检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Ho, Chih-Hsing Tsai, Shang-Ho Department of Electrical Engineering and Computer Science Honor Program National Chiao Tung University Hsinchu Taiwan Department of Electrical Engineering National Chiao Tung University Hsinchu Taiwan

Continuous learning seeks to perform the learning on the data that arrives from time to time. While prior works have demonstrated several possible solutions, these approaches require excessive training time as well as memory usage. This is impractical for applications where time and storage are constrained, such as edge computing. In this work, a novel training algorithm, regularized subspace approximation classifier (RSAC), is proposed to achieve lightweight continuous learning. RSAC contains a feature reduction module and classifier module with regularization. Extensive experiments show that RSAC is more efficient than prior continuous learning works and outperforms these works on various experimental settings. Copyright © 2020, The Authors. All rights reserved.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Autonomous cognitive gpr based on edge computing and reinforcement learning 2

Autonomous cognitive gpr based on edge computing and reinfor...

引用

2nd IEEE International Conference on Industrial Internet Cloud, ICII 2019

作者： Omwenga, Maxwell M. Wu, Dalei Liang, Yu Yang, Li Huston, Dryver Xia, Tian Department of Computer Science and Engineering University of Tennessee at Chattanooga United States Department of Mechanical Engineering University of Vermont United States Department of Electrical and Biomedical Engineering University of Vermont United States

ISBN: (纸本)9781728129778

Autonomous cognitive ground penetrating radar (ACGPR), carried by drones or other robotic platforms, may perform robust and accurate subsurface object detection and recognition in varying environments based on real-time data processing and decision making. However, limited system computing resources and intelligence generating capability pose significant challenges for the operations of such systems. To address these challenges, in this paper we propose an ACGPR enabled by edge computing (EC) and reinforcement learning. Specifically, an edge computing based system architecture is presented to utilize edge resources for real-time intelligence generation. A reinforcement learning approach is developed as the decision-making model for the ACGPR to adaptively adjust its operational parameters. Simulation results show the accuracy and efficacy of the proposed ACGPR system. The framework also provides insight into the design of autonomous cognitive industrial Internet of things (IoT) supported by edge computing and machine learning. © 2019 IEEE.

关键词： Ground penetrating radar systems

来源：评论

学校读者我要写书评

暂无评论

Sequence-Dependent Tyrosine-Containing Peptide Nano-Assemblies for Sensing Tyrosinase and Melanoma

SSRN

引用

SSRN 2022年

作者： Guo, Jun Zhao, Ruoyang Gao, Feng Li, Xiaofang Wang, Liping Zhang, Feng Quantum Biophotonic Lab School of Optical-Electrical and Computer-Engineering University of Shanghai for Science and Technology Shanghai200093 China Wenzhou Institute University of Chinese Academy of Sciences Wenzhou325001 China Oujiang Laboratory Zhejiang Wenzhou325000 China Pharmacy Laboratory Inner Mongolia International Mongolian Hospital Hohhot010065 China Department of Biomedical Engineering School of Basic Medical Sciences Guangzhou Medical University Guangzhou511436 China

Tyrosine-containing peptide nano-assemblies have received tremendous attention because of their potential applications in biomedicine and nanomaterial fields. However, a current outstanding challenge is to direct the equilibrium between oxidative polymerization of precursors and the non-covalent assembly to precisely tune their specific nano-structures and functionalities through the rational design of peptide sequences. With a simple library of tripeptides containing tyrosine, glycine and lysine, here we demonstrate how amino acid sequence encodes the property of tripeptide nano-assemblies by modulating the enzymatic oxidation of tyrosinase with the accompanied self-assembly, and thus selects the pathways towards fluorescent or melanin-like nano-assemblies. The fluorescence of tripeptide nano-assemblies has been demonstrated in sensing both tyrosinase and melanoma. Our findings will provide inspiration of peptide sequence design for generating the complex bioactive peptide nanomaterials for biomedical applications. © 2022, The Authors. All rights reserved.

关键词： Amino acids

来源：评论

学校读者我要写书评

暂无评论

Deterministic Learning with Probabilistic Analysis on Human-Robot Shared Contro

Deterministic Learning with Probabilistic Analysis on Human-...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Xiaotian Chen Paolo Stegagno Chengzhi Yuan Department of Mechanical Industrial and Systems Engineering University of Rhode Island Kingston USA Department of Electrical Computer and Biomedical Engineering University of Rhode Island Kingston USA

ISBN: (数字)9781728167947

ISBN: (纸本)9781728167954

In this paper, we present a novel method for controlling an unmanned ground vehicle (UGV) by using a new machine learning technique, Deterministic Learning (DL). With DL the robot is able to learn and recognize four specifically designed body gestures, which represent four corresponding moving directions (i.e., left, right, forward, and backward) of the controlled UGV. A Kinect camera is employed to collect human body skeleton data of a user. Eight specifically-designed features are extracted and utilized to train radial basis function neural networks (RBFNNs). The dynamics of the human arm waving motion is guaranteed to be accurately identified, represented, and stored as an RBFNN model with converged constant NN weights, which facilitates rapid recognition in the online identification phase. However, learning time of and storage space of RBFNNs grow exponentially with the number of features. In order drastically reduce required computations and storage space, we propose to split the features in subgroups, and use each subgroup to learn a smaller independent. In the online identification phase, the trained RBFNNs are used to analyze and identify any new incoming gestures. The identification results of all RBFNNs are then fused together following a probabilistic approach, and the gestures of the user are interpreted as commands for the UGV.

关键词： Feature extraction Probabilistic logic Data mining Dynamics Artificial neural networks Robots

来源：评论

学校读者我要写书评

暂无评论

Edge computing enabled cognitive portable ground penetrating radar 12

Edge computing enabled cognitive portable ground penetrating...

引用

12th EAI International Conference on Mobile Multimedia Communications, MOBIMEDIA 2019

作者： Wu, Dalei Omwenga, Maxwell M. Liang, Yu Yang, Li Huston, Dryver Xia, Tian Department of Computer Science and Engineering University of Tennessee Chattanooga United States Department of Mechanical Engineering University of Vermont United States Department of Electrical and Biomedical Engineering University of Vermont United States

ISBN: (纸本)9781631901836

With distributed communication, computation, and storage resources close to end users, edge computing has great potentials to support delay-sensitive industrial applications involving intelligent edge devices. Cognitive portable ground penetrating radars (GPRs) are expected to achieve high-quality sensing performance in a variety of industrial environments by operating intelligently and adaptively under varying sensing conditions. Although edge computing makes it very promising to develop cognitive portable GPRs, both strict performance requirement and trade-offs between communication and computation pose significant challenges. This paper presents an edge computing framework for cognitive portable GPRs. Specifically, the system architecture of an EC-enabled cognitive portable GPR is developed. Based on the identification of various involved computation tasks, an offloading policy was proposed to determine whether computation tasks should be executed locally or offloaded to the edge server. Experimental results show the efficacy of the proposed methods. The framework also provides insight into the design of cognitive Internet of things (IoT) supported by edge computing. © 2019 EAI.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach to 3D Segmentation of Brain Vasculature

A Deep Learning Approach to 3D Segmentation of Brain Vascula...

引用

Optics and the Brain, BRAIN 2019 - Part of Biophotonics Congress: Optics in the Life Sciences Congress 2019

作者： Tahir, Waleed Zhu, Jiabei Kura, Sreekanth Cheng, Xiaojun Boas, David Tian, Lei Department of Electrical and Computer Engineering Boston University United States Department of Optics and Optical Engineering University of Science and Technology of China China Department of Biomedical Engineering Boston University United States

The segmentation of blood-vessels is an important preprocessing step for the quantitative analysis of brain vasculature. We approach the segmentation task for two-photon brain angiograms using a fully convolutional 3D... 详细信息

ISBN: (纸本)9781943580545

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

Fingerprint spectroscopic SRS imaging of single living cells and whole brain by ultrafast tuning and spatial-spectral learning

arXiv

引用

arXiv 2020年

作者： Lin, Haonan Lee, Hyeon Jeong Tague, Nathan Lugagne, Jean-Baptiste Zong, Cheng Deng, Fengyuan Wong, Wilson Dunlop, Mary J. Cheng, Ji-Xin Department of Biomedical Engineering Department of Electrical & Computer Engineering Photonics Center Biological Design Center Boston University BostonMA02215 United States College of Biomedical Engineering and Instrument Sciences Zhejiang University Hangzhou China

Label-free vibrational imaging by stimulated Raman scattering (SRS) provides unprecedented insight into real-time chemical distributions in living systems. Specifically, SRS in the fingerprint region (400-1800 cm−1) can resolve multiple chemicals in a complex bio-environment using specific and well-separated Raman signatures. Yet, fingerprint SRS imaging with microsecond spectral acquisition has not been achieved due to the small fingerprint Raman cross-sections and the lack of ultrafast acquisition scheme with high spectral resolution and high fidelity. Here, we report a fingerprint spectroscopic SRS platform that acquires a distortion-free SRS spectrum with 10 cm-1 spectral resolution in 20 µs using a lab-built ultrafast delay-line tuning system. Meanwhile, we significantly improve the signal-to-noise ratio by employing a spatial-spectral residual learning network, reaching comparable quality to images taken with two orders of magnitude longer pixel dwell times. Collectively, our system achieves reliable fingerprint spectroscopic SRS with microsecond spectral acquisition speed, enabling imaging and tracking of multiple biomolecules in samples ranging from a live single microbe to a tissue slice, which was not previously possible with SRS imaging in the highly congested carbon-hydrogen region. To show the broad utility of the approach, we have demonstrated high-speed compositional imaging of lipid metabolism in living pancreatic cancer Mia PaCa-2 cells. We then performed high-resolution mapping of cholesterol, fatty acid, and protein in the mouse whole brain. Finally, we mapped the production of two biofuels in microbial samples by harnessing the superior spectral and temporal resolutions of our system. Copyright © 2020, The Authors. All rights reserved.

关键词： Stimulated Raman scattering

来源：评论

学校读者我要写书评

暂无评论

Unified Analysis on L1 over L2 Minimization for signal recovery

arXiv

引用

arXiv 2021年

作者： Tao, Min Zhang, Xiao-Ping Department of Mathematics National Key Laboratory for Novel Software Technology Nanjing University Nanjing210093 China Department of Electrical Computer and Biomedical Engineering Ryerson University TorontoONM5B 2K3 Canada

In this paper, we carry out a unified study for L1 over L2 sparsity promoting models, which are widely used in the regime of coherent dictionaries for recovering sparse nonnegative/arbitrary signals. First, we provide a unified theoretical analysis on the existence of the global solutions of the constrained and the unconstrained L1/L2 models. Second, we analyze the sparse property of any local minimizer of these L1/L2 models which serves as a certificate to rule out the nonlocal-minimizer stationary solutions. Third, we derive an analytical solution for the proximal operator of the L1/L2 with nonnegative constraint. Equipped with this, we apply the alternating direction method of multipliers to the unconstrained model with nonnegative constraint in a particular splitting way, referred to as ADMM+p. We establish its global convergence to a d-stationary solution (sharpest stationary) without the Kurdyka-Lojasiewicz assumption. Extensive numerical simulations confirm the superior of ADMM+p over the state-of-the-art methods in sparse recovery. In particular, ADMM+p reduces computational time by about 95% ∼ 99% while achieving a much higher accuracy than the commonly used scaled gradient projection method for the wavelength misalignment *** Codes 90C26, 90C90 © 2021, CC BY.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Machine learning based potentiating impacts of 12-lead ECG for classifying paroxysmal versus non-paroxysmal atrial fibrillation

引用

International Journal of Arrhythmia 2022年第1期23卷 1-9页

作者： Sungsoo Kim Alan C. Bovik Sohee Kwon Sung-Hwi Hong JunYong Kim Boyoung Joung Hui-Nam Pak Moon-Hyeong Lee Mia K. Markey Hye Jin Hwang Junbeom Park Electrical and Computer Engineering The University of Texas at Austin Austin USA Deparment of Internal Medicine College of Medicine Yonsei University Seoul South Korea Department of Epidemiology Harvard T. H. Chan School of Public Health Boston MA USA Harvard University Cambridge USA Department of Biomedical Engineering The University of Texas at Austin Austin USA Department of Imaging Physics The University of Texas MD Anderson Cancer Center Houston USA Cardiovascular Division Department of Medicine Beth Israel Deaconess Medical Center Boston MA USA Department of Cardiology College of Medicine Ewha Womans University 1071 Annyangcheon-ro Yangcheon-gu Seoul Republic of Korea

BackgroundConventional modality requires several days observation by Holter monitor to differentiate atrial fibrillation (AF) between Paroxysmal atrial fibrillation (PAF) and Non-paroxysmal atrial fibrillation (Non-PA... 详细信息

Background

Conventional modality requires several days observation by Holter monitor to differentiate atrial fibrillation (AF) between Paroxysmal atrial fibrillation (PAF) and Non-paroxysmal atrial fibrillation (Non-PAF). Rapid and practical differentiating approach is needed.

Objective

To develop a machine learning model that observes 10-s of standard 12-lead electrocardiograph (ECG) for real-time classification of AF between PAF versus Non-PAF.

Methods

In this multicenter, retrospective cohort study, the model training and cross-validation was performed on a dataset consisting of 741 patients enrolled from Severance Hospital, South Korea. For cross-institutional validation, the trained model was applied to an independent data set of 600 patients enrolled from Ewha University Hospital, South Korea. Lasso regression was applied to develop the model.

Results

In the primary analysis, the Area Under the Receiver Operating Characteristic Curve (AUC) on the test set for the model that predicted AF subtype only using ECG was 0.72 (95% CI 0.65–0.80). In the secondary analysis, AUC only using baseline characteristics was 0.53 (95% CI 0.45–0.61), while the model that employed both baseline characteristics and ECG parameters was 0.72 (95% CI 0.65–0.80). Moreover, the model that incorporated baseline characteristics, ECG, and Echocardiographic parameters achieved an AUC of 0.76 (95% CI 0.678–0.855) on the test set.

Conclusions

Our machine learning model using ECG has potential for automatic differentiation of AF between PAF versus Non-PAF achieving high accuracy. The inclusion of Echocar

关键词： Machine learning 12 leads surface electrocardiogram Atrial fibrillation

来源：评论

学校读者我要写书评

暂无评论

Unified Analysis on L1 over L2 Minimization for signal recovery

TechRxiv

引用

TechRxiv 2021年

In this paper, we carry out a unified study for L1 over L2 sparsity promoting models, which are widely used in the regime of coherent dictionaries for recovering sparse nonnegative/arbitrary signals. First, we provide a unified theoretical analysis on the existence of the global solutions of the constrained and the unconstrained L1/L2 models. Second, we analyze the sparse property of any local minimizer of these L1/L2 models which serves as a certificate to rule out the nonlocal-minimizer stationary solutions. Third, we derive an analytical solution for the proximal operator of the L1/L2 with nonnegative constraint. Equipped with this, we apply the alternating direction method of multipliers to the unconstrained model with nonnegative constraint in a particular splitting way, referred to as ADMM+p . We establish its global convergence to a d-stationary solution (sharpest stationary) without the Kurdyka-Lojasiewicz assumption. Extensive numerical simulations confirm the superior of ADMM+p over the state-of-the-art methods in sparse recovery. In particular, ADMM+p reduces computational time by about 95% ∼ 99% while achieving a much higher accuracy than the commonly used scaled gradient projection method for the wavelength misalignment problem. © 2021, CC BY.

关键词： Recovery

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

Background

Objective

Methods

Results

Conclusions

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

Background

Objective

Methods

Results

Conclusions

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：