检索结果-内蒙古大学图书馆

Two-Stage Deep Convolutional Neural Networks for DOA Estimation in Impulsive Noise

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION 2024年第2期72卷 2047-2051页

作者： Cai, Ruiyan Tian, Quan Taizhou Univ Sch Elect & Informat Engn Taizhou 318000 Peoples R China

Direction-of-arrival (DOA) estimation methods have been widely and deeply studied in Gaussian noise environments. However, if there is impulsive channel noise, the performance of the method will significantly decline, and reasonable results may not be obtained. Considering that the high performance of model-driven DOA estimation algorithms requires large arrays and more sample data, this communication proposes a two-stage deep convolutional neural network (TSDCN) algorithm for DOA estimation. The first stage suppresses alpha-stable distributed impulsive noise through an adversarial learning network, and the second stage realizes DOA estimation through a deep convolutional neural network. Simulation and real-world experiments show that the TSDCN outperforms most DOA estimation algorithms in terms of robustness and estimation accuracy in impulsive noise environments.

关键词： Estimation Direction-of-arrival estimation signal processing algorithms Decoding Antenna arrays Convolutional neural networks Array signal processing Adversarial learning deep convolutional neural network direction of arrival (DOA) impulsive noise

来源：评论

学校读者我要写书评

暂无评论

Adaptive Anomaly Detection in Network Flows With Low-Rank Tensor Decompositions and Deep Unrolling

IEEE OPEN JOURNAL OF SIGNAL PROCESSING

引用

IEEE OPEN JOURNAL OF signal processing 2025年 6卷 417-433页

作者： Schynol, Lukas Pesavento, Marius Tech Univ Darmstadt Darmstadt Germany

Anomaly detection (AD) is increasingly recognized as a key component for ensuring the resilience of future communication systems. While deep learning has shown state-of-the-art AD performance, its application in critical systems is hindered by concerns regarding training data efficiency, domain adaptation and interpretability. This work considers AD in network flows using incomplete measurements, leveraging a robust tensor decomposition approach and deep unrolling techniques to address these challenges. We first propose a novel block-successive convex approximation algorithm based on a regularized model-fitting objective where the normal flows are modeled as low-rank tensors and anomalies as sparse. An augmentation of the objective is introduced to decrease the computational cost. We apply deep unrolling to derive a novel deep network architecture based on our proposed algorithm, treating the regularization parameters as learnable weights. Inspired by Bayesian approaches, we extend the model architecture to perform online adaptation to per-flow and per-time-step statistics, improving AD performance while maintaining a low parameter count and preserving the problem's permutation equivariances. To optimize the deep network weights for detection performance, we employ a homotopy optimization approach based on an efficient approximation of the area under the receiver operating characteristic curve. Extensive experiments on synthetic and real-world data demonstrate that our proposed deep network architecture exhibits a high training data efficiency, outperforms reference methods, and adapts seamlessly to varying network topologies.

关键词： Tensors Computer architecture Computational modeling Adaptation models signal processing algorithms Artificial neural networks Data models Computational efficiency Anomaly detection Training data area under the curve deep unrolling low-rank network flows robust principal component analysis tensor decomposition

来源：评论

学校读者我要写书评

暂无评论

Extended Target Tracking Utilizing Machine-Learning Software-With Applications to Animal Classification

引用

IEEE signal processing LETTERS 2024年 31卷 376-380页

作者： Malmstrom, Magnus Kullberg, Anton Skog, Isaac Axehill, Daniel Gustafsson, Fredrik Linkoping Univ S-58183 Linkoping Sweden Swedish Def Res Agcy FOI S-58183 Linkoping Sweden Uppsala Univ S-75310 Uppsala Sweden

This letter considers the problem of detecting and tracking objects in a sequence of images. The problem is formulated in a filtering framework, using the output of object-detection algorithms as measurements. An extension to the filtering formulation is proposed that incorporates class information from the previous frame to robustify the classification. Further, the properties of the object-detection algorithm are exploited to quantify the uncertainty of the bounding box detection in each frame. The complete filtering method is evaluated on camera trap images of the four large Swedish carnivores, bear, lynx, wolf, and wolverine. The experiments show that the class tracking formulation leads to a more robust classification.

关键词： signal processing algorithms Classification algorithms Cameras Target tracking Filtering algorithms Standards Loss measurement Multi-object tracking object detection environmental monitoring deep learning Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Adaptively Optimized Masking EMD for Separating Intrinsic Oscillatory Modes of Nonstationary signals

引用

IEEE signal processing LETTERS 2024年 31卷 216-220页

作者： Sun, Congshan Li, Hongwei Xu, Cong Ma, Lin Li, Haifeng Harbin Inst Technol Fac Comp Harbin 150001 Peoples R China

Empirical mode decomposition (EMD) is a well-established technique to decompose nonstationary signals into intrinsic oscillatory modes, which is essential to catch crucial information hidden in nonstationary signals. However, when decomposing signals with intermittency or closely spaced frequency modes, EMD suffers from severe mode mixing problems (MMP). Therefore, we develop a novel adaptively optimized masking EMD (AOMEMD), a generalized, automated method to solve MMP. The work focuses on two aspects: i) Masking signals with different scales are adaptively iteratively generated based on Hilbert analytic solution and applied to raw data to assist EMD in solving MMP. ii) A universal mode mixing measure index (UMI) is proposed to quantitatively evaluate the extent of mode mixing. An optimization routine is then developed to optimize the amplitude and frequency of masking signals with the objective of minimizing the UMI to further improve the frequency separation performance of AOMEMD. Experiments on synthetic and real-world signals demonstrate that AOMEMD outperforms EMD and its variants in effectively addressing MMP, yielding more reasonable and reliable results. AOMEMD can separate modes with frequency ratios up to 0.9.

关键词： Optimization Indexes signal processing algorithms Power system reliability Oscillators Flowcharts Filtering Nonstationary signals EMD mode mixing problem masking signals universal mode mixing measure index

来源：评论

学校读者我要写书评

暂无评论

A Block Minorization-Maximization Algorithm for Row-Sparse Principal Component Analysis

引用

IEEE signal processing LETTERS 2024年 31卷 1905-1909页

作者： Rajpurohit, Pushpendra Arora, Aakash Babu, Prabhu Indian Inst Technol Delhi Ctr Appl Res Elect New Delhi 110016 India

We present a block minorization-maximization (MM) algorithm to solve the row-sparse principal component analysis (RSPCA) problem. The RSPCA problem consists of orthogonality and row-sparsity constraints. We model the decision variable as a product of a selection matrix and the matrix of principal components. This problem is solved by updating the two blocks in a cyclic manner. As the problem with respect to the selection matrix does not admit a closed-form solution, we propose to utilize the MM technique to solve this subproblem. Numerical simulations are provided to show the efficacy of the proposed algorithm.

关键词： Covariance matrices Sparse matrices Principal component analysis signal processing algorithms Convergence Linear programming Matrix decomposition Minorization-maximization (MM) sparse principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A Method for Generating Pseudo-Polarization Images

引用

IEEE signal processing LETTERS 2024年 31卷 3030-3033页

作者： Li, Shiyu Gao, Meijing Fan, Xiangrui Bai, Yang Yan, Yonghao Yanshan Univ Coll Informat Sci & Engn Qinhuangdao 066004 Peoples R China Beijing Inst Technol Sch Integrated Circuits & Elect Beijing 100081 Peoples R China Beijing Aerosp Automat Control Res Inst Beijing 100039 Peoples R China

This letter proposes an algorithm to generate pseudo-polarization images under situations with limited polarization image samples. The algorithm is inspired by the principle of polarimetric imaging with DoFP and utilizes a specially designed 2x2 pseudo-polarization filter to generate two sets of orthogonal pseudo-polarization images. Furthermore, the Gaussian filter layering and image gradient-based feature search method are employed for the simulated generation of polarization features for both specular and diffuse reflections. Experiment results indicate high correspondence between the generated pseudo-polarization and real polarization images. The method effectively simulates polarization images acquired by the DoFP polarimeter under different conditions.

关键词： Imaging signal processing algorithms Reflection Image synthesis Azimuth Indexes Estimation Fans Real-time systems Lighting Polarization imaging pseudo polarization image filtering gradient estimation

来源：评论

学校读者我要写书评

暂无评论

Gridless Maximum Likelihood One-Bit Direct Position Determination

引用

IEEE signal processing LETTERS 2024年 31卷 3099-3103页

作者： Li, Pan Li, Jianfeng Zhang, Xiaofei Wu, Qihui Nanjing Univ Aeronaut & Astronaut Coll Elect & Informat Engn Nanjing 210016 Peoples R China Nanjing Univ Aeronaut & Astronaut Key Lab Dynam Cognit Syst Electromagnet Spectrum S Minist Ind & Informat Technol Nanjing 211106 Peoples R China

Direct position determination (DPD) (a.k.a. direct localization) offers enhanced precision over traditional two-step approaches. This technique, however, involves considerable communication overhead for transmitting raw data. Low-bit direct localization methods have recently been introduced to address this issue. In this letter, we present a gridless, one-bit maximum likelihood (ML) approach for the direct localization of an orthogonal frequency division multiplexing (OFDM) signal source. A recent majorization-minimization (MM) algorithm introduced a surrogate function for the log-likelihood function, which lacks a closed-form optimal solution and requires exhaustive searches at each iteration. Our method improves upon this algorithm by developing a refined surrogate function that yields a closed-form optimal solution, thereby eliminating the need for exhaustive searches. Accordingly, the proposed MM approach can eliminate grid quantization errors (GQE) by eliminating the search process. Simulation results validate the proposed method's efficacy in mitigating GQE and its efficiency in scenarios with densely populated search grids.

关键词： Location awareness OFDM Quantization (signal) signal processing algorithms Maximum likelihood estimation Closed-form solutions Base stations Minimization Upper bound Time measurement Direct position determination majorization-minimization one-bit quantization maximum likelihood estimation localization

来源：评论

学校读者我要写书评

暂无评论

Gram Matrix Completion for Cooperative Localization in Partially Connected Wireless Sensor Network

引用

IEEE signal processing LETTERS 2024年 31卷 939-943页

作者： Jiang, Peiyue Zhuang, Zehong Xie, Wei South China Univ Technol Coll Automat Sci & Engn Guangzhou 510641 Peoples R China Southern Univ Sci & Technol Dept Mech & Energy Engn Shenzhen 518055 Peoples R China

The performance of cooperative localization can be degraded in the partially connected wireless sensor network (WSN). In this letter, we address the localization problem based on the incomplete distance information. By considering the input of distance-based localization algorithms, we proposed a novel Gram matrix completion method. With the function of Gram matrix, we indirectly represent the measurement of Gram matrix by the Euclidean distance matrix (EDM). The recovered Gram matrix can directly used for multidimensional scaling (MDS) or semi-definite programming (SDP) to localize the nodes. Then we present the procedure of MDS and rigid transformation estimation to localize the nodes. The performance of the proposed algorithm is evaluated compared with low rank matrix completion and positioning algorithms.

关键词： Location awareness Matrix decomposition Wireless sensor networks Transmission line matrix methods signal processing algorithms Minimization Linear matrix inequalities Cooperative localization gram matrix low rank matrix completion (LRMC) multidimensional scaling (MDS) semi-definite programming (SDP)

来源：评论

学校读者我要写书评

暂无评论

Enabling Model-Based Design for Real-Time Spike Detection

IEEE OPEN JOURNAL OF ENGINEERING IN MEDICINE AND BIOLOGY

引用

IEEE OPEN JOURNAL OF ENGINEERING IN MEDICINE AND BIOLOGY 2025年 6卷 312-319页

作者： Di Florio, Mattia Bornat, Yannick Care, Marta Cota, Vinicius Rosa Buccelli, Stefano Chiappalone, Michela Univ Genoa Dept Informat Bioengn Robot Syst Engn DIBRIS I-16145 Genoa Italy Univ Bordeaux Lab Integrat Mat Syst IMS Bordeaux INP CNRS UMR 5218 F-33405 Talence France IRCCS Osped Policlin San Martino I-16132 Genoa Italy Ist Italiano Tecnol Rehab Technol Lab I-16163 Genoa Italy

Goal: This study addresses the inherent difficulties in the creation of neuroengineering devices for real-time neural signal processing, a task typically characterized by intricate and technically demanding processes. Beneath the substantial hardware advancements in neurotechnology, there is often rather complex low-level code that poses challenges in terms of development, documentation, and long-term maintenance. Methods: We adopted an alternative strategy centered on Model-Based Design (MBD) to simplify the creation of neuroengineering systems and reduce the entry barriers. MBD offers distinct advantages by streamlining the design workflow, from modelling to implementation, thus facilitating the development of intricate systems. A spike detection algorithm has been implemented on a commercially available system based on a Field-Programmable Gate Array (FPGA) that combines neural probe electronics with configurable integrated circuit. The entire process of data handling and data processing was performed within the Simulink environment, with subsequent generation of hardware description language (HDL) code tailored to the FPGA hardware. Results: The validation was conducted through in vivo experiments involving six animals and demonstrated the capability of our MBD-based real time processing (latency <= 100.37 s) to achieve the same performances of offline spike detection. Conclusions: This methodology can have a significant impact in the development of neuroengineering systems by speeding up the prototyping of various system architectures. We have made all project code files open source, thereby providing free access to fellow scientists interested in the development of neuroengineering systems.

关键词： Hardware design languages Software packages Codes Field programmable gate arrays Computer architecture Hardware signal processing algorithms Neural engineering signal processing Computational modeling in vivo experiments HDL coder Field-Programmable Gate Array (FPGA) neuroengineering

来源：评论

学校读者我要写书评

暂无评论

Online Neyman-Pearson Classification With Hierarchically Represented Models

引用

IEEE JOURNAL OF SELECTED TOPICS IN signal processing 2025年第3期19卷 478-490页

作者： Can, Basarbatu Pelvan, Soner Ozgun Ozkan, Huseyin ABN Amro Bank NV NL-1082 PP Amsterdam Netherlands Sabanci Univ Fac Engn & Nat Sci Elect Engn TR-34956 Istanbul Turkiye

We consider the statistical anomaly detection problem with regard to false alarm rate (or false positive rate, FPR) controllability, nonlinear modeling and computational efficiency for real-time processing. A decision theoretical solution can be formulated as Neyman-Pearson (NP) hypothesis testing (binary classification: anomaly/nominal). In this framework, we propose an ensemble NP classifier (Tree OLNP) that is based on a binary partitioning tree. Tree OLNP generates an ensemble of sample space partitions. Each partition corresponds to an online piecewise linear (hence nonlinear) expert classifier as a union of online linear NP classifiers (union of OLNPs). While maintaining a precise control over the FPR, Tree OLNP generates its overall prediction as a performance driven and time varying weighted combination of the experts. This provides a dynamical nonlinear modeling power in the sense that simpler (more powerful) experts receive larger weights early (late) in the data stream, which manages the bias-variance trade-off and mitigates overfitting/underfitting issues. We mathematically prove that, for any stream, Tree OLNP asymptotically performs at least as well as of the best expert in terms of the NP performance with a regret diminishing in the order O(1/root t) (t: data size). Our algorithm is computationally highly efficient since it is online and its complexity scales linearly with respect to both the data size and tree depth, and scales twice-logarithmic with respect to the number of experts. We experimentally show that Tree OLNP strongly outperforms the state-of-the-art alternative techniques.

关键词： Costs Classification algorithms Data models Controllability Complexity theory Computational modeling Tuning Training signal processing algorithms Real-time systems Anomaly detection neyman pearson classification false alarm rate online decision tree partitioning

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：