检索结果-内蒙古大学图书馆

Two-Stage Residual Projection Network for Image Bit-Depth Enhancement

IEEE ACCESS 2025年 13卷 31215-31227页

作者： Liu, Zepeng Wang, Yizong Sang, Yayuan Liu, Chao Tian, Jiya Xinjiang Inst Technol Sch Informat Engn Aksu 843100 Peoples R China

Low bit-depth (LBD) images produce stubborn false contour artifacts and make detailed information disappear, making bit-depth enhancement (BDE) a challenging task. Considering the mixture of structural distortions and real edges in LBD images, multi-scale features are crucial for the BDE tasks. However, existing CNN-based methods suffer from structural bottlenecks, which make it difficult to capture sufficient LBD features in a single-stage network. To overcome this issue, this paper proposes a two-stage residual projection network (TRPN) to explore the multi-scale features of BDE. An encoder-decoder structure based on alternating up and down sampling is proposed to learn wide context information in stage 1. In stage 2, a residual projection module based on dense connection is proposed to preserve the detailed texture as much as possible and avoid over-smoothing in non-flat regions, which is caused by alternating up and down sampling. To efficiently utilize multi-scale features, we introduce a supervised attention module that improves network ability by dynamically adjusting the attention weights within the model. Finally, extensive experiments demonstrate that our method achieves outstanding performance improvements both quantitatively and qualitatively, which illustrates its effectiveness.

关键词： Feature extraction Convolution Image color analysis Image reconstruction Distortion Deconvolution Training signal processing algorithms Colored noise Visualization Bit-depth enhancement multi-scale features encoder-decoder alternating up and down sampling residual projection

来源：评论

学校读者我要写书评

暂无评论

Light-Weight Low-Latency Reconfigurable CORDIC Architecture With a New Non-Power-of-2 Angle Set of Microrotations

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2025年

作者： Verma, Anu Das, Bishnu Prasad Indian Inst Technol IIT Roorkee Dept Elect & Commun Engn Roorkee 247667 Uttarakhand India

Trigonometric functions are widely used in various scientific and engineering applications, including digital signal processing. This article proposes a low-complexity low-latency reconfigurable CORDIC (COordinate Rotation Digital Computer) algorithm that computes trigonometric functions, which is based on a novel angle set of microrotations. The CORDIC algorithm is an iterative algorithm that reduces the performance due to the high latency of computation. The proposed pipelined scale-free CORDIC algorithm computes the functions in only four iterations with an optimized angle set of microrotations with high accuracy. It can be configured in two modes with different trajectories 1) rotation-mode;and 2) vectoring-mode for circular and hyperbolic trajectories. On-board FPGA implementation of the proposed architecture consumes 34.95% less register, 48.12% less occupied slices, 19.06% less LUTs, 66.51% less slice-latency product (SLP), 59.29% less LUT-latency product (LLP), and 71.23% less register-latency product (RLP) compared to the best existing state-of-the-art CORDIC architectures. Moreover, the latency of the proposed architecture is 72.34% less than the best of existing designs. Besides, the parasitic-extracted layout simulation results of the proposed design across different word lengths are reported in TSMC 65-nm CMOS technology for the validation of the proposed architecture.

关键词： Computer architecture Accuracy Hardware Trajectory Convergence Taylor series Pipelines Complexity theory Table lookup signal processing algorithms Coordinate rotation digital computer (CORDIC) reconfigurable CORDIC FPGA ASIC

来源：评论

学校读者我要写书评

暂无评论

A Reliable Offloaded processing GNSS Receiver for Low-Power and Low-Accuracy Scenarios

引用

IEEE SENSORS JOURNAL 2025年第7期25卷 11532-11544页

作者： Su, Yu Jin, Tian Ju, Yi Beihang Univ Sch Elect & Informat Engn Beijing 100083 Peoples R China

Under the energy consumption constraints of mobile IoT terminals, global navigation satellite system (GNSS)-based tracking devices encounter significant challenges. Offloaded processing can offer a viable solution for reducing the energy consumption of GNSS tracking devices. This approach reduces the complexity of signal processing and utilizes remote servers for positioning. The signal tracking stage in the terminal is computationally intensive, and forwarding large amounts of raw data to the processing server consumes much power. To overcome these challenges, an offloaded processing GNSS receiver based on coarse acquisition results is introduced. Additionally, to improve the robustness of the measurements and the reliability of positioning, a fault detection and exclusion (FDE) algorithm based on geometric consistency and factor subset combination is proposed. The vehicle experiments demonstrate that the proposed algorithm can effectively detect and exclude faulty reconstructed pseudorange measurements by using a small number of subsets and can achieve a horizontal positioning accuracy of 33.17 m with 10 ms snapshot data.

关键词： Global navigation satellite system Receivers signal processing algorithms Servers Sensors Satellites Accuracy Internet of Things Energy consumption Codes Factor subset fault detection and exclusion (FDE) geometric consistency global navigation satellite system (GNSS)-based tracking offloaded processing GNSS receiver

来源：评论

学校读者我要写书评

暂无评论

Online Federated Reproduced Gradient Descent With Time-Varying Global Optima

引用

IEEE TRANSACTIONS ON signal processing 2025年 73卷 1379-1393页

作者： Lin, Yifu Li, Wenling Song, Jia Li, Xiaoming Beihang Univ BUAA Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China Beihang Univ BUAA Sch Astronaut Beijing 100191 Peoples R China Shenzhen Univ Res Inst Smart Cities Sch Architecture & Urban Planning Shenzhen 518060 Peoples R China

This paper addresses an online federated learning problem, where the time drift in data distribution leads to time-varying global optima. To adapt to the drift, this paper designs a random Fourier features (RFF) model combined with Reproducing Kernel Hilbert Space (RKHS) theory to tracking the global gradient. Meanwhile, the model also can mitigate gradient variance from local data and gradient bias due to data heterogeneity. Based on this model, the paper further proposes an online federated reproduced gradient descent (OFedRGD) algorithm. The Wasserstein distance is then employed as a distribution metric to analyze the regret by OFedRGD, which is composed of cumulative distribution drifts and cumulative gradient error caused by stochasticity and heterogeneity. Additionally, a set of CLEAR-datasets, including two online learning tasks, are used to test the proposed algorithm. The results show that the proposed algorithm can effectively improve classification accuracy in the two tasks by 5% and 16%, respectively, and its performance is less adversely affected by the degree of data dispersion.

关键词： Federated learning Optimization Adaptation models Data models signal processing algorithms Training Stochastic processes Probability distribution Vectors Servers Online federated learning random fourier feature reproducing kernel hilbert space time drift, gradient variance data heterogeneity reproduced gradient

来源：评论

学校读者我要写书评

暂无评论

Solving Quadratic Systems With Full-Rank Matrices Using Sparse or Generative Priors

引用

IEEE TRANSACTIONS ON signal processing 2025年 73卷 477-492页

作者： Chen, Junren Ng, Michael K. Liu, Zhaoqiang Univ Hong Kong Dept Math Hong Kong 852 Peoples R China Hong Kong Baptist Univ Dept Math Hong Kong 852 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China

The problem of recovering a signal x is an element of R-n from a quadratic system{yi=x(T)A(ix), i=1,...,m} with full-rank matrices A(i) frequently arises in applications such a sun assigned distance geometry and sub-wavelength imaging. With i.i.d. standard Gaussian matrices A(i) , this paper addresses the high-dimensional case where m << n by incorporating prior knowledge of x. First, we consider a k-sparse x and introduce the thresholded Wirtinger flow (TWF) algorithm that does not require the sparsity level k. TWF comprises two steps: the spectral initialization that identifies a point sufficiently closetox (up to a sign flip) when m=O(k(2)logn),and the thresholded gradient descent which, when provided a good initialization, produces a sequence linearly converging to x with m=O(k log n) measurements. Second, we explore the generative prior, assuming that x lies in the range of an L-Lipschitz continuous generative model with k-dimensional inputs in an l(2)-ball of radius r. With an estimate correlated with the signal, we develop the projected gradient descent (PGD)algorithm that also comprises two steps: the projected power method that provides an initial vector with O(root k log(L)/m) l(2)-error given m=O( k log(Lnr))measurements, and the projected gradient descent that refines the l(2)-error to O(delta) at a geometric rate when m=O(k log Lrn/delta(2)). Experimental results corroborate our theoretical findings and show that: (i)our approach for the sparse case notably outperforms the existing provable algorithm sparse power factorization;(ii) leveraging the generative prior allows for precise image recovery in the MNIST dataset from a small number of quadratic measurements.

关键词： Sparse matrices Complexity theory signal processing algorithms Vectors Phase measurement Compressed sensing Standards Particle measurements Image segmentation Image reconstruction Generative prior projected gradient descent projected power method quadratic system sparse prior wirtinger flow

来源：评论

学校读者我要写书评

暂无评论

Low-Complexity Data-Driven Communication Neural Receivers

引用

IEEE ACCESS 2025年 13卷 9325-9334页

作者： Wu, Qingle Liang, Yuanhui Ng, Benjamin K. Lam, Chan-Tong Ma, Yan Sichuan Univ Sci & Engn Sch Automat & Informat Engn Zigong 643000 Peoples R China Macao Polytech Univ Fac Appl Sci Macau 999078 Peoples R China Artificial Intelligence Key Lab Sichuan Prov Yibin 644000 Peoples R China Beijing Univ Posts & Telecommun BUPT Network Informat Ctr Beijing 100876 Peoples R China

Communication receivers based on deep learning have become a research hotspot in recent years. However, the excessive computational complexity and storage complexity prevent it from being deployed on communication hardware with limited resources. In order to reduce the computational complexity and required storage resources of communication neural receivers based on deep learning, we propose to use candecomp parafac (CP), Tucker, tensor-train (TT) and tensor-ring (TR) decomposition respectively to compress the data-driven deep learning based communication neural receiver. Through compression, the storage resources required by the communication neural receiver are reduced by about half with bit error rate (BER) performance degradation of only 0.75dB to 1.3dB.

关键词： Receivers Tensors Decoding OFDM Hardware Deep learning Symbols signal processing algorithms Computer architecture Wireless communication Tensor-train decomposition tensor-ring decomposition computational complexity communication neural receiver storage complexity

来源：评论

学校读者我要写书评

暂无评论

Near-Field High-Speed User Sensing in Wideband mmWave Communications: algorithms and Bounds

引用

IEEE TRANSACTIONS ON signal processing 2025年 73卷 919-935页

作者： Miao, Hongxia Peng, Mugen Beijing Univ Posts & Telecommun Sch Informat & Commun Engn State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China

Integrated sensing and communications (ISAC) has been expected to be a key technique in the sixth-generation cellular networks. With the increase of carrier frequency (to millimeter-wave or Terahertz spectrum) and antenna array size (to extremely large-scale antenna) in wireless communications, the near-field area is enlarged and cannot be ignored. Accordingly, the channel model and its estimation algorithms are changed, which bring new chances in ISAC. However, the impact of both Doppler and spatial wideband effects, caused by high mobility and multicarriers, on sensing performance using communication signals is not well studied. In this study, these two effects are shown to be helpful in user sensing. First, the channel model is proposed for a high-speed moving user transmitting an orthogonal frequency division multiplex (OFDM) signal, where there are six unknown parameters. Then, the Cramer-Rao lower bounds (CRLB) for joint six parameter estimation is determined, where the impact of the near-field parameter and the velocity on the CRLB of positioning are discussed and quantified. Further, to compensate for the deficiency that the CRLB is tight only in high signal-to-noise-ratio (SNR) scenarios, we derive the Ziv-Zakai bound (ZZB) for positioning by exploiting the prior information on positioning parameters. Subsequently, a joint position and velocity parameter estimation algorithm is designed by first performing a discrete fractional Fourier transform on the received signal to obtain a coarse estimation and then refining it by Newton-based refinement. Numerical results coincide with our analysis.

关键词： OFDM Estimation signal processing algorithms Channel estimation Chirp Frequency estimation Training signal to noise ratio Sensors Matching pursuit algorithms Near-field ISAC high-speed moving CRLB ZZB

来源：评论

学校读者我要写书评

暂无评论

A Wideband Lateral Multibeam Tiling Synthetic Aperture Method for High-Speed Side-Scan Sonar

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Mao, Weibo Zhao, Dongdong Chen, Peng Liu, Jian Liang, Shihui Shen, Yi Guo, Xinxin Liang, Ronghua Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou 310023 Zhejiang Peoples R China Chinese Acad Sci Inst Deep Sea Sci & Engn Sanya 572000 Hainan Peoples R China

Side-scan sonar technology plays an important role in seabed topographic exploration and mapping. However, the mainstream matched filtering technique does not fully utilize the bandwidth and the distance matching is susceptible to the Doppler effect, which limits the imaging effect and towing speed. In addition, the synthetic aperture method of radar is difficult to be adapted to sonar due to the transmission characteristics of acoustic waves in water. To address these issues, we propose a lateral multi-beam tiling synthetic aperture algorithm framework for linear array side-scan sonar (LMBT-SAS). The core idea is to improve long-range information acquisition capabilities through beam focusing, and indirectly increase the azimuth pulse repetition rate to serve synthetic aperture processing to increase towing speed. To further improve image performance and towing speed, within this framework, we also proposed some specific technical means. Including short-time Fourier frequency domain beamforming with speed compensation, beam tiling with pseudo pulse repetition, distance-dependent beam weight allocation mechanism and two-stage migration correction. The simulation results and lake test data imaging results demonstrate the effectiveness of the proposed LMBT-SAS algorithm, with a performance of 250 meters of transverse scanning distance and 12 knots of towing speed at 400 KHz signal.

关键词： Synthetic aperture sonar Apertures signal processing algorithms Side-scan sonar Frequency-domain analysis Broadband communication Sonar applications Focusing Azimuth Array signal processing High-speed side-scan sonar multibeam synthetic aperture pseudo-pulse repetition beam tiling short-time Fourier beamforming

来源：评论

学校读者我要写书评

暂无评论

APG-Net: APG Optimization-Induced Multiscale Attention Network for MRI Reconstruction From Undersampled k-Space Measurements

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Gan, Hongping Zhao, Zitong Chen, Yunong Shan, Shanshan Shi, Baoshun Liu, Chunyi Northwestern Polytech Univ Sch Software Xian 710072 Peoples R China Wuhan Univ State Key Lab Informat Engn Surveying Mapping & Re Wuhan 430072 Peoples R China Soochow Univ Sch Radiol & Interdisciplinary Sci State Key Lab Radiat Med & Protect Suzhou 215123 Peoples R China Yanshan Univ Sch Informat Sci & Engn Qinhuangdao 066004 Peoples R China

Compressed sensing magnetic resonance imaging (CS-MRI) can quickly reconstruct magnetic resonance (MR) images from undersampled k-space measurements, thereby accelerating MRI reconstruction. However, existing CS-MRI methods suffer from insufficient information interaction and an inability to adequately capture image features during the iterative reconstruction process, resulting in the reconstructed images having room for improvement in detail. Inspired by the accelerated proximal gradient (APG) algorithm, we propose an APG optimization-induced deep multiscale attention network, called APG-Net, for accelerating MRI reconstruction from k-space measurements. APG-Net transforms the traditional APG algorithm into a learnable network structure while introducing efficient feature extraction modules to effectively capture the features of the k-space data, resulting in high-quality MR image reconstruction. Specifically, it unrolls the iterative steps of the APG algorithm into a cascade block of fixed reconstruction phases, which include the iterative unfolding module (IUM) and multiscale dual-attention block (MDAB). The proposed IUM enhances feature fusion by leveraging information interaction between iterative phases. Moreover, the customized MDAB is utilized to extract multiscale feature information from the k-space measurements while enhancing attention to spatial and channel-related features in both dimensions, effectively boosting feature extraction capability. Extensive experiments demonstrate that our proposed APG-Net achieves remarkable performance on MRI reconstruction tasks in contrast to state-of-the-art methods. Our code is available at APG-Net.

关键词： Image reconstruction Feature extraction Magnetic resonance imaging Iterative algorithms Data mining signal processing algorithms Reconstruction algorithms Convergence Training Optimization Accelerated proximal gradient (APG) compressed sensing (CS) deep learning (DL) magnetic resonance (MR) imaging undersampled measurements

来源：评论

学校读者我要写书评

暂无评论

Robust Airborne Radar Clutter Suppression Algorithm via Deep Neural Networks Under Small-Sample Conditions

引用

IEEE SENSORS JOURNAL 2025年第7期25卷 11587-11600页

作者： Huang, Weijun Wang, Tong Cui, Weichen Xidian Univ Natl Lab Radar Signal Proc Xian 710071 Peoples R China Beijing Aerosp Automat Control Inst Beijing 100854 Peoples R China Natl Key Lab Sci & Technol Aerosp Intelligence Con Beijing 100854 Peoples R China

Space-time adaptive processing (STAP) is a powerful technique for clutter suppression in airborne radar systems. However, in practical applications, STAP performance is often compromised by the limited availability of independent and identically distributed (i.i.d.) samples, which restricts its clutter suppression capabilities. Inspired by compressed sensing, researchers have extensively investigated sparse recovery-based STAP (SR-STAP) algorithms, which can achieve near-optimal performance under ideal conditions. Yet, these algorithms experience notable performance degradation in the presence of spatial and temporal errors. To address this issue, we propose a deep neural network framework for clutter suppression, cascading a gridless sparse recovery network (GLSRNet) with a generative adversarial network (GAN), ensuring accurate clutter covariance matrix estimation under small-sample conditions with errors. During GAN training, we observed that the traditional binary cross-entropy (BCE) loss function led to significant oscillations in the training loss, impeding effective convergence. To resolve this, we design a new loss function that achieves stable convergence. Extensive experiments validate the effectiveness of the proposed algorithm in clutter suppression.

关键词： Clutter Training Vectors Generative adversarial networks signal processing algorithms Generators Airborne radar Minimization Accuracy Radar clutter Clutter suppression deep unfolding generative adversarial network (GAN) space-time adaptive processing (STAP)

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：