检索结果-内蒙古大学图书馆

Self-Knowledge Distillation-Based Staged Extraction and Multiview Collection Network for RGB-D Mirror Segmentation

IEEE signal processing LETTERS 2024年 31卷 1029-1033页

作者： Zhang, Han Ran, Xiaoxiao Zhou, Wujie Zhejiang Univ Sci & Technol Sch Informat & Elect Engn Hangzhou 310023 Peoples R China COMAC Shanghai Aircraft Mfg Co Ltd 5G Innovat Ctr Shanghai 201324 Peoples R China

Integrating RGB and depth information could improve mirror segmentation performance. Therefore, it is important to extract and use both types of information. Previous algorithms have often used existing backbone networks for feature extraction, frequently ignoring the differences between different feature layers. To address this issue, we propose an algorithm for staged feature extraction using a multitype backbone network that combines the features of convolutional neural networks and transformers. In addition, we developed a multiview collector to extract cross-modal fusion features from various perspectives. Furthermore, we applied the self-knowledge distillation technique to the proposed algorithm, thereby improving the model's performance. The proposed model achieved competitive results on a benchmark dataset.

关键词： Feature extraction Mirrors Data mining Semantic segmentation Convolution signal processing algorithms Decoding Mirror segmentation convolutional neural networks transformer self-knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Power Control in D2D Networks: A Distributed ADMM Approach With Dynamic Penalty Coefficient

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第5期74卷 8238-8250页

作者： Huang, Yuting Gao, Xiaozheng Shi, Minwei Ye, Neng Yang, Kai Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Beijing Inst Technol Sch Cyberspace Sci & Technol Beijing 100081 Peoples R China

Device-to-device (D2D) communication plays an important role in future networks due to the explosive growth in Internet of Things (IoT) devices. The surge of mobile devices necessitates higher data transmission rates and resource utilization efficiency. To address the requirements, developing effective power control algorithms is crucial to improve network performance and reduce energy consumption. In this work, we propose a distributed power control scheme based on the combination of the alternating direction method of multipliers (ADMM) algorithm and the successive convex approximation (SCA) algorithm. With the aim of maximizing energy efficiency, the original problem is decomposed into multiple convex subproblems through SCA, and the distributed optimization of ADMM is used to solve each subproblem, thus making the solution of the problem more efficient. In particular, a dynamic penalty coefficient strategy is also developed to improve the convergence performance of the distributed algorithm. The simulation results demonstrate that compared with centralized power control methods, the proposed method can achieve similar optimal values and effectively distribute the computational load to each device, which can support the optimization design and implementation of future D2D communication systems.

关键词： Device-to-device communication Power control Throughput Power demand Data communication signal processing algorithms Resource management Power amplifiers Internet of Things Heuristic algorithms Alternating direction method of multipliers D2D communication energy efficiency power control

来源：评论

学校读者我要写书评

暂无评论

A Unified Affine-Projection-Like Adaptive Algorithm for System Identification

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2024年第2期71卷 982-986页

作者： Li, Yingsong Fu, Yonglin Miao, Yongchun Huang, Zhixiang Diniz, Paulo S. R. Anhui Univ Key Lab Intelligent Comp & Signal Proc Minist Educ Hefei 230601 Anhui Peoples R China Univ Fed Rio de Janeiro Program Elect Engn BR-21941972 Rio De Janeiro Brazil

A unified affine-projection-like adaptive (UAPLA) algorithm is devised and verified for system identification. The UAPLA algorithm uses a generalized cost function encompassing some data-reusing methods to cope with colored input signals. Furthermore, the UAPLA algorithm is derived based on the new cost function to approximate several affine-projection algorithms. As a result, the proposed UAPLA algorithm approximates some classical adaptive filters that can be considered as special cases of the UAPLA, allowing flexibility to achieve low estimation errors under impulsive noises. The obtained results conducted by simulations help to corroborate the superiority of the proposed UAPLA algorithm over other popular AP algorithms.

关键词： Approximation algorithms Convergence signal processing algorithms System identification Mathematical models Echo cancellers Robustness Unified adaptive filter algorithm general cost function system identification impulsive noise

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

A Time-Domain Frequency Analyzer Based on Goertzel Algorithm

引用

IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS 2025年第6期33卷 1516-1529页

作者： Zareie, Mahsa El-Sankary, Kamal Colombo, Dalton Martini El-Masry, Ezz Dalhousie Univ Dept Elect & Comp Engn Halifax NS B3H 4R2 Canada Univ Fed Minas Gerais Elect Engn Dept BR-31270901 Belo Horizonte Brazil

This article presents a novel time-domain implementation of the second-order Goertzel frequency analyzer, which can be extended for use in infinite impulse response (IIR)/finite impulse response (FIR) filters. A set of time-domain arithmetic circuits, including a one-step time register (TR), time amplifier (TA), time adder, and unit delay operator (z(-1)), are introduced to overcome the limitations of conventional time-domain filters. The working principles and nonidealities of each block are analyzed and compared with the existing methods. The proposed filter is implemented in a 180-nm CMOS process with a 0.9-V supply voltage. The designed frequency analyzer is tunable to extract the amplitude and phase angle of signals up to 400 Hz. Simulation results, targeting a 280-Hz signal at a 19.88-kHz sampling frequency, demonstrate that the filter can detect the amplitude and phase of a voltage signal in the time domain with an error below 5%. The filter achieves a resolution of 76.7 dBV/s, consumes less than 24 mu W of power, and the estimated silicon area is almost 0.828 mm(2).

关键词： Time-domain analysis Filters Delays Circuits Inverters Time-frequency analysis signal processing algorithms Voltage IIR filters Discrete Fourier transforms Goertzel algorithm infinite impulse response (IIR) filter time amplifier (TA) time domain time register (TR) voltage-to-time converter (VTC)

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

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

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：