检索结果-内蒙古大学图书馆

Deep Learning for Compressed Sensing-Based Blade Vibration reconstruction From Sub-Sampled Tip-Timing Signals

IEEE ACCESS 2023年 11卷 38251-38262页

作者： Chen, Zhongsheng Sheng, Hao Liao, Lianying Liu, Chengwu Xiong, Yeping Changzhou Inst Technol Coll Automot Engn Changzhou 213032 Peoples R China Hunan Univ Technol Coll Elect & Informat Engn Zhuzhou 412007 Peoples R China Univ Southampton Fac Engn & Phys Sci Southampton SO16 7QF England

Blade tip-timing (BTT) signals are always seriously under sampled, so reconstruction is much needed for vibration analysis. Blade vibration responses are sparse in order domain and classical compressed sensing (CS) algorithms are difficult to reconstruct vibration orders due to lack of prior sparse information under variable speeds. In order to address this issue, this paper introduces deep learning (DL) into BTT vibration reconstruction and proposes an end-to-end deep compressed sensing (DCS) method. Firstly, a multi-coset BTT measurement model is built under variable speeds and the DCS model is derived in order domain, where a specific convolutional neural network (CNN) is designed. Next, a Simulink model is built to generate training and testing samples. The simulation results show that the convolution layer with the rectified linear unit (ReLU) layer placed after the batch normalization (BN) layer can improve the reconstruction performance and the proposed method has better reconstruction accuracy and efficiency than classical CS algorithms. Finally, experiments are done and the results demonstrate that blade vibration orders can be recovered accurately by the proposed method, which will provide a novel way of BTT signal analysis.

关键词： Vibrations Blades Probes Vibration measurement Image reconstruction reconstruction algorithms Monitoring Blade tip-timing deep compressed sensing multi-coset angular sampling unknown multi-band vibrations vibration reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Total-Body Ultralow-Dose PET reconstruction Method via Image Space Shuffle U-Net and Body Sampling

引用

IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2024年第4期8卷 357-365页

作者： Chen, Gaoyu Liu, Sheng Ding, Wenxiang Lv, Li Zhao, Chen Weng, Fenghua Long, Yong Zan, Yunlong Huang, Qiu Shanghai Jiao Tong Univ Univ Michigan Shanghai Jiao Tong Univ Joint Inst Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China Ruijia Technol Ltd Dept Res & Dev Shanghai 201203 Peoples R China Shanghai Jiao Tong Univ Dept Biomed Engn Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Rui Jin Hosp Sch Med Dept Nucl Med Shanghai 200240 Peoples R China

Low-dose positron emission tomography (PET) reconstruction algorithms manage to reduce the injected dose and/or scanning time in PET examination while maintaining the image quality, and thus has been extensively studied. In this article, we proposed a novel ultralow-dose reconstruction method for total-body PET. Specifically, we developed a deep learning model named ISS-Unet based on U-Net and introduced 3-D PixelUnshuffle/PixelShuffle pair in image space to reduce the training time and GPU memory. We then introduced two body sampling methods in the training patch preparation step to improve the training efficiency and local metrics. We also reported the misalignment artifacts that were often neglected in 2-D training. The proposed method was evaluated on the MICCAI 2022 Ultralow-Dose PET Imaging Challenge dataset and won the first prize in the first-round competition according to the comprehensive score combining global and local metrics. In this article, we disclosed the implementation details of the proposed method followed by the comparison results with three typical methods.

关键词： Image reconstruction Three-dimensional displays Positron emission tomography Training Solid modeling reconstruction algorithms Neural networks Deep learning (DL) image analysis low dose positron emission tomography (PET) tomographic image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Tabu-DART: a dynamic update strategy for efficient discrete algebraic reconstruction

引用

VISUAL COMPUTER 2023年第10期39卷 4671-4683页

作者： Frenkel, Daniel Six, Nathanael De Beenhouwer, Jan Sijbers, Jan Univ Antwerp Dept Phys Univ Pl 1 B-2610 Antwerp Belgium

In X-ray computed tomography, discrete tomography (DT) algorithms have been successful at reconstructing objects composed of only a few distinct materials. Many DT-based methods rely on a divide-and-conquer procedure to reconstruct the volume in parts, which improves their run-time and reconstruction quality. However, this procedure is based on static rules, which introduces redundant computation and diminishes the efficiency. In this work, we introduce an update strategy framework that allows for dynamic rules and increases control for divide-and-conquer methods for DT. We illustrate this framework by introducing Tabu-DART, which combines our proposed framework with the Discrete Algebraic reconstruction Technique (DART). Through simulated and real data reconstruction experiments, we show that our approach yields similar or improved reconstruction quality compared to DART, with substantially lower computational complexity.

关键词： X-ray tomography reconstruction algorithms Discrete tomography Limited data tomography

来源：评论

学校读者我要写书评

暂无评论

Super- resolution reconstruction algorithm for optical- resolution photoacoustic microscopy images based on sparsity and deconvolution

引用

OPTICS EXPRESS 2023年第1期31卷 598-609页

作者： Zhang, Xi Li, Zhongliang Nan, Nan Wang, Xiangzhao Chinese Acad Sci Shanghai Inst Opt & Fine Mech Lab Informat Opt & Optoelect Technol Shanghai 201800 Peoples R China Univ Chinese Acad Sci Ctr Mat Sci & Optoelect Engn Beijing 100049 Peoples R China

The lateral resolution of the optical-resolution photoacoustic microscopy (OR-PAM) system depends on the focusing diameter of the probe beam. By increasing the numerical aperture (NA) of optical focusing, the lateral resolution of OR-PAM can be improved. However, the increase in NA results in smaller working distances, and the entire imaging system becomes very sensitive to small optical imperfections. The existing deconvolution-based algorithms are limited by the image signal-to-noise ratio when improving the resolution of OR-PAM images. In this paper, a super-resolution reconstruction algorithm for OR-PAM images based on sparsity and deconvolution is proposed. The OR-PAM image is sparsely reconstructed according to the constructed loss function, which utilizes the sparsity of the image to combat the decrease in the resolution. The gradient accelerated Landweber iterative algorithm is used to deconvolve to obtain high-resolution OR-PAM images. Experimental results show that the proposed algorithm can improve the resolution of mouse retinal images by approximately 1.7 times without increasing the NA of the imaging system. In addition, compared to the Richardson-Lucy algorithm, the proposed algorithm can further improve the image resolution and maintain better imaging quality, which provides a foundation for the development of OR-PAM in clinical research. (c) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Blind deconvolution Image processing algorithms Image quality Imaging techniques Medical imaging reconstruction algorithms

来源：评论

学校读者我要写书评

暂无评论

3D-deep optical learning: a multimodal and multitask reconstruction framework for optical molecular tomography

引用

OPTICS EXPRESS 2023年第15期31卷 23768-23789页

作者： Li, Shuangchen Wang, Beilei Yu, Jingjing Kang, Dizhen He, Xuelei Guo, Hongbo He, Xiaowei Northwest Univ Sch Informat Sci & Technol Xian 710127 Peoples R China Xian Key Lab Radi & Intelligent Percept Xian Peoples R China Shaanxi Normal Univ Sch Phys & Informat Technol Xian 710119 Peoples R China

Optical molecular tomography (OMT) is an emerging imaging technique. To date, the poor universality of reconstruction algorithms based on deep learning for various imaged objects and optical probes limits the development and application of OMT. In this study, based on a new mapping representation, a multimodal and multitask reconstruction framework-3D deep optical learning (3DOL), was presented to overcome the limitations of OMT in universality by decomposing it into two tasks, optical field recovery and luminous source reconstruction. Specifically, slices of the original anatomy (provided by computed tomography) and boundary optical measurement of imaged objects serve as inputs of a recurrent convolutional neural network encoded parallel to extract multimodal features, and 2D information from a few axial planes within the samples is explicitly incorporated, which enables 3DOL to recognize different imaged objects. Subsequently, the optical field is recovered under the constraint of the object geometry, and then the luminous source is segmented by a learnable Laplace operator from the recovered optical field, which obtains stable and high-quality reconstruction results with extremely few parameters. This strategy enable 3DOL to better understand the relationship between the boundary optical measurement, optical field, and luminous source to improve 3DOL's ability to work in a wide range of spectra. The results of numerical simulations, physical phantoms, and in vivo experiments demonstrate that 3DOL is a compatible deep-learning approach to tomographic imaging diverse objects. Moreover, the fully trained 3DOL under specific wavelengths can be generalized to other spectra in the 620-900 nm NIR-I window.

关键词： Computed tomography Diffuse optical tomography Image quality Imaging techniques Optical fields reconstruction algorithms

来源：评论

学校读者我要写书评

暂无评论

Fast algorithms of Image Fusion for Super-Resolution reconstruction from Multiple Images with Random Shifts

引用

Chinese Journal of Electronics 2023年第1期21卷 69-72页

作者： Beijia Ning Jie Li Xinbo Gao VIPS Laboratory School of Electronic Engineering Xidian University Xi'an China

The commonly-used image Super-resolution (SR) reconstruction methods are computationally expensive and only applicable to “offline processing” cases. To reduce the work-load of SR fusion, three algorithms, i.e., Neighborhood searching nearest interpolation (NSNI), Fixed-distance searching nearest interpolation (FDSNI) and Two-direction linear interpolation (TDLI), are proposed in this paper in the condition of multiple lower resolution images with global random shifts. The simulation results illustrate the effectiveness, speed and quality advantages of the three proposed SR algorithms over classic algorithms.

关键词： Interpolation Simulation Superresolution reconstruction algorithms Real-time systems Image fusion Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

URGLQ: An Efficient Covariance Matrix reconstruction Method for Robust Adaptive Beamforming

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2023年第5期59卷 5634-5645页

作者： Luo, Tao Chen, Peng Cao, Zhenxin Zheng, Le Wang, Zongxin Southeast Univ State Key Lab Millimeter Waves Nanjing 210096 Peoples R China Xidian Univ State Key Lab Integrated Serv Networks Xian 710071 Peoples R China Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Beijing Inst Technol Chongqing Innovat Ctr Chongqing 401120 Peoples R China

The computational complexity of the conventional adaptive beamformer is relatively large, and the performance degrades significantly due to the model mismatch errors and the unwanted signals in received data. In this article, an efficient unwanted signal removal and Gauss-Legendre quadrature-based covariance matrix reconstruction method is proposed. Different from the prior covariance matrix reconstruction methods, a projection matrix is constructed to remove the unwanted signal from the received data, which improves the reconstruction accuracy of the covariance matrix. Considering that the computational complexity of most matrix reconstruction algorithms is relatively large due to the integral operation, we proposed a Gauss-Legendre quadrature-based method to approximate the integral operation while maintaining accuracy. Moreover, to improve the robustness of the beamformer, the mismatch in the desired steering vector is corrected by maximizing the output power of the beamformer under a constraint that the corrected steering vector cannot converge to any interference steering vector. Simulation results and prototype experiments demonstrate that the performance of the proposed beamformer outperforms the compared methods and is much closer to the optimal beamformer in different scenarios.

关键词： Covariance matrices Interference Array signal processing reconstruction algorithms Robustness Loading Estimation Covariance matrix reconstruction desired signal removal Gauss-Legendre quadrature (GLQ) robust adaptive beamforming steering vector estimation

来源：评论

学校读者我要写书评

暂无评论

Parallel Fourier ptychographic microscopy reconstruction method based on FPGA

引用

OPTICS EXPRESS 2023年第3期31卷 5016-5026页

作者： Zhao, Hongyang Hui, Wangwei Ye, Qing Huang, Kaicheng Shi, Quishuai Tian, Jianguo Zhou, Wenyuan Nankai Univ Sch Phys Key Lab Weak Light Nonlinear Photon Minist Educ Tianjin 300071 Peoples R China

Fourier ptychographic microscopy (FPM) can bypass the limitation of spatial bandwidth product to get images with large field-of-view and high resolution. The complicated sequential iterative calculation in the FPM reconstruction process reduces the reconstruction efficiency of the FPM. Therefore, we propose a parallel FPM reconstruction method based on field programmable gate array (FPGA) to accelerate the FPM reconstruction process. Using this method, multiple sub-regions in the Fourier domain can be computed in parallel and we customize a dedicated high-performance computational architecture for this approach. We deploy 4 FPM reconstruct computing architectures with a parallelism of 4 in a FPGA to compute the FPM reconstruction process, achieving the speed nearly 180 times faster than traditional methods. The proposed method provides a new perspective of parallel computing for FPM reconstruction. (c) 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Adaptive optics Computational imaging Holographic techniques Imaging systems Optical fields reconstruction algorithms

来源：评论

学校读者我要写书评

暂无评论

Inverse design of photonic crystal filters with arbitrary correlation and size for accurate spectrum reconstruction

引用

APPLIED OPTICS 2023年第8期62卷 1907-1914页

作者： Wang, Wenqi Dong, Qiao Zhang, Zhixiao Cao, Hao Xiang, Jin Gao, Li Nanjing Univ Posts & Telecommun Sch Mat Sci & Engn State Key Lab Organ Elect & Informat Displays Nanjing 210023 Peoples R China Chongqing Univ Sch Optoelect Engn Key Lab Optoelect Technol & Syst Minist Educ Chongqing 400044 Peoples R China Univ Wisconsin Sch Elect & Comp Engn Madison WI 53706 USA

Spectroscopic technique based on nanophotonic filters can recover spectral information through compressive sensing theory. The spectral information is encoded by nanophotonic response functions and decoded by computational algorithms. They are generally ultracompact, low in cost, and offer single-shot operation with spectral resolution better than 1 nm. Thus, they could be ideally suited for emerging wearable and portable sensing and imaging applications. Previous work has revealed that successful spectral reconstruction relies on well-designed filter response functions with sufficient randomness and low mutual correlation, but no thorough discussion has been performed on the filter array design. Here, instead of blind selection of filter structures, inverse design algorithms are proposed to obtain a photonic crystal filter array with predefined correlation coefficients and array size. Such rational spectrometer design can perform accurate reconstruction for a complex spectrum and maintain the performance under noise perturbation. We also discuss the impact of correlation coefficient and array size on the spectrum reconstruction accuracy. Our filter design method can be extended to different filter structures and suggests a better encoding component for reconstructive spectrometer applications. (c) 2023 Optica Publishing Group

关键词： Neural networks Numerical simulation Optical spectroscopy Photonic crystals reconstruction algorithms Signal processing

来源：评论

学校读者我要写书评

暂无评论

Off-axis point spread function reconstruction for single conjugate adaptive optics

引用

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION 2023年第7期40卷 1382-1391页

作者： Wagner, Roland Niebsch, Jenny Ramlau, Ronny Johannes Kepler Univ Linz Ind Math Inst Altenberger Str 69 A-4040 Linz Austria Austrian Acad Sci Johann Radon Inst Computat & Appl Math Altenberger Str 69 A-4040 Linz Austria

Modern giant segmented mirror telescopes (GSMTs) such as the Extremely Large Telescope, which is currently under construction, depend heavily on adaptive optics (AO) systems to correct for atmospheric distortions. However, a residual blur always remains in the astronomical images corrected by single conjugate AO (SCAO) systems due to fitting and bandwidth errors, which can mathematically be described by a convolution of the true image with a point spread function (PSF). Due to the nature of the turbulent atmosphere and its correction, the PSF is spatially varying, which is known as an anisoplanatic effect. The PSF serves, e.g., as a quality measure for science images and therefore needs to be known as accurately as possible. In this paper, we present an algorithm for PSF reconstruction from pupil-plane data in directions apart from the guide star direction in an SCAO system. Our algorithm is adapted to the needs of GSMTs focused on estimating the contribution of the anisoplanatic and generalized fitting error to the PSF. Results obtained in an end-to-end simulation tool show a qualitatively good reconstruction of the PSF compared to the PSF calculated directly from the simulated incoming wavefront as well as stable performance with respect to imprecise knowledge of atmospheric parameters. & COPY;2023 Optica Publishing Group

关键词： Atmospheric turbulence Image analysis Large telescopes reconstruction algorithms Segmented mirrors Spatial filtering

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：