检索结果-内蒙古大学图书馆

Adaptive Superpixel-Guided Non-Homogeneous Image Dehazing

IEEE signal processing LETTERS 2025年 32卷 591-595页

作者： Zhang, Hao Lu, Ping Qi, Te Xu, Yan Zeng, Tieyong Chinese Univ Hong Kong Dept Math Hong Kong Peoples R China ZTE Corp Shenzhen 518057 Peoples R China

Image dehazing is regarded as a fundamental image processing task with a major impact on higher-level imaging tasks. Many existing haze removal methods are designed for homogeneous haze, but in real-world cases, the haze is normally non-homogeneous. Superpixels, which segment an image into a set of closely spaced regions, can be employed in real-world scenarios to deal with non-homogeneous haze. In our paper, an adaptive non-homogeneous image dehazing approach that utilizes the superpixel-guided algorithm is designed to segment different hazy regions. Considering that both ambient light and transmission map estimation have a significant impact on the results, our research focuses on the development of a variational dehazing model that takes into account non-uniform ambient light and non-uniform transmission maps to address varying levels of haze. A series of numerical results illustrate the superiority and efficacy of our method.

关键词： Scattering signal processing algorithms Mathematical models Atmospheric modeling Image segmentation Optimization Feature extraction Numerical models Lighting Estimation Image dehazing non-homogeneous superpixel algorithm

来源：评论

学校读者我要写书评

暂无评论

MPHR: A Robust Algorithm for Estimating Nodal Head in Water Networks

引用

IEEE signal processing LETTERS 2025年 32卷 856-860页

作者： Maggang, Amin A. Tay, David B. Gong, Jinzhe Josey, Brendan M. Deakin Univ Sch IT Geelong Vic 3220 Australia Deakin Univ Sch Engn Geelong Vic 3220 Australia

The monitoring of the pressure, in terms of nodal head values, is an important task in water distribution networks, to ascertain the integrity of the components, e.g. pipes. The placement of sensors at desired locations, in realistic situations, is a challenging problem due to various practical constraints. In practice, nodal heads are estimated at locations with no sensors. In this work, we propose an algorithm, termed mean percolation head reconstruction (MPHR), for estimating the nodal heads. The iterative algorithm is inspired by concepts from graph signal processing (GSP), and consists of two stages. The first stage is equivalent to the percolation of known values across the network, and the second stage performs some form of constrained consensus computations. The algorithm is robust against uncertainty in the network parameters and suboptimal placement of sensors. Extensive simulations have demonstrated the superiority of MPHR compared to other proposed reconstruction algorithms.

关键词： signal processing algorithms Sensors Magnetic heads Pressure sensors Head Distribution networks Vectors Uncertainty Training signal processing Graph signal processing (GSP) graph signal reconstruction nodal head estimation water distribution network

来源：评论

学校读者我要写书评

暂无评论

Windowed Quantum Phase Estimation: signal processing Approach to a Quantum Algorithm

Windowed Quantum Phase Estimation: Signal Processing Approac...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Xue Wen Samsung Research China Beijing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Quantum phase estimation (QPE) is a key ingredient to some of the most important results of quantum computing. In this paper we examine the QPE algorithm through the looking glass of signal processing. This perspective helps to reveal a relation between the distribution of quantum phase estimates and the shape of the discrete Fourier transform (DFT) of a pure complex sinusoid. Guided by spectral shaping theory, we design a class of quantum circuits that are the quantum equivalents to classical windowing operators, for a family of window functions that have compact support in the DFT. These circuits have complexity linear in the number of target qubits, strictly lower than QPE itself. Using these circuits we are able to reshape QPE's performance characteristics. In particular, the asymptotic marginal cost for 2x reduction in fail rate (2x improvement in reliability) is reduced from one qubit to 1/3 qubit or lower, which can help reduce the qubit budget for a preset accuracy-reliability target, especially in high-reliability scenarios. This makes a demonstration of the value of signal processing principles in designing quantum algorithms.

关键词： Quantum algorithm Shape Qubit Discrete Fourier transforms Phase estimation signal processing algorithms Quantum mechanics signal processing Windows Speech processing

来源：评论

学校读者我要写书评

暂无评论

Fitting Multiple Machine Learning Models With Performance Based Clustering

引用

IEEE signal processing LETTERS 2025年 32卷 816-820页

作者： Lorasdagi, Mehmet E. Koc, Ahmet B. Koc, Ali T. Kozat, Suleyman S. Bilkent Univ Dept Elect & Elect Engn TR-06800 Ankara Turkiye

Traditional machine learning approaches assume that data comes from a single generating mechanism, which may not hold for most real life data. In these cases, the single mechanism assumption can result in suboptimal performance. We introduce a clustering framework that eliminates this assumption by grouping the data according to the relations between the features and the target values, and we obtain multiple separate models to learn different parts of the data. We further extend our framework to applications having streaming data where we produce outcomes using an ensemble of models. For this, the ensemble weights are updated based on the incoming data batches. We demonstrate the performance of our approach over the widely-studied real life datasets, showing significant improvements over the traditional single-model approaches.

关键词： Data models Clustering algorithms Vectors signal processing algorithms Wind turbines Training Predictive models Data mining Convergence Wind speed Clustering expectation-maximization streaming data ensemble methods

来源：评论

学校读者我要写书评

暂无评论

Switching Games for Image Compression

引用

IEEE signal processing LETTERS 2025年 32卷 1016-1020页

作者： Huhtanen, Marko Univ Oulu Fac Informat Technol & Elect Engn Oulu 090570 Finland

To compress an image, a technique based on optimal scalings with diagonal matrices is described. To start the process, an initial image of high compression ratio is required. Such an image can be produced, for example, with the 2D FFT or 2D DCT of the original image. Principal component analysis is a special case of this compression technique where the initial image is extremely rough, consisting of the first 2D Fourier basis function only. This initial image is then optimally orthogonalized and expanded by iteratively applying diagonal matrices from the left and right to attain double orthogonality. The process can be viewed as a continuous version of Berlekamp's switching game.

关键词： Image coding Switches Principal component analysis Discrete cosine transforms Games Eigenvalues and eigenfunctions Approximation algorithms Solids signal processing algorithms Matrix decomposition Lossy compression double orthogonality principal component analysis 2D FFT 2D DCT

来源：评论

学校读者我要写书评

暂无评论

Stochastic Analysis of FxLMS Algorithm for Feedback Active Noise Control

引用

IEEE signal processing LETTERS 2025年 32卷 416-420页

作者： Wang, Cong Wu, Ming Zhou, Shuang Yang, Jun Chinese Acad Sci Inst Acoust Key Lab Noise & Vibrat Res Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China

Feedback active noise control (ANC) systems are effective in reducing predictable noise, e.g. periodic, narrowband and colored noise. There are still few studies on the theoretical analysis of feedback ANC systems, and are limited to idealized signals such as sinusoidal or Gaussian signals. This paper presents the stochastic analysis of a feedback ANC system based on the filtered-x least mean square (FxLMS) algorithm, which is not relying on a specific noise model and perfect secondary path. The equations for the mean and mean-square convergence behavior are derived. Extensive simulations of sinusoidal, band-limited white noise, and hybrid signals illustrate the accuracy of the analysis.

关键词： Noise Vectors Mathematical models Convergence Delays Adaptive filters Stochastic processes signal processing algorithms Feedforward systems White noise Feedback active noise control (ANC) FxLMS steady-state and transient behavior stochastic analysis

来源：评论

学校读者我要写书评

暂无评论

Distributed Precoder Based on Weighted MMSE With Low Complexity for Massive MIMO Systems

引用

IEEE COMMUNICATIONS LETTERS 2025年第3期29卷 482-486页

作者： Zhou, Ningxin Wang, Zheng Ma, Cong Huang, Yongming Shi, Qingjiang Southeast Univ Sch Informat Sci & Engn Nanjing 210096 Peoples R China ZTE Corp Shenzhen 518057 Peoples R China Tongji Univ Sch Software Engn Shanghai 201804 Peoples R China

The weighted sum mean squared error minimization (WMMSE) algorithm has gained widespread adoption owing to its superior performance. In this letter, we propose a novel low-complexity distributed WMMSE (LCD-WMMSE) algorithm, which is implemented over a decentralized architecture based on ring topology. Although each distributed unit (DU) in LCD-WMMSE works only with the local channel state information (CSI), LCD-WMMSE algorithm is still able to approach the performance of traditional WMMSE. Moreover, we show that LCD-WMMSE is also scalable since its required interconnection bandwidth is independent of the number of transmitter antennas, making it promising to various scenarios of massive MIMO. Simulation results validate that the proposed LCD-WMMSE algorithm not only achieves the low complexity cost in a distributed manner but also exhibits negligible performance loss.

关键词： Precoding signal processing algorithms Massive MIMO Computer architecture Vectors Topology Downlink Interference Distributed databases Antenna arrays Distributed precoding massive MIMO decentralized architecture maximization sum-rate WMMSE

来源：评论

学校读者我要写书评

暂无评论

Distributed Blind Source Separation Based on FastICA

引用

IEEE signal processing LETTERS 2025年 32卷 881-885页

作者： Musluoglu, Cem Ates Bertrand, Alexander Katholieke Univ Leuven Stadius Ctr Dynam Syst Dept Elect Engn ESAT Signal Proc & Data Analyt B-3001 Leuven Belgium Leuven AI KU Leuven Inst AI B-3001 Leuven Belgium

With the emergence of wireless sensor networks (WSNs), many traditional signal processing tasks are required to be computed in a distributed fashion, without transmissions of the raw data to a centralized processing unit, due to the limited energy and bandwidth resources available to the sensors. In this paper, we propose a distributed independent component analysis (ICA) algorithm, which aims at identifying the original signal sources based on observations of their mixtures measured at various sensor nodes. One of the most commonly used ICA algorithms is known as FastICA, which requires a spatial pre-whitening operation in the first step of the algorithm. Such a pre-whitening across all nodes of a WSN is impossible in a bandwidth-constrained distributed setting as it requires to correlate each channel with each other channel in the WSN. We show that an explicit network-wide pre-whitening step can be circumvented by leveraging the properties of the so-called Distributed Adaptive signal Fusion (DASF) framework. Despite the lack of such a network-wide pre-whitening, we can still obtain the $Q$ least Gaussian independent components of the centralized ICA solution, where $Q$ scales linearly with the required communication load.

关键词： signal processing algorithms Wireless sensor networks Sensors Distributed databases Europe Artificial intelligence Sensor fusion Optimization Indexes Fitting Distributed optimization distributed spatial filtering independent component analysis

来源：评论

学校读者我要写书评

暂无评论

XSNet: A Lightweight X-Ray Security Image Segmentation Model Combining State-Space Models and Convolutional Neural Networks

引用

IEEE signal processing LETTERS 2025年 32卷 1351-1355页

作者： Jia, Weichao Liu, Wei Zhang, Changsheng Fu, Jian Liu, Qiong Beijing Informat Sci & Technol Univ Beijing 100192 Peoples R China Beihang Univ Ningbo Innovat Res Inst Ningbo 315800 Peoples R China Beijing Univ Aeronaut & Astronaut Beijing 100191 Peoples R China

In this letter, we propose a novel lightweight X-ray image contraband segmentation network, XSNet, which integrates State Space Models (SSM) with Convolutional Neural Networks (CNNs) to achieve a significant trade-off between segmentation accuracy and lightweight design for computer-aided X-ray security check. The model is built based on the encoder-decoder framework. Specifically, we design an Multi-scale Convolution Fusion (MCF) block for multi-scale information extraction and a Dual-branch State Space Model (DSSM) block to relieve the bias caused by the imbalance of single branch structure in feature extraction and maintain the capabilities of SSM in modeling long range pixel dependencies. In addition, we present two versions of the model in two different sizes called XSNet-s and XSNet-l respectively. The quantitative and qualitative evaluations on the public PIDray and PIXray datasets both show the superiority of two models in terms of mean Intersection over Union (mIoU) and FLOPs.

关键词： Computational modeling Image segmentation Feature extraction X-ray imaging Security Training Decoding Accuracy Data mining signal processing algorithms Contraband segmentation state space models X-ray images deep learning

来源：评论

学校读者我要写书评

暂无评论

Robust Multitask Diffusion Bias Compensation M-Estimate algorithms for Distributed Adaptive Learning With Noisy Input

引用

IEEE signal processing LETTERS 2025年 32卷 1146-1150页

作者： Peng, Senran Jia, Lijuan Yang, Zi-Jiang Tao, Ran Wang, Yue Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Ibaraki Univ Coll Engn Dept Mech Syst Engn Ibaraki 3168511 Japan

This letter studies the issue of robust multitask distributed estimation under the error-in-variable (EIV) model where input noise and output impulsive noise are considered. In such cases, existing distributed algorithms suffer from severe performance degradation. To tackle this problem, a robust multitask diffusion bias-compensated least mean M-estimate (R-MD-BCLMM) is proposed. We adopt a new real-time input noise variance estimation method which utilizes piecewise linearity of the modified Huber function to resist input noises. To further improve network information exchange capability and estimation performance, a robust spatial average combination based multitask adaptive clustering strategy is proposed. Finally, simulations demonstrate that the proposed R-MD-BCLMM algorithm outperforms some state-of-the-art distributed algorithms.

关键词： Noise Estimation signal processing algorithms Clustering algorithms Noise measurement Vectors Real-time systems Cost function Adaptation models Modeling Multitask networks robust M-estimate bias compensation spatial average combination

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：