检索结果-内蒙古大学图书馆

Off-axis propagation algorithm for partial reconstruction of wide-angle computer-generated holograms

OPTICS EXPRESS 2022年第18期30卷 31898-31912页

作者： Martinez-Carranza, Juan Kozacki, Tomasz Warsaw Univ Technol Inst Micromech 8 Sw A Boboli St PL-02525 Warsaw Poland

A method for reconstruction of partial off-axis areas of arbitrary size for wide-angle viewing computer generated holograms is presented. Proposed method employs paraxial spherical phase factors and modified propagation kernels. This significantly reduces the numerical space-bandwidth product needed for off-axis wave field calculations, which makes it an efficient propagation method. As a result, propagated wavefields of high-off axis and large size output windows can be obtained. To that end, a phase-space analysis for obtaining the proper condition for implementing spatial-frequency zero-padding for accurate wavefield propagation is carried out. Hence, suppression of aliased components and high spatial resolution is possible. Nevertheless, proposed algorithm faces a computer memory bottleneck when reconstructing very large off-axis areas due to too extensive zero-padding needed. To solve this problem, a memory optimized tiling implementation is introduced. Utility of the developed propagation tools are proven by partial reconstructions from a high-resolution hologram. The size of the reconstructions areas ranges from 100 x 100 mm(2) up to 550 x 550 mm(2). (C) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Fourier transforms Holographic displays Propagation methods reconstruction algorithms Spatial resolution Wave propagation

来源：评论

学校读者我要写书评

暂无评论

A Multiple-Gain-Reconfigurable-Rectifier-Based IPT System for Battery Multistage Constant-Current High-Efficiency Wireless Charging

引用

IEEE TRANSACTIONS ON POWER ELECTRONICS 2024年第1期39卷 1853-1869页

作者： Xu, Yefei Li, Yong Chen, Yang Zhou, Wei Mai, Ruikun He, Zhengyou Sichuan Univ Sch Elect Engn Chengdu 610065 Peoples R China Southwest Jiaotong Univ Sch Elect Engn Chengdu 610031 Peoples R China Southwest Jiaotong Univ Key Lab Magnet Suspens Technol & Maglev Vehicle Minist Educ Chengdu 610031 Peoples R China

Inductive power transfer (IPT) technology is widely used for battery charging, whereas trickle charging is necessary for precharging a deeply discharged battery to prolong its lifetime. However, the trickle charging current is much less than the rated charging current. This leads to a challenge for IPT systems to achieve trickle charging and high transmission efficiency as well. In this article, a multiple-gain-reconfigurable-rectifier (MGRR)-based IPT system is proposed for the battery multiple stage constant-current (MSCC) high-efficiency wireless charging, especially for the deeply discharged battery MSCC high-efficiency wireless charging. With the MGRR, the IPT system can theoretically achieve 1.0, 0.5, 0.25, and 0.125 times of the rated output. Thus, trickle charging can be realized without a complicated control scheme. Calculation analysis shows that the proposed IPT system can simultaneously satisfy the battery charging requirements and achieve a near impedance matching for the high transmission efficiency. Finally, a 164-W prototype is built to validate the performance of the system. Experimental results show that the MGRR-based IPT system can effectively charge a deeply discharged battery with a high transmission efficiency as the efficiency in the entire charging process ranges from 89.4% to 93.7%.

关键词： Batteries Topology Rectifiers Inverters Zero voltage switching reconstruction algorithms Voltage Battery efficiency inductive power transfer (IPT) multiple gain reconfigurable rectifiers (MGRRs) multiple stage constant current (MSCC)

来源：评论

学校读者我要写书评

暂无评论

Computationally Efficient Implicit Training Strategy for Unrolled Networks (IMUNNE): A Preliminary Analysis Using Accelerated Real-Time Cardiac Cine MRI

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2025年第1期72卷 187-197页

作者： Iakovlev, Nikolay Schiffers, Florian A. Tapia, Santiago L. Shen, Daming Hong, Kyungpyo Markl, Michael Lee, Daniel C. Katsaggelos, Aggelos K. Kim, Daniel Northwestern Univ Feinberg Sch Med Dept Radiol Chicago IL 60611 USA Northwestern Univ Dept Comp Sci Chicago IL USA Northwestern Univ Dept Elect & Comp Engn Chicago IL USA GE Healthcare Inc Chicago IL USA Northwestern Univ Feinberg Sch Med Dept Med Chicago IL USA

Objective: Highly-undersampled, dynamic MRI reconstruction, particularly in multi-coil scenarios, is a challenging inverse problem. Unrolled networks achieve state-of-the-art performance in MRI reconstruction but suffer from long training times and extensive GPU memory cost. Methods: In this work, we propose a novel training strategy for IMplicit UNrolled NEtworks (IMUNNE) for highly-undersampled, multi-coil dynamic MRI reconstruction. It formulates the MRI reconstruction problem as an implicit fixed-point equation and leverages gradient approximation for backpropagation, enabling training of deep architectures with fixed memory cost. This study represents the first application of implicit network theory in the context of real-time cine MRI. The proposed method is evaluated using a prospectively undersampled, real-time cine dataset using radial k-space sampling, comprising balanced steady-state free precession (b-SSFP) readouts. Experiments include a hyperparameter search, head-to-head comparisons with a complex U-Net (CU-Net) and an alternating unrolled network (Alt-UN), and an analysis of robustness under noise perturbations;peak signal-to-noise ratio, structural similarity index, normalized root mean-square error, spatio-temporal entropic difference, and a blur metric were used. Results: IMUNNE produced significantly and slightly better image quality compared to CU-Net and Alt-UN, respectively. Compared with Alt-UN, IMUNNE significantly reduced training and inference times, making it a promising approach for highly-accelerated, multi-coil real-time cine MRI reconstruction. Conclusion: IMUNNE strategy successfully applies unrolled networks to image reconstruction of highly-accelerated, real-time radial cine MRI. Significance: Implicit training enables rapid, high-quality, and cost-effective CMR exams by reducing training and inference times and lowering memory cost associated with advanced reconstruction methods.

关键词： Magnetic resonance imaging Image reconstruction Real-time systems Training Iterative methods Biomedical imaging reconstruction algorithms Compressed sensing deep learning image reconstruction implicit network unrolled network

来源：评论

学校读者我要写书评

暂无评论

Blind Recognition of 5G LDPC Codes Over a Candidate Set

引用

IEEE COMMUNICATIONS LETTERS 2024年第4期28卷 744-748页

作者： Wang, Yuan Che, Shuling Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China

Blind recognition of channel codes is an important technology in Adaptive Modulation and Coding (AMC) systems. Shortening and puncturing have been adopted to achieve flexible code rates and code lengths for different application scenarios in 5G Low Density Parity Check (LDPC) codes, which leads to a challenge for their blind recognition. In this letter, a novel Extended Exponent Matrix (EEM) reconstruction method is proposed to find complete parity checks for punctured codes, which offers the feasibility of Log-Likelihood Ratio (LLR) based blind recognition of punctured linear block codes over a candidate set. Simultaneously, a lifting size parallel operation via the quasi-cyclic property of 5G LDPC codes and limited weights of parity checks are employed in our proposed algorithm to efficiently reduce the reconstruction complexity. At last, simulation results are presented to show the effectiveness of our reconstruction algorithm.

关键词： Parity check codes 5G mobile communication Support vector machines Phase change materials Encoding reconstruction algorithms Complexity theory Blind recognition LDPC codes punctured codes shift values reconstruction algorithm

来源：评论

学校读者我要写书评

暂无评论

Recognition of UAVs in Infrared Images Based on YOLOv8

引用

IEEE ACCESS 2025年 13卷 1534-1545页

作者： Zhou, Gang Liu, Xiuqi Bi, Hongliang Naval Univ Engn Sch Elect Engn Wuhan 430033 Hubei Peoples R China Wuhan Univ Sch Elect Engn Wuhan 430072 Hubei Peoples R China Wuhan Univ Sch Comp Sci Wuhan 430072 Hubei Peoples R China China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221008 Jiangsu Peoples R China

With the advancement of Unmanned Aerial Vehicle (UAV) technology, there has been a notable increase in the utilization of UAVs by criminals for engaging in illegal activities, which poses significant threats to critical infrastructure and national security. Previous studies have predominantly relied on visible image recognition, which is vulnerable to variations in lighting conditions. Additionally, the performance of detection models is often hindered by the poor quality of images capturing UAV small targets. In contrast to visible light images, infrared images can capture the heat emitted by UAVs, rendering them less susceptible to fluctuations in lighting. To address the necessity for micro UAV detection in complex environments, this paper proposes an infrared image UAV detection method that employs super-resolution reconstruction through the Super-Resolution Convolutional Neural Network (SRCNN) and YOLOv8. Initially, a convolutional neural network is utilized to enhance the resolution and clarity of the infrared images. Subsequently, the YOLOv8 target detection model is applied to identify and detect UAVs. The results indicate that the average accuracy in detecting UAVs is 93.1%, which proves that it has excellent detection performance.

关键词： Autonomous aerial vehicles Accuracy Superresolution Feature extraction YOLO Image reconstruction Convolution Signal resolution reconstruction algorithms Data models UAV infrared image SRCNN YOLOv8 object detection super-resolution image recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Unfolding Basis Pursuit: Improving Sparse Channel reconstruction via Data-Driven Measurement Matrices

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2022年第10期21卷 8090-8105页

作者： Wu, Pengxia Cheng, Julian Univ British Columbia Sch Engn Kelowna BC V1X 1V7 Canada

For massive multiple-input multiple-output systems operating in frequency-division duplex mode, downlink channel state information (CSI) acquisition will incur large overhead. This overhead is substantially reduced when sparse channel estimation techniques are employed, owing to the channel sparsity in the angular domain. When a sparse channel estimation method is implemented, the measurement matrix, which is related to the pilot matrix, is essential to the channel estimation performance. Existing sparse channel estimation schemes widely adopt random measurement matrices, which have been criticized for their suboptimal reconstruction performance. This paper proposes novel data-driven solutions to design the measurement matrix. Model-based autoencoders are customized to optimize the measurement matrix by unfolding the classical basis pursuit algorithm. The obtained data-driven measurement matrices are applied to existing sparse reconstruction algorithms, leading to flexible hybrid data-driven implementations for sparse channel estimation. Numerical results show that the proposed data-driven measurement matrices can achieve more accurate reconstructions and use fewer measurements than the existing random matrices, thereby leading to a higher achievable rate for CSI acquisition. Moreover, compared with existing pure deep learning-based sparse reconstruction methods, the proposed hybrid data-driven scheme, which uses the novel data-driven measurement matrices with conventional sparse reconstruction algorithms, can achieve higher reconstruction accuracy.

关键词： Sparse matrices Channel estimation reconstruction algorithms Downlink Massive MIMO Antenna measurements Wireless communication Compressive sensing channel state information deep learning sparse reconstruction

来源：评论

学校读者我要写书评

暂无评论

Learn Stable MRI Under-Sampling Pattern With Decoupled Sampling Preference

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING

引用

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2024年 10卷 246-260页

作者： Sun, Haoze Tian, Chenyu Xiao, Jing Yang, Yujiu Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Shenzhen 518055 Peoples R China Ping An Technol Co Ltd Shenzhen 518126 Peoples R China

Accelerating the scanning time of magnetic resonance imaging (MRI) and improving the imaging quality is critical to the patient experience in clinical applications. In accelerated MRI, MR data can be under-sampled in the raw k-space, and the available measurements are used for image reconstruction. Many recent studies have shown that the quality of image reconstruction depends largely on the MRI under-sampling pattern. Our study shows that the way to binarize sampling masks in previous deep-learning-based under-sampling patterns leads to unstable reconstruction results when cooperating with data-driven reconstruction methods. Therefore, we design a stable under-sampling pattern learning strategy, which straightly optimizes the sampling mask at fixed k-space locations. In addition, our method designs the sampling pattern from both reconstruction contribution and reconstruction capacity perspectives, which are not considered in previous approaches. We decouple the under-sampling preferences and form a new paradigm for pattern optimization. To accelerate the joint learning process, we utilize prior knowledge of the MRI k-space energy distribution to guide the optimization of under-sampling patterns in our proposed paradigm. Experimental results demonstrate that our proposed under-sampling pattern learning strategy can yield better reconstruction quality than previous methods and facilitate the training process, irrespective of the task being single-coil MRI reconstruction or parallel MRI reconstruction.

关键词： Image reconstruction Magnetic resonance imaging reconstruction algorithms Compressed sensing Training Probability density function Optimization Accelerated MRI sampling pattern design deep learning compressed sensing

来源：评论

学校读者我要写书评

暂无评论

A Physics-Assisted Deep-Learning Scheme Based on Globally Perceptive Modules for Electromagnetic Inverse Scattering Problems

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Du, Changlin Pan, Jin Yang, Deqiang Hu, Jun Nie, Zaiping Chen, Yongpin Univ Elect Sci & Technol China Sch Elect Sci & Engn Chengdu 611731 Peoples R China

The multiple scattering effect is commonly present in electromagnetic (EM) scattering and can serve as a priori information to guide the solution of inverse scattering problems (ISPs). As depicted by the Green's function, the multiple scattering effect exhibits both global and local features, i.e., the interaction between subscatterers is in principle global but the coupling strength is usually large in the neighboring region and decays with distance. For solving ISPs, the convolutional layer (CL) has been proven to be highly effective as a fundamental building block in learning-based solvers. Through supervised learning, CL-based networks can predict the refined result from the pre-solution of EM parameters. However, due to the limitation of local perception capability, CL can only model the local feature of the multiple scattering effect. To remedy this, this article proposes a globally perceptive (GP) module that cascades a global self-attention layer (GSAL) and a CL to capture both global interaction and local emphasis. To show the effectiveness of the GP module, a deep-learning scheme with global perception (DLSGP) is constructed using a U-shape structure, where the pre-solution is provided by the backpropagation (BP) or domain current (DC) method. Validation results using cross-set data, noisy data, and measured data demonstrate the high accuracy, strong generalization ability, and robustness of the proposed module. The study on the global perception ability further confirms that the proposed module contains more information on the multiple scattering effect. Since this effect is common in ISPs, this fundamental module can be applied to other learning-based solvers.

关键词： Scattering Neural networks Learning systems Accuracy Vectors Iterative methods Inverse problems Electromagnetic scattering Robustness reconstruction algorithms Deep learning global self-attention globally perceptive (GP) module inverse scattering problems (ISPs) multiple scattering effect

来源：评论

学校读者我要写书评

暂无评论

Hybrid Domain Enhancement Network for Ultraclean Pure Shift Spectroscopy With Fast Acquisition

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Shen, Jia Huang, Mingkai Chen, Yida Wu, Liubin Li, Hong Yang, Yu Chen, Zhong Xiamen Univ Dept Elect Sci Xiamen 361005 Peoples R China Univ Hong Kong Dept Elect & Elect Engn Hong Kong Peoples R China Jimei Univ Sch Ocean Informat Engn Xiamen 361021 Peoples R China

Pure shift technique can greatly improve the resolution of proton spectra compared to conventional nuclear magnetic resonance (NMR) spectroscopy but at the cost of longer acquisition time. To accelerate data acquisition in pure shift experiments, nonuniform sampling (NUS) is usually incorporated along with advanced data processing methods to reconstruct the spectrum. While some deep learning (DL) approaches have been proposed for this purpose, their performance declines when dealing with data under varying experimental conditions, primarily because they solely rely on frequency-domain information. To overcome this limitation, we develop a novel hybrid domain enhancement (HDE) network that combines time- and frequency-domain signals as input. We introduced an adaptive-domain transform unit (ADTU) to extract time-domain features that capture segmental correlations while retaining some temporal sequential information. Our experiments demonstrate that the proposed network effectively suppresses chunking sidebands and undersampling artifacts, showing exceptional robustness in complex scenarios, particularly under phase distortion. On real experimental data, it achieves a 5%-33% higher precision than state-of-the-art (SOTA) methods, indicating fewer artifacts in the reconstructed spectrum. This approach holds great potential for broader application in NMR spectroscopy, offering clearer and more accurate spectral interpretation.

关键词： Nuclear magnetic resonance Time-domain analysis Image reconstruction Couplings Amplitude modulation Spectroscopy Phase distortion Discrete Fourier transforms Time-frequency analysis reconstruction algorithms Chunking sideband neural network nonuniform sampling (NUS) pure shift signal reconstruction

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Channel Distillation Network for Image Compressive Sensing

引用

IEEE ACCESS 2025年 13卷 9524-9537页

作者： Zhang, Tianyu Ye, Kuntao Zhang, Yue Lu, Rui Jiangxi Univ Sci & Technol Sch Sci Ganzhou 341000 Peoples R China State Grid Xinyu Power Supply Co Elect Power Commun Dept Xinyu 338000 Peoples R China

Recently, convolutional neural networks (CNNs) have demonstrated striking success in computer vision tasks. Methods based on CNNs for image compressive sensing (CS) have also gained prominence. However, existing methods tend to increase the depth of the network in feature space for better reconstruction quality, neglecting the hierarchical representation of intermediate features in pixel space. In order to coordinate the feature space and pixel space to complete the deep reconstruction of images, and further improve the reconstruction performance of current CS methods, we propose a multi-scale channel distillation network (MSCDN). This network first obtains images of multiple scales using a scale-space image decomposition method at the sampling stage, followed by sampling these decomposed images through a convolutional operation. In this way, multi-scale information in the compressed domain is aggregated. During the reconstruction phase, a low-frequency information recovery network generates a preliminary image, whereas a high-frequency feature aggregation network refines the image further. Specifically, we design a dual-branch deep reconstruction architecture with channel distillation residual block (CDRB) as the core component. One branch extracts features gradually by cascading multiple CDRB modules, thereby supplementing the initial reconstructed image with a large amount of high-frequency content in feature space. The other branch takes the initial reconstructed image as input and sequentially fuses the intermediate feature outputs by CDRBs to increase the local details of the image in pixel space. Combining outputs from both branches, we achieve an optimal reconstructed image. Extensive experimental results on four benchmark datasets demonstrate that MSCDN surpasses state-of-the-art CS methods not only in reconstruction accuracy but also in perceptual visual quality.

关键词： Image reconstruction Feature extraction Convolution reconstruction algorithms Image coding Computational complexity Compressed sensing Training Optimization Matched filters Convolutional neural networks compressive sensing intermediate feature multi-scale image reconstruction

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：