检索结果-内蒙古大学图书馆

fast iterative shrinkage-thresholding algorithm with Continuation for Brain Injury Monitoring Imaging Based on Electrical Impedance Tomography

引用

SENSORS 2022年第24期22卷 9934-9934页

作者： Liu, Xuechao Zhang, Tao Ye, Jian'an Tian, Xiang Zhang, Weirui Yang, Bin Dai, Meng Xu, Canhua Fu, Feng Fourth Mil Med Univ Dept Biomed Engn Xian 710032 Peoples R China Shaanxi Key Lab Bioelectromagnet Detect & Intellig Xian 710032 Peoples R China Xining Joint Logist Support Ctr Drug & Instrument Supervis & Inspection Stn Lanzhou 730050 Peoples R China

Electrical impedance tomography (EIT) is low-cost and noninvasive and has the potential for real-time imaging and bedside monitoring of brain injury. However, brain injury monitoring by EIT imaging suffers from image noise (IN) and resolution problems, causing blurred reconstructions. To address these problems, a least absolute shrinkage and selection operator model is built, and a fast iterative shrinkage-thresholding algorithm with continuation (FISTA-C) is proposed. Results of numerical simulations and head phantom experiments indicate that FISTA-C reduces IN by 63.2%, 47.2%, and 29.9% and 54.4%, 44.7%, and 22.7%, respectively, when compared with the damped least-squares algorithm, the split Bergman, and the FISTA algorithms. When the signal-to-noise ratio of the measurements is 80-50 dB, FISTA-C can reduce IN by 83.3%, 72.3%, and 68.7% on average when compared with the three algorithms, respectively. Both simulation and phantom experiments suggest that FISTA-C produces the best image resolution and can identify the two closest targets. Moreover, FISTA-C is more practical for clinical application because it does not require excessive parameter adjustments. This technology can provide better reconstruction performance and significantly outperforms the traditional algorithms in terms of IN and resolution and is expected to offer a general algorithm for brain injury monitoring imaging via EIT.

关键词： electrical impedance tomography reconstruction algorithm brain injury monitoring imaging fast iterative shrinkage-thresholding algorithm least absolute shrinkage and selection operator model

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of CUDA GPU Implementations in Python With the fast iterative shrinkage-thresholding algorithm for LASSO

引用

IEEE ACCESS 2022年 10卷 53324-53343页

作者： Cho, Younsang Kim, Jaeoh Yu, Donghyeon Inha Univ Dept Stat Incheon 22212 South Korea Inha Univ Dept Data Sci Incheon 22212 South Korea

A general-purpose GPU (GPGPU) is employed in a variety of domains, including accelerating the spread of deep natural network models;however, further research into its effective implementation is needed. When using the compute unified device architecture (CUDA), which has recently gained popularity, the situation is analogous to use the GPUs and its memory space. This is due to the lack of a gold standard for selecting the most efficient approach for CUDA GPU parallel computation. Contrarily, as solving the least absolute shrinkage and selection operator (LASSO) regression fully consists of the basic linear algebra operations, the computation using GPGPU is more effective than other models. Additionally, its optimization problem often requires fast and efficient calculations. The purpose of this study is to provide brief introductions to the implementation approaches and numerically compare the computational efficiency of GPU parallel computation with that of the fast iterative shrinkage-thresholding algorithm for LASSO. This study contributes to providing gold standards for the CUDA GPU parallel computation, considering both computational efficiency and ease of implementation. Based on our comparison results, we recommend implementing the CUDA GPU parallel computation using Python, with either a dynamic-link library or PyTorch for the iterative algorithms.

关键词： Graphics processing units Libraries Codes Python Kernel Computational modeling Programming Compute unified device architecture graphics processing unit fast iterative shrinkage-thresholding algorithm LASSO Python

来源：评论

学校读者我要写书评

暂无评论

Inverse Patch Transfer Function With fast iterative shrinkage-thresholding algorithm as a Tool for Sparse Source Identification

引用

IEEE ACCESS 2020年 8卷 13915-13923页

作者： Lou, Lingyu Xu, Zhongming Huang, Linsen Zhang, Zhifei He, Yansong Chongqing Univ Coll Automot Engn Chongqing 400044 Peoples R China Chongqing Univ State Key Lab Mech Transmiss Chongqing 400044 Peoples R China

Inverse patch transfer functions (iPTF) method is an efficient technique for sound field reconstruction and separation of arbitrarily shaped sound sources in noisy acoustic environments. By applying Neumann boundary condition to a closed virtual cavity surrounding the source, the Helmholtz integral equation is simplified and can be solved with a Green & x2019;s function satisfying the Neumann boundary condition. However, in the identification of sparsely distributed sources, ghost sources appear in the result solved by using the iPTF method with classic Tikhonov regularization methods and influence the accuracy of identification. In the present work, an evanescent Green & x2019;s function with fast convergence of calculation is utilized, and a technique that combines the iPTF method and fast iterative shrinkage-thresholding algorithm aimed at improving the performance for the identification of sparsely distributed source is proposed. Then double layer measurements, instead of using expensive p-u probes, are employed to acquire the normal velocity of the hologram surface. In numerical simulations, the normal velocities of two anti-phased piston sources are well reconstructed with high sparsity while a disturbing source is radiating in the sound field within the frequency band of 50 to 1000 Hz. Finally, an experiment on two baffled loudspeakers has been carried out. The results of simulations and experiments indicate that the proposed technique has obviously improved the accuracy of the iPTF method in the identification of sparsely distributed sources for the frequency band from 50 to 1000 Hz.

关键词： Acoustic source identification fast iterative shrinkage-thresholding algorithm Green's function

来源：评论

学校读者我要写书评

暂无评论

Restoration for fiber bundle endomicroscopy using a fast iterative shrinkage-thresholding algorithm

Restoration for fiber bundle endomicroscopy using a fast ite...

引用

Applied Optics and Photonics China (AOPC) Conference - Optical Spectroscopy and Imaging and Biomedical Optics

作者： Liu, Jialin Zhou, Wei Xu, Baoteng Yang, Xibin Xiong, Daxi Chinese Acad Sci Suzhou Inst Biomed Engn & Technol 88 Keling St Suzhou 215163 Peoples R China Univ Chinese Acad Sci 19A Yuquan Rd Beijing 100049 Peoples R China

ISBN: (纸本)9781510639546

Optical endomicroscope via fiber bundles has been widely used to provide cellular-level visualization for clinical applications. However, improving the quality and spatial resolution of the under-sampling images obtained by fiber bundle with the inter-core spacing remains a challenging problem. In this paper, we address the problem of deconvolution and restoration in fiber-bundle-based imaging. We propose a fast iterative shrinkage-thresholding algorithm (FISTA) solve this problem, and a high-resolution (HR) image without honeycomb patterns is restored from a low-resolution (LR) fiber bundle image. The feasibility of this mothed is verified by experimental results, which shows a promising and wide applications for fiber bundle imaging.

关键词： Optical endomicroscopy Honeycomb pattern Restoration Deconvolution fast iterative shrinkage-thresholding algorithm Resolution

来源：评论

学校读者我要写书评

暂无评论

An Alternative Hybrid Time-Frequency Domain Approach Based on fast iterative shrinkage-thresholding algorithm for Rotating Acoustic Source Identification

引用

IEEE ACCESS 2019年 7卷 59797-59805页

作者： Zhang, Xin Chu, Zhigang Yang, Yang Zhao, Shuyi Yang, Yongxin Chongqing Univ State Key Lab Mech Transmiss Chongqing 400044 Peoples R China Chongqing Univ Coll Automot Engn Chongqing 400044 Peoples R China Chongqing Vehicle Test & Res Inst Co Ltd Chongqing 401122 Peoples R China

An alternative hybrid time-frequency domain approach based on the fast iterative shrinkage-thresholding algorithm (FISTA) is presented for rotating acoustic source identification. This approach is similar to the existing approaches based on the deconvolution approach for the mapping of acoustic sources (DAMAS) and non-negative least squares (NNLS) without the sample interpolation of sound pressure signal in the time domain. The acoustic source is first identified using the time-domain tracking Delay and Sum (DAS) method. The Frequency-domain deconvolution is then performed to attenuate the sidelobes and improve the spatial resolution. The simulation and experimental results indicate that the proposed approach is robust to the sampling rate and enjoys the good spatial convergence and resolution, effective sidelobe suppression, accurate quantification, as well as high computational efficiency. In general, at a lowtime-domain sampling rate, the proposed approach outperforms the DAMAS- or NNLS-based hybrid time-frequency domain approaches without the sample interpolation of sound pressure signal in the time domain.

关键词： Rotating acoustic source identification hybrid time-frequency domain approach fast iterative shrinkage-thresholding algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive step-size fast iterative shrinkage-thresholding algorithm and sparse-spike deconvolution

引用

COMPUTERS & GEOSCIENCES 2020年 134卷 104343-000页

作者： Pan, Shulin Yan, Ke Lan, Haiqiang Badal, Jose Qin, Ziyu Southwest Petr Univ Sch Earth Sci & Technol Chengdu 610500 Sichuan Peoples R China Petro China Southwest Oil & Gasfield Co Chengdu 610051 Sichuan Peoples R China Chinese Acad Sci Inst Geol & Geophys State Key Lab Lithospher Evolut Beijing 100029 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Univ Zaragoza Sci B Phys Earth Pedro Cerbuna 12 Zaragoza Spain Chengdu Univ Technol Sch Geophys Chengdu 610059 Sichuan Peoples R China

The standard fast iterative shrinkage-thresholding algorithm (FISTA) adopts a search approach consisting of linear increases to determine the step size of the internal gradient. If the input of the initial step-size is not accurate, the convergence of FISTA may be restricted when the linear search scheme is applied. To overcome this problem, we tentatively reduce the step size before each iteration to then obtain the most suitable step-size using a linear search approach. To ensure the convergence of the algorithm, we introduce the step size for the previous and subsequent iterations during the calculation process. This has allowed us sparse-spike deconvolution based on an adaptive step size algorithm (ASFISTA), which to a certain extent solves the problem of the degree of convergence of the standard method. In this paper we first present the new algorithm and then we test its convergence. In order to check the effectiveness of the modified algorithm, we use both the standard FISTA method and the improved ASFISTA method to conduct sparse spike deconvolution on a theoretical model. Finally, we carry out a similar analysis aimed at the recovery of the sparse real signal.

关键词： fast iterative shrinkage-thresholding algorithm Adaptive step-size algorithm Linear search approach Convergence rate Sparse-spike deconvolution

来源：评论

学校读者我要写书评

暂无评论

SIMO Array Imaging Based on Compressed Sensing and fast iterative shrinkage-thresholding algorithm 9

SIMO Array Imaging Based on Compressed Sensing and Fast Iter...

引用

9th IEEE International Conference on Microwave and Millimeter Wave Technology (ICMMT)

作者： Liao, Yi Liu, Shuang Xie, Haomiao Sun, Houjun Beijing Inst Technol Beijing Key Lab Millimeter Wave & Terahertz Tech Beijing 100081 Peoples R China

ISBN: (纸本)9781467389839

An effective imaging approach based on compressed sensing (CS) and fast iterative shrinkage-thresholding algorithm (FISTA) is proposed to realize the two-dimensional imaging in the single-input multiple-output (SIMO) radar system. In comparison with the traditional imaging method based on matched filtering, considerable simplification of the hardware structure would come true through the implementation ofthe imaging method presented in this paper. It takes full advantage of the superiority of CS in signal processing to realize the sparsity of the array elements and the stepped frequency points, and restores the echo signal by FISTA, which not only preforms excellently but has enough high efficiency. In the end, the two-dimensional imaging result through numerical simulations would be presented to verify the validity and effectiveness of this particular imaging method.

关键词： single input multiple output (SIMO) compressed sensing two-dimensional imaging fast iterative shrinkage-thresholding algorithm

来源：评论

学校读者我要写书评

暂无评论

An enhanced sparse autoencoder for machinery interpretable fault diagnosis

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2024年第5期35卷 055108-055108页

作者： Niu, Maogui Jiang, Hongkai Wu, Zhenghong Shao, Haidong Northwestern Polytech Univ Sch Civil Aviat Xian 710072 Peoples R China Hunan Univ Coll Mech & Vehicle Engn Changsha 410082 Peoples R China

The interpretability of individual components within existing autoencoders remains insufficiently explored. This paper aims to address this gap by delving into the interpretability of the encoding and decoding structures and their correlation with the physical significance of vibrational signals. To achieve this, the Sparse Coding with Multi-layer Decoders (SC-MD) model is proposed, which facilitates fault diagnosis from two perspectives: the working principles of the model itself and the evolving trends of fault features. Specifically, a sparse coding protocol to prevent L1-norm collapse is proposed in the encoding process, regularizing the encoding to ensure that each latent code component possesses variance greater than a fixed threshold on a set of sparse representations given the input data. Subsequently, a multi-layer decoder structure is designed to capture the intricate mapping relationship between features and fault patterns. Finally, the fast iterative shrinkage-thresholding algorithm (FISTA) is employed as the solver for the SC-MD model, enabling end-to-end updates of all parameters by unfolding FISTA. The coherent theoretical framework ensures the interpretability of SC-MD. Utilizing aeroengine bearing data, we demonstrate the exceptional performance of our proposed approach under both normal conditions and intense noise, as compared to state-of-the-art deep learning methods.

关键词： sparse coding multi-layer decoders fault diagnosis aircraft engine bearing data fast iterative shrinkage-thresholding algorithm

来源：评论

学校读者我要写书评

暂无评论

Mixed Matrix Completion in Complex Survey Sampling under Heterogeneous Missingness

引用

JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS 2024年第4期33卷 1320-1328页

作者： Mao, Xiaojun Wang, Hengfang Wang, Zhonglei Yang, Shu Shanghai Jiao Tong Univ Sch Math Sci Key Lab Sci & Engn Comp Minist Educ Shanghai Peoples R China Fujian Normal Univ Sch Math & Stat Fuzhou Fujian Peoples R China Fujian Normal Univ Fujian Prov Key Lab Stat & Artificial Intelligence Fuzhou Fujian Peoples R China Xiamen Univ Wang Yanan Inst Studies Econ Xiamen Fujian Peoples R China Xiamen Univ Sch Econ Xiamen Fujian Peoples R China North Carolina State Univ Dept Stat Raleigh NC USA Fujian Normal Univ Sch Math & Stat Fuzhou 350007 Fujian Peoples R China Fujian Normal Univ Fujian Prov Key Lab Stat & Artificial Intelligence Fuzhou 350007 Fujian Peoples R China

Modern surveys with large sample sizes and growing mixed-type questionnaires require robust and scalable analysis methods. In this work, we consider recovering a mixed dataframe matrix, obtained by complex survey sampling, with entries following different canonical exponential distributions and subject to heterogeneous missingness. To tackle this challenging task, we propose a two-stage procedure: in the first stage, we model the entry-wise missing mechanism by logistic regression, and in the second stage, we complete the target parameter matrix by maximizing a weighted log-likelihood with a low-rank constraint. We propose a fast and scalable estimation algorithm that achieves sublinear convergence, and the upper bound for the estimation error of the proposed method is rigorously derived. Experimental results support our theoretical claims, and the proposed estimator shows its merits compared to other existing methods. The proposed method is applied to analyze the National Health and Nutrition Examination Survey data. Supplementary materials for this article are available online.

关键词： Covariate matrix Exponential family fast iterative shrinkage-thresholding algorithm

来源：评论

学校读者我要写书评

暂无评论

Neutron Tomograph of Spent Fuel Casks

引用

JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY 2022年第4期94卷 399-409页

作者： Liu, Zhihua Fang, Ming George, Jon Meng, Ling-Jian Di Fulvio, Angela Univ Illinois Dept Nucl Plasma & Radiol Engn 104 South Wright St Urbana IL 61801 USA Univ Chicago Med Dept Radiat & Cellular Oncol 5758 S Maryland Ave Urbana IL 60637 USA Univ Illinois Beckman Inst Adv Sci & Technol 405 N Mathews Ave Urbana IL 61801 USA Univ Illinois Dept Bioengn 1406 W Green St Urbana IL 61801 USA

Dry casks for spent nuclear fuel (SNF) ensure the safe storage of SNF and provide radiation shielding. However, the presence of the thick casks encompassing several layers of steel and concrete makes inspection of the SNF a challenging task. fast neutron interrogation is a viable method for the nondestructive assay of dry storage casks. In this study, we performed a Monte Carlo simulation-based study associated with a machine-learning-based image reconstruction method to verify the content of SNF dry storage casks. We studied the use of neutron transmission and back-scattered measurements to assess the potential damage to fuel assemblies or fuel pin diversion during transportation of dry casks. We used Geant4 to model a realistic HI-STAR 100 cask, MPC-68 canister and basket, and GE-14 fuel assembly irradiated by a D-T neutron generator. Several bundle diversion scenarios were simulated. The angular distribution of the neutrons scattered by the cask was used to identify the diversions inside the fuel cask. A fuel bundle with at least 75% of its pins removed can be identified with a drop in the back-scattered signature larger than 2 sigma compared with a fully loaded scenario. We combined an iterative reconstruction algorithm with a convolutional neural network (CNN) to obtain a cross- sectional image of the fuel inside the cask. The proposed imaging approach allows locating the position of a missing fuel bundle with at least 75% of the pins removed when performing tomographic imaging of a canister with an overall scan time of less than two hours, when using a commercial neutron generator with a source strength of 1010 n/s in the 4 sigma solid angle.

关键词： Neutron tomography Spent nuclear fuel Dry cask storage Nondestructive assay fast iterative shrinkage-thresholding algorithm

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：