) methods based on label propagation have been proposed. However, these methods mainly pay attention to learning a label prediction matrix, neglecting the efficient learning of a low-dimensional representation of original data. Additionally, they lead to inconsistent structures with NMF when leveraging label constraints, compromising the learning performance for low-dimensional representation and basis matrix. To address these problems, this paper proposes a novel semi-supervised NMF method named semi-supervised non-negative matrix factorization with weighted label propagation (SNMFWLP). Firstly, SNMFWLP considers an orthogonal constraint on basis matrix to minimize the redundancy in the process of decomposition in NMF. Secondly, SNMFWLP introduces a weighted label propagation model into NMF to learn an efficient low-dimensional representation used as label prediction matrix. The weighted label propagation model not only propagates label information but also maintains the structures consistent with structures of NMF, beneficial to a consistent low-dimensional representation. Additionally, effective algorithm and convergence analysis are also presented. Finally, numerous experiments on real-world data sets are conducted to demonstrate the superiority of the proposed method in comparison to several state-of-the-art unsupervised and semi-supervised NMF methods.

标签传播被广泛用于提高聚类的性能。人们提出了许多基于标签传播的半监督非负矩阵分解（NMF）方法。然而，这些方法主要关注标签预测矩阵的学习，忽略了对原始数据低维表示的有效学习。此外，当利用标签约束时，它们会导致与NMF结构不一致，从而影响低维表示和基矩阵的学习性能。针对这些问题，本文提出了一种新的半监督非负矩阵分解加权标签传播方法（SNMFWLP）。首先，SNMFWLP考虑基矩阵的正交约束，以最小化NMF分解过程中的冗余。其次，SNMFWLP在NMF中引入加权标签传播模型，学习高效的低维表示作为标签预测矩阵。加权标签传播模型不仅传播标签信息，而且保持了与NMF结构一致的结构，有利于一致的低维表示。并给出了有效的算法和收敛性分析。最后，在真实世界的数据集上进行了大量实验，以证明与几种最先进的无监督和半监督NMF方法相比，所提出的方法具有优越性。

{"title":"Semi-supervised non-negative matrix factorization with weighted label propagation for data representation","authors":"Wenjing Jing , Linzhang Lu , Weihua Ou","doi":"10.1016/j.sigpro.2025.110407","DOIUrl":"10.1016/j.sigpro.2025.110407","url":null,"abstract":"<div><div>Label propagation has been widely used to enhance performance for clustering. Many semi-supervised non-negative matrix factorization (NMF) methods based on label propagation have been proposed. However, these methods mainly pay attention to learning a label prediction matrix, neglecting the efficient learning of a low-dimensional representation of original data. Additionally, they lead to inconsistent structures with NMF when leveraging label constraints, compromising the learning performance for low-dimensional representation and basis matrix. To address these problems, this paper proposes a novel semi-supervised NMF method named semi-supervised non-negative matrix factorization with weighted label propagation (SNMFWLP). Firstly, SNMFWLP considers an orthogonal constraint on basis matrix to minimize the redundancy in the process of decomposition in NMF. Secondly, SNMFWLP introduces a weighted label propagation model into NMF to learn an efficient low-dimensional representation used as label prediction matrix. The weighted label propagation model not only propagates label information but also maintains the structures consistent with structures of NMF, beneficial to a consistent low-dimensional representation. Additionally, effective algorithm and convergence analysis are also presented. Finally, numerous experiments on real-world data sets are conducted to demonstrate the superiority of the proposed method in comparison to several state-of-the-art unsupervised and semi-supervised NMF methods.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"241 ","pages":"Article 110407"},"PeriodicalIF":3.6,"publicationDate":"2025-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145528906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fuzzy K-means clustering without cluster centroids 没有聚类质心的模糊k均值聚类

IF 3.6 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Signal Processing

Pub Date : 2025-11-11 DOI: 10.1016/j.sigpro.2025.110406

Yuxuan Liu, Yichen Bao, Han Lu, Quanxue Gao

Fuzzy K-Means is a classic clustering method that performs fuzzy partitioning of data by iteratively updating the cluster centers and the membership degrees of each data point. This makes it particularly suitable for handling data with unclear boundaries. However, the algorithm is highly sensitive to the choice of initial cluster centroids, which can affect the stability of the clustering results. To address this issue, we propose a robust fuzzy K-Means clustering algorithm(FKMVC) that eliminate the reliance on cluster centroids, obtaining membership metrices solely through distance matrix computation. Specifically, we reexpress fuzzy K-Means from the perspective of manifold, construct the manifold structure by labels, and then perform clustering update labels on the manifold structure, so that the labels can be obtained without centroid estimation, and the consistency of manifolds and labels is maintained. In addition, our proposed model supports various types of distance matrices to accommodate complex linearly inseparable data. The results from extensive experiments across multiple databases substantiate the superiority of our proposed model.

模糊K-Means是一种经典的聚类方法，它通过迭代更新聚类中心和每个数据点的隶属度来对数据进行模糊划分。这使得它特别适合处理边界不明确的数据。然而，该算法对初始聚类质心的选择高度敏感，影响聚类结果的稳定性。为了解决这个问题，我们提出了一种鲁棒模糊k -均值聚类算法（FKMVC），该算法消除了对聚类质心的依赖，仅通过距离矩阵计算获得隶属度度量。具体来说，我们从流形的角度重新表示模糊K-Means，通过标记构造流形结构，然后对流形结构进行聚类更新标记，使得在不需要质心估计的情况下获得标记，并且保持了流形与标签的一致性。此外，我们提出的模型支持各种类型的距离矩阵，以适应复杂的线性不可分割的数据。跨多个数据库的大量实验结果证实了我们提出的模型的优越性。

{"title":"Fuzzy K-means clustering without cluster centroids","authors":"Yuxuan Liu, Yichen Bao, Han Lu, Quanxue Gao","doi":"10.1016/j.sigpro.2025.110406","DOIUrl":"10.1016/j.sigpro.2025.110406","url":null,"abstract":"<div><div>Fuzzy <em>K</em>-Means is a classic clustering method that performs fuzzy partitioning of data by iteratively updating the cluster centers and the membership degrees of each data point. This makes it particularly suitable for handling data with unclear boundaries. However, the algorithm is highly sensitive to the choice of initial cluster centroids, which can affect the stability of the clustering results. To address this issue, we propose a robust fuzzy <em>K</em>-Means clustering algorithm(FKMVC) that eliminate the reliance on cluster centroids, obtaining membership metrices solely through distance matrix computation. Specifically, we reexpress fuzzy <em>K</em>-Means from the perspective of manifold, construct the manifold structure by labels, and then perform clustering update labels on the manifold structure, so that the labels can be obtained without centroid estimation, and the consistency of manifolds and labels is maintained. In addition, our proposed model supports various types of distance matrices to accommodate complex linearly inseparable data. The results from extensive experiments across multiple databases substantiate the superiority of our proposed model.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"241 ","pages":"Article 110406"},"PeriodicalIF":3.6,"publicationDate":"2025-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unbiased censored regression Euclidean direction search algorithm 无偏删节回归欧几里德方向搜索算法

IF 3.6 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Signal Processing

Pub Date : 2025-11-11 DOI: 10.1016/j.sigpro.2025.110405

Qiang Wang , Lu Lu , Tao Yu , Guangya Zhu

This paper proposes a novel adaptive filtering algorithm, termed the bias-compensated censored regression Euclidean direction search (BC-CR-EDS) algorithm, to address the joint challenges of censored outputs and noisy inputs in censored regression (CR) models. In the CR model, the output data outside the specified range are censored and not measured exactly. The traditional adaptive filtering algorithms may not work effectively in such a model. Furthermore, a CR model with noisy input can lead to a biased estimation of the algorithm. In this scenario, the bias-compensated Heckman (BC-Heckman) algorithm was developed, but its convergence rate and steady-state performance may deteriorate. To surmount this problem, a novel BC-CR-EDS algorithm is proposed. Benefiting from the numerical stability of the EDS algorithm and the unbiasedness principle criterion, the BC-CR-EDS algorithm can achieve improved steady-state performance and tracking performance. As an additional contribution, an online method to estimate the variance of the input data is developed for the BC-CR-EDS algorithm. In addition, the steady-state performance of mean and mean-square for the BC-CR-EDS algorithm is analyzed. Simulation results demonstrate that the BC-CR-EDS algorithm achieves approximately a 10 dB improvement in steady-state performance compared to the existing algorithms for system identification and acoustic echo cancellation.

本文提出了一种新的自适应滤波算法，称为偏差补偿的删节回归欧几里得方向搜索（BC-CR-EDS）算法，以解决删节回归（CR）模型中删节输出和噪声输入的共同挑战。在CR模型中，超出指定范围的输出数据被截除，不能精确测量。传统的自适应滤波算法在这种模型下可能无法有效地工作。此外，带有噪声输入的CR模型可能导致算法的偏估计。在这种情况下，开发了偏差补偿Heckman （BC-Heckman）算法，但其收敛速度和稳态性能可能会下降。为了克服这一问题，提出了一种新的BC-CR-EDS算法。得益于EDS算法的数值稳定性和无偏性准则，BC-CR-EDS算法可以获得更好的稳态性能和跟踪性能。作为一个额外的贡献，我们为BC-CR-EDS算法开发了一种在线估计输入数据方差的方法。此外，还分析了BC-CR-EDS算法的均值和均方稳态性能。仿真结果表明，BC-CR-EDS算法在系统识别和声回波消除方面的稳态性能比现有算法提高了约10 dB。

{"title":"Unbiased censored regression Euclidean direction search algorithm","authors":"Qiang Wang , Lu Lu , Tao Yu , Guangya Zhu","doi":"10.1016/j.sigpro.2025.110405","DOIUrl":"10.1016/j.sigpro.2025.110405","url":null,"abstract":"<div><div>This paper proposes a novel adaptive filtering algorithm, termed the bias-compensated censored regression Euclidean direction search (BC-CR-EDS) algorithm, to address the joint challenges of censored outputs and noisy inputs in censored regression (CR) models. In the CR model, the output data outside the specified range are censored and not measured exactly. The traditional adaptive filtering algorithms may not work effectively in such a model. Furthermore, a CR model with noisy input can lead to a biased estimation of the algorithm. In this scenario, the bias-compensated Heckman (BC-Heckman) algorithm was developed, but its convergence rate and steady-state performance may deteriorate. To surmount this problem, a novel BC-CR-EDS algorithm is proposed. Benefiting from the numerical stability of the EDS algorithm and the unbiasedness principle criterion, the BC-CR-EDS algorithm can achieve improved steady-state performance and tracking performance. As an additional contribution, an online method to estimate the variance of the input data is developed for the BC-CR-EDS algorithm. In addition, the steady-state performance of mean and mean-square for the BC-CR-EDS algorithm is analyzed. Simulation results demonstrate that the BC-CR-EDS algorithm achieves approximately a 10 dB improvement in steady-state performance compared to the existing algorithms for system identification and acoustic echo cancellation.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"241 ","pages":"Article 110405"},"PeriodicalIF":3.6,"publicationDate":"2025-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145528907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimized conversion-sample filter under maximum correntropy criterion 在最大熵准则下优化了转换样本滤波器

IF 3.6 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Signal Processing

Pub Date : 2025-11-11 DOI: 10.1016/j.sigpro.2025.110404

Shibo Jin , Lujuan Dang , Badong Chen

The linear minimum mean square error (LMMSE) framework is widely used for state estimation in dynamic systems owing to the robust performance of this approach under Gaussian assumptions. However, in nonlinear estimation problems, the performance of LMMSE is relatively inferior compared to other nonlinear algorithms. The optimized conversion-sample filter (OCF) was developed within the LMMSE framework. This filter obtains final estimates through optimized uncorrelated conversion (UC), while enhancing nonlinear system processing capabilities through integration of the deterministic sampling (DS) method and constrained Rayleigh quotient optimization techniques. Although OCF demonstrates improved performance in nonlinear systems, its effectiveness remains compromised under impulsive noise conditions. To overcome this issue, we propose an optimized conversion-sample filter based on the maximum correntropy criterion (MCOCF). MCOCF integrates the maximum correntropy criterion (MCC), thereby enhancing DS and the constrained Rayleigh quotient to a certain extent. Simulation results indicate that the MCOCF not only improves performance in environments with impulse noise but also significantly enhances the ability to process nonlinear systems.

线性最小均方误差（LMMSE）框架由于其在高斯假设下的鲁棒性而被广泛应用于动态系统的状态估计。然而，在非线性估计问题中，LMMSE的性能与其他非线性算法相比相对较差。在LMMSE框架下开发了优化的转换样本滤波器（OCF）。该滤波器通过优化的不相关转换（UC）获得最终估计，同时通过集成确定性采样（DS）方法和约束瑞利商优化技术增强非线性系统处理能力。尽管OCF在非线性系统中表现出了较好的性能，但在脉冲噪声条件下，OCF的有效性仍然受到损害。为了克服这个问题，我们提出了一种基于最大熵准则（MCOCF）的优化转换样本滤波器。mccof集成了最大熵准则（MCC），从而在一定程度上增强了DS和约束瑞利商。仿真结果表明，该方法不仅提高了系统在脉冲噪声环境下的性能，而且显著提高了处理非线性系统的能力。

{"title":"Optimized conversion-sample filter under maximum correntropy criterion","authors":"Shibo Jin , Lujuan Dang , Badong Chen","doi":"10.1016/j.sigpro.2025.110404","DOIUrl":"10.1016/j.sigpro.2025.110404","url":null,"abstract":"<div><div>The linear minimum mean square error (LMMSE) framework is widely used for state estimation in dynamic systems owing to the robust performance of this approach under Gaussian assumptions. However, in nonlinear estimation problems, the performance of LMMSE is relatively inferior compared to other nonlinear algorithms. The optimized conversion-sample filter (OCF) was developed within the LMMSE framework. This filter obtains final estimates through optimized uncorrelated conversion (UC), while enhancing nonlinear system processing capabilities through integration of the deterministic sampling (DS) method and constrained Rayleigh quotient optimization techniques. Although OCF demonstrates improved performance in nonlinear systems, its effectiveness remains compromised under impulsive noise conditions. To overcome this issue, we propose an optimized conversion-sample filter based on the maximum correntropy criterion (MCOCF). MCOCF integrates the maximum correntropy criterion (MCC), thereby enhancing DS and the constrained Rayleigh quotient to a certain extent. Simulation results indicate that the MCOCF not only improves performance in environments with impulse noise but also significantly enhances the ability to process nonlinear systems.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"241 ","pages":"Article 110404"},"PeriodicalIF":3.6,"publicationDate":"2025-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust PCA with adaptive weighting for sparse outlier suppression 基于自适应加权的鲁棒PCA稀疏离群值抑制

IF 3.6 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Signal Processing

Pub Date : 2025-11-10 DOI: 10.1016/j.sigpro.2025.110392

Kexin Li , You-wei Wen , Xu Xiao , Mingchao Zhao

Robust Principal Component Analysis (RPCA) is a powerful framework for separating low-rank and sparse structures in data, with widespread applications in image processing, video surveillance, and anomaly detection. Classical RPCA models typically employ

ℓ_{1}

-norm regularization to promote sparsity; however, such convex relaxations often introduce estimation bias and perform poorly in the presence of strong noise or large outliers. While non-convex penalties can alleviate these issues, they are often computationally expensive and sensitive to initialization. In this paper, we propose a novel RPCA framework that incorporates Adaptive Weighted Least Squares (AWLS) and Low-Rank Matrix Factorization (LRMF) to address these limitations. A key innovation of our method lies in its dynamic weight updating strategy, which enables the weight matrix to automatically adapt during each iteration, thereby suppressing outliers more effectively. The sparse component is regularized using a weighted Frobenius norm, which reduces bias and simplifies the optimization process through closed-form updates. An alternating minimization algorithm is adopted to solve the model efficiently. Extensive numerical experiments demonstrate that the proposed method achieves superior robustness and accuracy compared to state-of-the-art non-convex RPCA methods, while maintaining low computational complexity.

鲁棒主成分分析（Robust Principal Component Analysis， RPCA）是一种用于分离数据中低秩和稀疏结构的强大框架，在图像处理、视频监控和异常检测等领域有着广泛的应用。经典RPCA模型通常采用1-范数正则化来提高稀疏性；然而，这种凸松弛通常会引入估计偏差，并且在存在强噪声或大异常值时表现不佳。虽然非凸惩罚可以缓解这些问题，但它们通常在计算上很昂贵，并且对初始化很敏感。在本文中，我们提出了一个新的RPCA框架，该框架结合了自适应加权最小二乘（AWLS）和低秩矩阵分解（LRMF）来解决这些限制。该方法的一个关键创新在于其动态权值更新策略，该策略使权值矩阵在每次迭代过程中自动适应，从而更有效地抑制异常值。稀疏分量使用加权Frobenius范数进行正则化，减少了偏差，并通过封闭形式的更新简化了优化过程。采用交替最小化算法对模型进行高效求解。大量的数值实验表明，与最先进的非凸RPCA方法相比，该方法具有更好的鲁棒性和准确性，同时保持较低的计算复杂度。

{"title":"Robust PCA with adaptive weighting for sparse outlier suppression","authors":"Kexin Li , You-wei Wen , Xu Xiao , Mingchao Zhao","doi":"10.1016/j.sigpro.2025.110392","DOIUrl":"10.1016/j.sigpro.2025.110392","url":null,"abstract":"<div><div>Robust Principal Component Analysis (RPCA) is a powerful framework for separating low-rank and sparse structures in data, with widespread applications in image processing, video surveillance, and anomaly detection. Classical RPCA models typically employ <span><math><msub><mrow><mi>ℓ</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span>-norm regularization to promote sparsity; however, such convex relaxations often introduce estimation bias and perform poorly in the presence of strong noise or large outliers. While non-convex penalties can alleviate these issues, they are often computationally expensive and sensitive to initialization. In this paper, we propose a novel RPCA framework that incorporates Adaptive Weighted Least Squares (AWLS) and Low-Rank Matrix Factorization (LRMF) to address these limitations. A key innovation of our method lies in its dynamic weight updating strategy, which enables the weight matrix to automatically adapt during each iteration, thereby suppressing outliers more effectively. The sparse component is regularized using a weighted Frobenius norm, which reduces bias and simplifies the optimization process through closed-form updates. An alternating minimization algorithm is adopted to solve the model efficiently. Extensive numerical experiments demonstrate that the proposed method achieves superior robustness and accuracy compared to state-of-the-art non-convex RPCA methods, while maintaining low computational complexity.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"241 ","pages":"Article 110392"},"PeriodicalIF":3.6,"publicationDate":"2025-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145528905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Tap-Decomposed robust distributed linear-in-the-parameters nonlinear recursive adaptive graph filters tap - decomposition鲁棒分布参数线性非线性递归自适应图滤波器

IF 3.6 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Signal Processing

Pub Date : 2025-11-08 DOI: 10.1016/j.sigpro.2025.110401

Peng Cai , Dongyuan Lin , Yunfei Zheng , Shanli Chen , Cong Wu , Shiyuan Wang

To address the nonlinear prediction problem in distributed graph signal processing, the distributed nonlinear adaptive graph filter (DNAGF) has been developed. However, DNAGF is based on the minimum mean square error criterion and assumes a strict Gaussian distribution, which leads to significant performance degradation in the presence of non-Gaussian noise. To this end, a novel family of robust distributed nonlinear recursive adaptive graph filters (R-DNRAGFs) is proposed based on the linear-in-the-parameters model that incorporates five nonlinear expansions. The proposed R-DNRAGF family can effectively handle various types of noise by modeling the disturbed noise with a Gaussian mixture model. This modeling enhances its robustness, especially its adaptability to different noise distributions. Furthermore, to address the heavy computational burden of R-DNRAGF in resource-constrained distributed networks, we propose a robust nearest Kronecker product distributed nonlinear recursive adaptive graph filter (R-NKP-DNRAGF) family. By employing the nearest Kronecker product decomposition method, the long weight vector is divided into two shorter vectors that can be updated simultaneously, enhancing both efficiency and flexibility. Finally, simulation results from four examples demonstrate the robust performance of the proposed R-DNRAGF and R-NKP-DNRAGF families.

为了解决分布式图信号处理中的非线性预测问题，提出了分布式非线性自适应图滤波器（DNAGF）。然而，DNAGF基于最小均方误差准则，并假设严格的高斯分布，这导致在存在非高斯噪声时性能显著下降。为此，提出了一种基于参数中线性模型的鲁棒分布非线性递归自适应图滤波器（r- dnragf）。所提出的R-DNRAGF家族通过高斯混合模型对干扰噪声进行建模，可以有效地处理各种类型的噪声。该模型增强了其鲁棒性，特别是对不同噪声分布的适应性。此外，为了解决R-DNRAGF在资源受限的分布式网络中计算量大的问题，我们提出了一种鲁棒的最近邻Kronecker积分布非线性递归自适应图滤波器（R-NKP-DNRAGF）族。采用最近邻Kronecker积分解方法，将较长的权向量分解为两个较短的可以同时更新的向量，提高了效率和灵活性。最后，通过四个实例的仿真结果验证了所提出的R-DNRAGF和R-NKP-DNRAGF家族的鲁棒性。

{"title":"Tap-Decomposed robust distributed linear-in-the-parameters nonlinear recursive adaptive graph filters","authors":"Peng Cai , Dongyuan Lin , Yunfei Zheng , Shanli Chen , Cong Wu , Shiyuan Wang","doi":"10.1016/j.sigpro.2025.110401","DOIUrl":"10.1016/j.sigpro.2025.110401","url":null,"abstract":"<div><div>To address the nonlinear prediction problem in distributed graph signal processing, the distributed nonlinear adaptive graph filter (DNAGF) has been developed. However, DNAGF is based on the minimum mean square error criterion and assumes a strict Gaussian distribution, which leads to significant performance degradation in the presence of non-Gaussian noise. To this end, a novel family of robust distributed nonlinear recursive adaptive graph filters (R-DNRAGFs) is proposed based on the linear-in-the-parameters model that incorporates five nonlinear expansions. The proposed R-DNRAGF family can effectively handle various types of noise by modeling the disturbed noise with a Gaussian mixture model. This modeling enhances its robustness, especially its adaptability to different noise distributions. Furthermore, to address the heavy computational burden of R-DNRAGF in resource-constrained distributed networks, we propose a robust nearest Kronecker product distributed nonlinear recursive adaptive graph filter (R-NKP-DNRAGF) family. By employing the nearest Kronecker product decomposition method, the long weight vector is divided into two shorter vectors that can be updated simultaneously, enhancing both efficiency and flexibility. Finally, simulation results from four examples demonstrate the robust performance of the proposed R-DNRAGF and R-NKP-DNRAGF families.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"241 ","pages":"Article 110401"},"PeriodicalIF":3.6,"publicationDate":"2025-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145528908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Recursive filter for 2-D Markov jump systems under multi-channel deception attacks and weighted try-once-discard protocol 二维马尔可夫跳变系统在多信道欺骗攻击下的递归滤波和加权尝试一次丢弃协议

IF 3.6 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Signal Processing

Pub Date : 2025-11-08 DOI: 10.1016/j.sigpro.2025.110391

Yufan Wang, Chunyan Han

This paper investigates the state estimation for 2-D Markov jump systems with stochastic nonlinearity, and multichannel deception attacks under the weighted try-once-discard (WTOD) scheduling protocol. A novel multi-channel deception attack model is developed within a 2-D framework, in which the deception attacks are assumed to occur in two classes of channels: the output channels between the plant and sensors and the communication channels from the sensors to the estimator. The status of the multi-channel attacks is governed by two diagonal matrices, where each diagonal element is modeled as a Bernoulli random variable, and the attack signals are energy bounded. Furthermore, a 2-D WTOD protocol is developed to schedule data transmission, which orchestrates the nodes to access the network based on a quadratic selection principle. The main aim of this paper is to design a recursive estimator that minimizes the upper bounds (UBs) of the error variances (EVs) in the presence of two-channel attacks and the WTOD protocol. By means of mathematical induction and matrix inequality techniques, certain UBs are attained on the EVs. The filter gain is then computed at each step to minimize the devised UBs by solving a set of 2-D Riccati difference equations.

研究了加权尝试一次丢弃调度协议下二维随机非线性马尔可夫跳变系统的状态估计和多信道欺骗攻击问题。在二维框架内建立了一种新的多通道欺骗攻击模型，该模型假设欺骗攻击发生在两类通道上：设备与传感器之间的输出通道和传感器与估计器之间的通信通道。多通道攻击的状态由两个对角矩阵控制，其中每个对角元素被建模为一个伯努利随机变量，攻击信号是能量有界的。在此基础上，提出了一种二维WTOD协议来调度数据传输，该协议基于二次选择原则编排节点访问网络。本文的主要目的是设计一个递归估计器，在存在双通道攻击和WTOD协议的情况下最小化误差方差（ev）的上界（UBs）。利用数学归纳法和矩阵不等式技术，在ev上得到了一定的UBs。然后在每一步计算滤波器增益，通过求解一组二维里卡蒂差分方程来最小化所设计的UBs。

{"title":"Recursive filter for 2-D Markov jump systems under multi-channel deception attacks and weighted try-once-discard protocol","authors":"Yufan Wang, Chunyan Han","doi":"10.1016/j.sigpro.2025.110391","DOIUrl":"10.1016/j.sigpro.2025.110391","url":null,"abstract":"<div><div>This paper investigates the state estimation for 2-D Markov jump systems with stochastic nonlinearity, and multichannel deception attacks under the weighted try-once-discard (WTOD) scheduling protocol. A novel multi-channel deception attack model is developed within a 2-D framework, in which the deception attacks are assumed to occur in two classes of channels: the output channels between the plant and sensors and the communication channels from the sensors to the estimator. The status of the multi-channel attacks is governed by two diagonal matrices, where each diagonal element is modeled as a Bernoulli random variable, and the attack signals are energy bounded. Furthermore, a 2-D WTOD protocol is developed to schedule data transmission, which orchestrates the nodes to access the network based on a quadratic selection principle. The main aim of this paper is to design a recursive estimator that minimizes the upper bounds (UBs) of the error variances (EVs) in the presence of two-channel attacks and the WTOD protocol. By means of mathematical induction and matrix inequality techniques, certain UBs are attained on the EVs. The filter gain is then computed at each step to minimize the devised UBs by solving a set of 2-D Riccati difference equations.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"241 ","pages":"Article 110391"},"PeriodicalIF":3.6,"publicationDate":"2025-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145529035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improved RIP-based bounds performance guarantee for sparse signal recovery via Lorentzian iterative hard thresholding 改进的基于rip的洛伦兹迭代硬阈值恢复稀疏信号的边界性能保证

IF 3.6 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Signal Processing

Pub Date : 2025-11-08 DOI: 10.1016/j.sigpro.2025.110381

Haifeng Li, Xinxin Geng

The Lorentzian-based iterative hard thresholding (LIHT) algorithm demonstrates significant superiority over conventional sparse reconstruction techniques in impulsive noise environments. Previous analyses of the algorithm’s guaranteed recovery performance have primarily focused on the restricted isometry property (RIP) of the sensing matrix. In this work, we establish a tighter RIP-based convergence bound for LIHT, refining the required condition to

δ_{3 s} < \frac{\sqrt{5} - 1}{2}

, where

δ_{3 s}

represents the restricted isometry constant of order

3 s

. Furthermore, for scenarios with partial support knowledge (LIHT-PKS), we propose an enhanced bound requiring only

δ_{3 s - 2 k} < \frac{\sqrt{5} - 1}{2}

, where

k

denotes the number of known support elements. Finally, we present the impact of parameter

γ

on the performance of LIHT.

基于洛伦兹的迭代硬阈值（LIHT）算法在脉冲噪声环境下比传统的稀疏重建技术具有显著的优越性。以往对该算法保证恢复性能的分析主要集中在传感矩阵的受限等距特性（RIP）上。在这项工作中，我们建立了一个更严格的基于rip的LIHT收敛界，将所需条件细化为δ3s<；5−12，其中δ3s表示3s阶的限制等距常数。此外，对于具有部分支撑知识（light - pks）的场景，我们提出了一个只需要δ3s−2k<；5−12的增强边界，其中k表示已知支撑元素的数量。最后，我们给出了参数γ对光致发光性能的影响。

{"title":"Improved RIP-based bounds performance guarantee for sparse signal recovery via Lorentzian iterative hard thresholding","authors":"Haifeng Li, Xinxin Geng","doi":"10.1016/j.sigpro.2025.110381","DOIUrl":"10.1016/j.sigpro.2025.110381","url":null,"abstract":"<div><div>The Lorentzian-based iterative hard thresholding (LIHT) algorithm demonstrates significant superiority over conventional sparse reconstruction techniques in impulsive noise environments. Previous analyses of the algorithm’s guaranteed recovery performance have primarily focused on the restricted isometry property (RIP) of the sensing matrix. In this work, we establish a tighter RIP-based convergence bound for LIHT, refining the required condition to <span><math><mrow><msub><mrow><mi>δ</mi></mrow><mrow><mn>3</mn><mi>s</mi></mrow></msub><mo><</mo><mfrac><mrow><msqrt><mrow><mn>5</mn></mrow></msqrt><mo>−</mo><mn>1</mn></mrow><mrow><mn>2</mn></mrow></mfrac></mrow></math></span>, where <span><math><msub><mrow><mi>δ</mi></mrow><mrow><mn>3</mn><mi>s</mi></mrow></msub></math></span> represents the restricted isometry constant of order <span><math><mrow><mn>3</mn><mi>s</mi></mrow></math></span>. Furthermore, for scenarios with partial support knowledge (LIHT-PKS), we propose an enhanced bound requiring only <span><math><mrow><msub><mrow><mi>δ</mi></mrow><mrow><mn>3</mn><mi>s</mi><mo>−</mo><mn>2</mn><mi>k</mi></mrow></msub><mo><</mo><mfrac><mrow><msqrt><mrow><mn>5</mn></mrow></msqrt><mo>−</mo><mn>1</mn></mrow><mrow><mn>2</mn></mrow></mfrac></mrow></math></span>, where <span><math><mi>k</mi></math></span> denotes the number of known support elements. Finally, we present the impact of parameter <span><math><mi>γ</mi></math></span> on the performance of LIHT.</div></div>","PeriodicalId":49523,"journal":{"name":"Signal Processing","volume":"241 ","pages":"Article 110381"},"PeriodicalIF":3.6,"publicationDate":"2025-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145528939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0