检索结果-内蒙古大学图书馆

Super-Resolution With Binary Priors: Theory and algorithms

IEEE TRANSACTIONS ON signal processing 2023年 71卷 3213-3228页

作者： Sarangi, Pulak Hattori, Ryoma Komiyama, Takaki Pal, Piya Univ Calif San Diego Elect & Comp Engn La Jolla CA 92092 USA Univ Calif San Diego Ctr Neural Circuits & Behav Neurobiol Sect Dept Neurosci La Jolla CA 92092 USA Univ Calif Halicioglu Data Sci Inst San Diego CA 92092 USA

The problem of super-resolution is concerned with the reconstruction of temporally/spatially localized events (or spikes) from samples of their convolution with a low-pass filter. Distinct from prior works which exploit sparsity in appropriate domains in order to solve the resulting ill-posed problem, this paper explores the role of binary priors in super-resolution, where the spike (or source) amplitudes are assumed to be binary-valued. Our study is inspired by the problem of neural spike deconvolution, but also applies to other applications such as symbol detection in hybrid millimeter wave communication systems. This paper makes several theoretical and algorithmic contributions to enable binary super-resolution with very few measurements. Our results show that binary constraints offer much stronger identifiability guarantees than sparsity, allowing us to operate in "extreme compression" regimes, where the number of measurements can be significantly smaller than the sparsity level of the spikes. To ensure exact recovery in this "extreme compression" regime, it becomes necessary to design algorithms that exactly enforce binary constraints without relaxation. In order to overcome the ensuing computational challenges, we consider a first order auto-regressive filter (which appears in neural spike deconvolution), and exploit its special structure. This results in a novel formulation of the super-resolution binary spike recovery in terms of binary search in one dimension. We perform numerical experiments that validate our theory and also show the benefits of binary constraints in neural spike deconvolution from real calcium imaging datasets.

关键词： Superresolution Deconvolution Filtering algorithms Calcium Low-pass filters IIR filters signal processing algorithms Beta-expansions binary compressed sensing sparsity binary search spike deconvolution super-resolution

来源：评论

学校读者我要写书评

暂无评论

Diffusion Bayesian Decorrelation algorithms Over Networks

引用

IEEE TRANSACTIONS ON signal processing 2023年 71卷 571-586页

作者： Huang, Fuyi Zhang, Sheng Zhang, Jiashu Chen, Hongyang Sayed, Ali H. Guangxi Univ Sch Comp Elect & Informat Guangxi Key Lab Multimedia Commun & Network Techno Nanning 530004 Peoples R China Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu 611756 Peoples R China Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu 611756 Peoples R China Res Ctr Graph Comp Zhejiang Lab Hangzhou 311121 Peoples R China Ecole Polytech Federalede Lausanne Sch Engn CH-1015 Lausanne Switzerland

The convergence rate of the diffusion normalized least mean squares (NLMS) algorithm can be speeded up by decorrelation of signals. However, the diffusion decorrelation NLMS algorithm confronts the conflicting requirements of fast convergence rate and small steady-state error. To address the issue, this paper proposes a family of diffusion Bayesian decorrelation least mean squares (DBDLMS) algorithms based on decorrelated observation models. Firstly, the weight update equations of the proposed DBDLMS algorithms are obtained by performing Bayesian inference over the decorrelated observation models, with variable step-sizes emerging naturally to help address the conflicting requirement. Secondly, the update equations of the decorrelation coefficient vectors are inferred from the Bayesian perspective, with the variable step-sizes emerging again. Subsequently, the performance analysis of the proposed DBDLMS algorithms is carried out. Moreover, a simple and effective approach is derived to estimate the free parameters for the proposed DBDLMS algorithms. Finally, the learning performance of the proposed algorithms are verified by Monte Carlo simulations.

关键词： Decorrelation signal processing algorithms Bayes methods Estimation Convergence Inference algorithms Steady-state Adaptive networks decorrelation diffusion strategy distributed processing least mean squares

来源：评论

学校读者我要写书评

暂无评论

Finite-Time Analysis of Markov Gradient Descent

引用

IEEE TRANSACTIONS ON AUTOMATIC CONTROL 2023年第4期68卷 2140-2153页

作者： Doan, Thinh T. Virginia Tech Bradley Dept Elect & Comp Engn Blacksburg VA 24060 USA

Motivated by its broad applications in system identifications, stochastic control, and machine learning, we study the popular stochastic gradient descent (SGD) when the gradient samples of the underlying objective function are generated from Markov processes. This Markov sampling leads to the gradient samples being biased and not independent. The existing results for the convergence of SGD under Markov settings are often established under the assumption on the boundedness of either the iterates or the gradient samples. This assumption can be guaranteed through an impractical projection step to a compact set often defined over the unknown optimal solution of the underlying problem. In this article, we show that this projection step is unnecessary in many settings. In particular, we study the convergence of SGD under Markov samples without requiring any projection step for different objective functions, ranging from strongly convex to nonconvex objectives satisfying Polyak-Lojasiewicz conditions. We show that SGD converges nearly at the same rate with Markovian gradient samples as with independent gradient samples. The only difference is a logarithmic factor that accounts for the mixing time of the Markov process. Finally, we provide numerical experiments in robust identification problems to illustrate our theoretical results, where we consider SGD with samples generated by a Markov process.

关键词： Markov processes Convergence Optimization Linear programming TV Convex functions signal processing algorithms Gradient methods optimization

来源：评论

学校读者我要写书评

暂无评论

Information Geometry-Based Track-Before-Detect Algorithm for Slow-Moving Fluctuating Target Detection

引用

IEEE TRANSACTIONS ON signal processing 2023年 71卷 1833-1848页

作者： Wu, Hao Cheng, Yongqiang Chen, Xixi Yang, Zheng Li, Xiang Natl Univ Def Technol Coll Elect Sci & Technol Changsha 410000 Peoples R China Air Force Engn Univ Air & Missile Def Coll Xian 710051 Peoples R China

To treat the slow-moving fluctuating target detection issues, the information geometry-based track-before-detect algorithms, which combines the performance advantages of information geometry detectors and the multi-frame information integration ability of dynamic programming algorithm, are proposed in this article. The proposed methods are based on the Hermitian positive definite (HPD) manifold and power spectrum (PS) manifold, that the geometric properties of the target feature track and clutter track on the HPD or PS manifold are exploited for the integration of inter-frame target information. Specifically, the IG-based scoring function is designed to evaluate the candidate trajectories, and a general IG-based DP algorithm is deduced to obtain the trajectories with the maximum integration of scoring functions. Moreover, to avoid the performance degradation resulting from the illegal candidate trajectories, a stricter constraint for the trajectories of slow-moving target is established, and a corresponding efficient IG-based DP algorithm is deduced by utilizing the skipping transition. Experimentally, the superiority of the proposed methods have been validated with the real-recorded ship target echo data and sea clutter data. The experimental results show that the proposed methods can provide a signal-to-clutter ratio improvement of approximately 5.5 dB.

关键词： Clutter Detectors Trajectory Target tracking Manifolds Covariance matrices signal processing algorithms Information geometry information geometry detector track-before-detect (TBD) dynamic programming Hermitian positive definite manifold power spectrum manifold

来源：评论

学校读者我要写书评

暂无评论

Walk for Learning: A Random Walk Approach for Federated Learning From Heterogeneous Data

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2023年第4期41卷 929-940页

作者： Ayache, Ghadir Dassari, Venkat El Rouayheb, Salim Rutgers State Univ Elect & Comp Engn Dept Piscataway NJ 08854 USA US Army Res Lab White Oak MD 20783 USA

We consider the problem of a Parameter Server (PS) that wishes to learn a model that fits data distributed on the nodes of a graph. We focus on Federated Learning (FL) as a canonical application. One of the main challenges of FL is the communication bottleneck between the nodes and the parameter server. A popular solution in the literature is to allow each node to do several local updates on the model in each iteration before sending it back to the PS. While this mitigates the communication bottleneck, the statistical heterogeneity of the data owned by the different nodes has proven to delay convergence and bias the model. In this work, we study random walk (RW) learning algorithms for tackling the communication and data heterogeneity problems. The main idea is to leverage available direct connections among the nodes themselves, which are typically "cheaper" than the communication to the PS. In a random walk, the model is thought of as a "baton" that is passed from a node to one of its neighbors after being updated in each iteration. The challenge in designing the RW is the data hetErogeneity and the uncertainty about the data distributions. Ideally, we would want to visit more often nodes that hold more informative data. We cast this problem as a sleeping multi-armed bandit (MAB) to design near-optimal node sampling strategy that achieves a variance reduced gradient estimates and approaches sub-linearly the optimal sampling strategy. Based on this framework, we present an adaptive random walk learning algorithm. We provide theoretical guarantees on its convergence. Our numerical results validate our theoretical findings and show that our algorithm outperforms existing random walk algorithms.

关键词： Convergence Data models signal processing algorithms Costs Adaptation models Numerical models Computational modeling Decentralized learning distributed learning random walk incremental algorithms multi-armed bandit

来源：评论

学校读者我要写书评

暂无评论

Adaptive Frame-Rate Partitioned Video SAR

IEEE TRANSACTIONS ON RADAR SYSTEMS

引用

IEEE TRANSACTIONS ON RADAR SYSTEMS 2025年 3卷 576-590页

作者： Sun, Zhengyang Wen, Liwu Ding, Jinshan Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China

Video synthetic aperture radar (ViSAR) is a promising technology for the surveillance of ground-moving targets. Traditionally, ViSAR imaging and moving target tracking are performed sequentially, where high-frame-rate imaging is applied to the entire SAR scene. However, this approach generates redundant information that is often unnecessary for ViSAR applications. We propose a partitioned adaptive frame-rate (PAFR) ViSAR processing strategy, which adaptively partitions the SAR scene, applying high-frame-rate imaging to potential target regions and low frame rate to large static areas. An integrated imaging and tracking algorithm that synthesizes back-projection (BP) and track-before-detect (TBD) techniques has been derived for efficient bidirectional information exchange. BP imaging provides high-resolution measurements to refine tracking parameters, while TBD tracking offers predictive data to guide the adaptive partitioning of the imaging area. Additionally, we enhance the traditional dynamic programming-based TBD (DP-TBD) algorithm by incorporating the morphological features of target shadows, allowing for more accurate corrections and refinements of predicted states. This enhancement significantly improves both tracking accuracy and speed. The experimental results from airborne radar data have proven the capability of the proposed algorithm to achieve both efficient PAFR imaging and fast target tracking simultaneously, which paves the way for more potential applications in ViSAR.

关键词： Target tracking Radar tracking Imaging Radar imaging Synthetic aperture radar Radar Prediction algorithms Heuristic algorithms signal processing algorithms Radar polarimetry Ground-moving target indication (GMTI) radar imaging target tracking track before detect (TBD) video synthetic aperture radar (ViSAR)

来源：评论

学校读者我要写书评

暂无评论

Subgradient Descent Learning Over Fading Multiple Access Channels With Over-the-Air Computation

引用

IEEE ACCESS 2023年 11卷 94623-94635页

作者： Gez, Tamir L. S. Cohen, Kobi Ben Gurion Univ Negev Sch Elect & Comp Engn IL-8410501 Beer Shev Israel

We focus on a distributed learning problem in a communication network, consisting of $N$ distributed nodes and a central parameter server (PS). The PS is responsible for performing the computation based on data received from the nodes, which are transmitted over a multiple access channel (MAC). The objective function for this problem is the sum of the local loss functions of the nodes. This problem has gained attention in the field of distributed sensing systems, as well as in the area of federated learning (FL) recently. However, current approaches to solving this problem rely on the assumption that the loss functions are continuously differentiable. In this paper, we first address the case where this assumption does not hold. We develop a novel algorithm called Sub-Gradient descent Multiple Access (SGMA) to solve the learning problem over MAC. SGMA involves each node transmitting an analog shaped waveform of its local subgradient over MAC, and the PS receiving a superposition of the noisy analog signals, resulting in a bandwidth-efficient over-the-air (OTA) computation used to update the learned model. We analyze the performance of SGMA and prove that it has a convergence rate that approaches that of the centralized subgradient algorithm in large networks. Simulation results using real datasets show the effectiveness of SGMA.

关键词： Fading channels Bandwidth Task analysis Noise measurement Computational modeling Simulation signal processing algorithms Decentralized control Learning systems Federated learning Multiple access interference Distributed learning gradient descent (GD)-type learning subgradient methods federated learning (FL) multiple access channel (MAC) over-the-air (OTA) computation

来源：评论

学校读者我要写书评

暂无评论

Distributed Set-Membership Fusion Filtering for Nonlinear 2-D Systems Over Sensor Networks: An Encoding-Decoding Scheme

引用

IEEE TRANSACTIONS ON CYBERNETICS 2023年第1期53卷 416-427页

作者： Zhu, Kaiqun Wang, Zidong Han, Qing-Long Wei, Guoliang Univ Shanghai Sci & Technol Dept Control Sci & Engn Shanghai 200093 Peoples R China Brunel Univ London Dept Comp Sci Uxbridge UB8 3PH Middx England Swinburne Univ Technol Sch Sci Comp & Engn Technol Melbourne Vic 3122 Australia Univ Shanghai Sci & Technol Coll Sci Shanghai 200093 Peoples R China

In this article, the distributed set-membership fusion filtering problem is investigated for a class of nonlinear 2-D shift-varying systems subject to unknown-but-bounded noises over sensor networks. The sensors are communicated with their neighbors according to a given topology through wireless networks of limited bandwidth. With the purpose of relieving the communication burden as well as enhancing the transmission security, a logarithmic-type encoding-decoding mechanism is introduced for each sensor node so as to encode the transmitted data with a finite number of bits. A distributed set-membership filter is designed to determine the local ellipsoidal set that contains the system state by only utilizing the data from the local sensor node and its neighbors, where the proposed filter scheme is truly distributed with desirable scalability. Then, a new ellipsoid-based fusion rule is developed for the designed set-membership filters in order to form the fused ellipsoidal set that has a globally smaller volume than all local ellipsoidal sets. With the aid of the mathematical induction technique, the set theory, and the convex optimization approach, sufficient conditions are derived for the existence of the desired distributed set-membership filters and the fusion weights. Then, the filter parameters and the fusion weights are acquired by solving a set of constrained optimization problems. Finally, an illustrative example is given to demonstrate the effectiveness of the proposed fusion filtering algorithm.

关键词： Symmetric matrices Decoding Topology signal processing algorithms Network topology Wireless networks Two dimensional displays Distributed set-membership filtering (SMF) encoding-decoding mechanism (EDM) fusion filtering sensor networks two-dimensional (2-D) systems

来源：评论

学校读者我要写书评

暂无评论

SPANet: A Self-Balancing Position Attention Network for Anchor-Free SAR Ship Detection

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2023年 16卷 8363-8378页

作者： Chang, Hao Fu, Xiongjun Lu, Jihua Guo, Kunyi Dong, Jian Zhao, Congxia Feng, Cheng Li, Ziying Zhang, Yue Beijing Inst Technol Sch Integrated Circuits & Elect Beijing 100081 Peoples R China

Synthetic aperture radar (SAR) images of ships have complex background interference, multi-scale targets, and irregular distribution characteristics. However, existing mainstream SAR ship detection algorithms rely on manually designed hyperparameters. This results in poor robustness, which makes it difficult to effectively balance the detection accuracy and speed. To solve these problems, a novel anchor-free SAR ship detection algorithm based on self-balancing position attention (SBPA) is proposed. First, a lightweight feature extraction backbone (GhostVS-Net) is designed by FOCUS, ghost, and separable convolution modules to extract feature information. This helps to extract the contour features of ships and suppress unrelated interference, making it more suitable for the scattering characteristics of SAR images. Second, an SBPA module is designed, which balances the local image features under multiple receptive fields, and aggregates the global position information and spatial context information. The proposed SBPA module considers the characteristics of background, scale, and distribution of SAR images to obtain greatly improved positioning accuracy. Finally, the feature pyramid network is applied to fuse the scale context information, and further improve the accuracy of detection. Experimental results on the SSDD and HRSID datasets show that the proposed network bears feature of accurate detection and strong robustness, with the mean average precision reaches 99.72% and 95.30%, which reveals that it outperforms all current state-of-the-art algorithms with super high performances.

关键词： Feature extraction Marine vehicles Radar polarimetry Convolution Detection algorithms Prediction algorithms signal processing algorithms Anchor-free mechanism self-attention small target detection synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Cardiotocography Paper Digitization and Classification for Abnormality Detection

引用

IEEE ACCESS 2023年 11卷 42521-42533页

作者： Ozturk, Sibel Sahin, Safiye Agapinar Aksoy, Ayse Nur Ari, Berna Akinbi, Alex Ataturk Univ Dept Midwifery TR-25030 Erzurum Turkiye Erzurum Reg Training & Res Hosp Dept Obstet & Gynecol TR-25240 Erzurum Turkiye Firat Univ Dept Elect & Elect Engn TR-23119 Elazig Turkiye Liverpool John Moores Univ Sch Comp Sci & Math Liverpool L2 2QP England

Cardiotocography (CTG) is a clinical procedure that is used to track and gauge the severity of fetal distress. Although CTG is the most often used equipment to monitor and assess the health of the fetus, the high rate of false positive results due to visual interpretation significantly contributes to needless surgical delivery or delayed intervention. In this study, a novel approach is introduced where both printing CTG paper is digitized and a machine learning approach is employed to detect the abnormality in the digitized CTG signal. Image processing-based preprocessing steps are employed to make the printing of CTG paper more convenient to extract the CTG signal. Various signal-processing techniques are used to calibrate the extracted CTG signal. Then, Empirical Mode Decomposition (EMD) is used to decompose the CTG signal into its frequency components and instantaneous frequency and spectral entropy features are extracted. After feature normalization and feature selection with ReliefF algorithm, support vector machines (SVM) is used for the classification of the normal and abnormal classes. A novel dataset is used in the experimental works and various performance evaluation metrics are used for the evaluation of the achievement of the proposed method. 10-fold cross-validation-based experiments show that the proposed method is quite efficient in abnormality detection in printing CTG papers where an average accuracy score of around 90.0% is produced.

关键词： Image color analysis Feature extraction Image processing signal processing algorithms Fetal heart rate Classification algorithms Prediction algorithms EMD feature selection image enhancement printing CTG paper signal reconstruction SVM classifier

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：