检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Cui, Leilei Jiang, Zhong-Ping Sontag, Eduardo D. Department of Electrical and Computer Engineering New York University BrooklynNY United States Department of Electrical and Computer Engineering Department of BioEngineering Northeastern University BostonMA United States

This paper studies the effect of perturbations on the gradient flow of a general nonlinear programming problem, where the perturbation may arise from inaccurate gradient estimation in the setting of data-driven optimization. Under suitable conditions on the objective function, the perturbed gradient flow is shown to be small-disturbance input-to-state stable (ISS), which implies that, in the presence of a small-enough perturbation, the trajectories of the perturbed gradient flow must eventually enter a small neighborhood of the optimum. This work was motivated by the question of robustness of direct methods for the linear quadratic regulator problem, and specifically the analysis of the effect of perturbations caused by gradient estimation or round-off errors in policy optimization. We show small-disturbance ISS for three of the most common optimization algorithms: standard gradient flow, natural gradient flow, and Newton gradient flow. Copyright © 2023, The Authors. All rights reserved.

关键词： Nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

AMAG: additive, multiplicative and adaptive graph neural network for forecasting neural activity 23

AMAG: additive, multiplicative and adaptive graph neural net...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Jingyuan Li Leo Scholl Trung Le Pavithra Rajeswaran Amy Orsborn Eli Shlizerman Department of Electrical & Computer Engineering University of Washington Seattle WA Department of Bioengineering University of Washington Seattle WA Department of Electrical & Computer Engineering University of Washington Seattle WA and Department of Bioengineering University of Washington Seattle WA Department of Electrical & Computer Engineering University of Washington Seattle WA and Department of Applied Mathematics University of Washington Seattle WA

Latent Variable Models (LVMs) propose to model the dynamics of neural populations by capturing low-dimensional structures that represent features involved in neural activity. Recent LVMs are based on deep learning methodology where a deep neural network is trained to reconstruct the same neural activity given as input and as a result to build the latent representation. Without taking past or future activity into account such a task is non-causal. In contrast, the task of forecasting neural activity based on given input extends the reconstruction task. LVMs that are trained on such a task could potentially capture temporal causality constraints within its latent representation. Forecasting has received less attention than reconstruction due to recording challenges such as limited neural measurements and trials. In this work, we address modeling neural population dynamics via the forecasting task and improve forecasting performance by including a prior, which consists of pairwise neural unit interaction as a multivariate dynamic system. Our proposed model—Additive, Multiplicative, and Adaptive Graph Neural Network (AMAG)— leverages additive and multiplicative message-passing operations analogous to the interactions in neuronal systems and adaptively learns the interaction among neural units to forecast their future activity. We demonstrate the advantage of AMAG compared to non-GNN based methods on synthetic data and multiple modalities of neural recordings (field potentials from penetrating electrodes or surface-level micro-electrocorticography) from four rhesus macaques. Our results show the ability of AMAG to recover ground truth spatial interactions and yield estimation for future dynamics of the neural population.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comment on“In vivo flow cytometry reveals a circadian rhythm of circulating tumor cells”

引用

Light(Science & Applications) 2021年第10期10卷 1998-1999页

作者： Amber L.Williams Jessica E.Fitzgerald Fernando Ivich Eduardo DSontag Mark Niedre Department of Bioengineering Northeastern UniversityBostonMAUSA Department of Electrical and Computer Engineering Northeastern UniversityBostonMAUSA Laboratory of Systems Pharmacology Harvard Medical SchoolBostonMAUSA

Dear Editor,Circulating tumor cells(CTCs)are instrumental in hematogenous metastasis and are widely studied using liquid biopsy *** involve analysis and characterization of CTCs from fractionally small blood samples drawn from *** biopsy implicitly assumes that the number and phenotypical distribution of CTCs in small blood samples is representative of the full peripheral blood volume,and furthermore that CTC numbers are approximately constant over the days and hours surrounding the blood draw.

关键词： biopsy metastasis furthermore

来源：评论

学校读者我要写书评

暂无评论

A Multi-Scale Control Framework for Electric and Automated Buses in Intercity Lines

A Multi-Scale Control Framework for Electric and Automated B...

引用

IEEE Conference on Decision and Control

作者： S. Graffione S. Bracco C. Pasquale S. Sacone S. Siri A. Ferrara Department of Informatics Bioengineering Robotics and Systems Engineering University of Genova Italy Department of Electrical Electronics and Telecommunication Engineering and Naval Architecture University of Genova Italy Department of Electrical Computer and Biomedical Engineering University of Pavia Italy

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

This paper proposes a multi-scale control scheme aimed at controlling speed, dwell time, and charging time of electric and automated buses performing the transport service on lines where there are no reserved lanes. The proposed control scheme has two layers characterized by different control objectives, level of detail and time scales. The high-level controller periodically solves a multi-objective optimal control problem formalized to ensure an adequate transport service, while the low-level controller, being based on a more accurate description of the bus dynamics and energy consumption, seeks to follow the high-level control actions while taking into account the effective traffic conditions encountered on the line and the effective dynamic behaviour of the bus. The paper concludes with the application to a case study in order to demonstrate the effectiveness of the proposed control scheme.

关键词： Energy consumption Accuracy Optimal control Minimization Real-time systems Delays Batteries State of charge Brakes MATLAB

来源：评论

学校读者我要写书评

暂无评论

Multiparametric ultrasound analysis for diagnosis of hepatic steatosis in human subjects

Multiparametric ultrasound analysis for diagnosis of hepatic...

引用

2023 IEEE International Ultrasonics Symposium, IUS 2023

作者： Baek, Jihye Basavarajappa, Lokesh Kaffas, Ahmed El Kamaya, Aya Hoyt, Kenneth Parker, Kevin J. Stanford University Department of Radiology StanfordCA United States University of Texas at Dallas Department of Bioengineering RichardsonTX United States Texas A&m University Department of Biomedical Engineering College StationTX United States University of Rochester Department of Electrical and Computer Engineering RochesterNY United States

ISBN: (纸本)9798350346459

Quantitative ultrasound (QUS) can assist in the diagnosis of hepatic steatosis by providing more sensitive measurements compared to traditional B-scan US imaging. However, QUS requires quantification of parameter properties and clinicians must integrate information across the parametric estimates. Thus, we suggest a multiparametric US (MPUS) approach which combines information from multiple measured values. A total of 10 patients were included with hepatic steatosis and a fat fraction between 0.5 and 24 % was measured by magnetic resonance imaging-derived proton density fat fraction (MRI-PDFF). US scans were performed using a clinical system (Philips EPIQ 7 system, Philips Healthcare, Bothell, WA). Expanding on previous QUS and multiparametric analyses, we extracted 13 features: H-scan US color (relative scatterer size), US attenuation, speckle statistics related to the Burr power law and Nakagami analysis, conventional measures of B-scan US intensity and the hepatorenal index (HRI), and shear wave elasticity, viscosity, and dispersion. To combine information from the multiple US measures, a feature selection was performed and then the first principal component (PC1) was obtained using these select features. The PC1 from a selected feature set, including H-scan US analysis, speckle intensity, and shear wave measurement, resulted in a significant correlation with MRI-PDFF (Spearman's correlation coefficient Rs = 0.98, p © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Advances in Wireless,Batteryless,Implantable Electronics for Real‑Time,Continuous Physiological Monitoring

引用

Nano-Micro Letters 2024年第3期16卷 254-302页

作者： Hyeonseok Kim Bruno Rigo Gabriella Wong Yoon Jae Lee Woon‑Hong Yeo IEN Center for Wearable Intelligent Systems and Healthcare Georgia Institute of TechnologyAtlantaGA 30332USA George W.Woodruff School of Mechanical Engineering Georgia Institute of TechnologyAtlantaGA 30332USA School of Electrical and Computer Engineering Georgia Institute of TechnologyAtlantaGA 30332USA Wallace H.Coulter Department of Biomedical Engineering Georgia Tech and Emory University School of MedicineAtlantaGA 30332USA Parker H.Petit Institute for Bioengineering and Biosciences Institute for MaterialsInstitute for Robotics and Intelligent MachinesGeorgia Institute of TechnologyAtlantaGA 30332USA

This review summarizes recent progress in developing wireless,batteryless,fully implantable biomedical devices for real-time continuous physiological signal monitoring,focusing on advancing human health *** considerations,such as biological constraints,energy sourcing,and wireless communication,are discussed in achieving the desired performance of the devices and enhanced interface with human *** addition,we review the recent achievements in materials used for developing implantable systems,emphasizing their importance in achieving multi-functionalities,biocompatibility,and *** wireless,batteryless devices offer minimally invasive device insertion to the body,enabling portable health monitoring and advanced disease ***,we summarize the most recent practical applications of advanced implantable devices for human health care,highlighting their potential for immediate commercialization and clinical uses.

关键词： Implantable electronics Biomedical systems Batteryless devices Wireless electronics Physiological signal monitoring

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution Terahertz Imaging Through a Plasmonic Photoconductive Focal-Plane Array

Super-Resolution Terahertz Imaging Through a Plasmonic Photo...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Li, Xurong Mengu, Deniz Ozcan, Aydogan Jarrahi, Mona Electrical and Computer Engineering Department University of California Los AngelesCA90095 United States California NanoSystems Institute University of California Los AngelesCA United States Department of Bioengineering University of California Los AngelesCA United States

ISBN: (纸本)9781957171258

We utilize hyperspectral amplitude and phase information of imaged objects with a plasmonic photoconductive focal-plane array to resolve their structural information with an effective number of pixels exceeding 1-kilo-pixel using a pixel-super-resolution convolutional neural network. © Optica Publishing Group 2023 © 2023 The Author(s)

关键词： Focusing

来源：评论

学校读者我要写书评

暂无评论

Disease specific imaging utilizing support vector machine: assessment of steatosis

Disease specific imaging utilizing support vector machine: a...

引用

2023 IEEE International Ultrasonics Symposium, IUS 2023

作者： Baek, Jihye Basavarajappa, Lokesh Hoyt, Kenneth Parker, Kevin J. Stanford University Department of Radiology StanfordCA United States University of Texas at Dallas Department of Bioengineering RichardsonTX United States Texas A&m University Department of Biomedical Engineering College StationTX United States University of Rochester Department of Electrical and Computer Engineering RochesterNY United States

ISBN: (纸本)9798350346459

Quantitative tissue characterization can be used to differentiate between normal and diseased tissues utilizing statistical analysis and machine learning classifiers. However, the classification typically distinguishes tissue condition (normal or diseased) but does not necessarily provide disease progression levels and visual display on US images. We have proposed a new framework, known as disease-specific imaging (DSI), which produces a color overlaid highlight on B-mode ultrasound (US) images, visualizing disease progression level. DSI has been conducted to distinguish between normal liver, steatotic liver, fibrotic liver, and metastatic cancer in liver. In this study, the performance of DSI was tested with an early steatosis dataset which was acquired separately from a previous training set of various liver diseases. For the steatosis animal model, nonalcoholic fatty liver disease (NAFLD) was induced with a methionine and choline deficient (MCD) diet. Steatosis was induced for 2 weeks in 6 mice, and 4 control mice were fed a normal diet. The animals underwent US scanning to capture radiofrequency (RF) data with a 15 MHz center frequency transducer at baseline (week 0) and week 2. From the RF data, 3 US features were measured: B-mode intensity, H-scan parameter, and attenuation coefficient. DSI utilized a support vector machine to classify disease types and the inner product was applied to specify disease severity. As a reference, fat fraction was measured from histology images. A combined parameter of DSI resulted in a strong agreement (Spearman's correlation coefficient of 0.83) with the histology fat fraction. Moreover, DSI visualized fatty tissue region in B-mode images, displaying disease type by color and disease progression by color intensity. Therefore, we anticipate the clinical use of DSI for simple interpretation of tissue characterization which does not require clinician's pre-training for QUS parameters. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Polarization-based underwater geolocalization with deep learning

引用

eLight 2023年第1期3卷 122-135页

作者： Xiaoyang Bai Zuodong Liang Zhongmin Zhu Alexander Schwing David Forsyth Viktor Gruev Department of Electrical and Computer Engineering University of Illinois at Urbana-ChampaignUrbanaIL 61801USA Department of Computer Science University of Illinois at Urbana-ChampaignUrbanaIL 61801USA Department of Bioengineering University of Illinois at Urbana-ChampaignUrbanaIL 61801USA Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-ChampaignUrbanaIL 61801USA Carle Illinois College of Medicine University of Illinois at Urbana-ChampaignUrbanaIL 61820USA

Water is an essential component of the Earth’s climate,but monitoring its properties using autonomous underwater sampling robots remains a significant challenge due to lack of underwater geolocalization *** methods for underwater geolocalization rely on tethered systems with limited coverage or daytime imagery data in clear waters,leaving much of the underwater environment *** in turbid waters or at night has been considered unfeasible due to absence of identifiable *** this paper,we present a novel method for underwater geolocalization using deep neural networks trained on-10 million polarization-sensitive images acquired globally,along with camera position sensor *** approach achieves longitudinal accuracy of-55 km(-1000 km)during daytime(nighttime)at depths up to-8 m,regardless of water *** clear waters,the transfer learning longitudinal accuracy is-255 km at 50 m *** leveraging optical data in conjunction with camera position information,our novel method facilitates underwater geolocalization and offers a valuable tool for untethered underwater navigation.

关键词： Underwater geolocalization Ocean exploration Celestial-based navigation Polarization Deep learning

来源：评论

学校读者我要写书评

暂无评论

A New AI System for Precise Grading of HCC Based on Analyzing DW-MRI Radiomics and Alpha-fetoprotein as Liver Cancer Clinical Marker 27th

A New AI System for Precise Grading of HCC Based on Analyzin...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Elkhouly, Abdelrhman Alksas, Ahmed Saleh, Gehad A. Shehata, Mohamed Karawia, Abdelrahman Ghazal, Mohammed Contractor, Sohail El-Baz, Ayman Mathematics Department Faculty of Science Mansoura University Mansoura Egypt Department of Bioengineering University of Louisville LouisvilleKY United States Diagnostic and Interventional Radiology Department Faculty of Medicine Mansoura University Mansoura Egypt Electrical Computer Biomedical Engineering Department Abu Dhabi University Abu Dhabi United Arab Emirates Department of Radiology University of Louisville LouisvilleKY United States

ISBN: (纸本)9783031783975

Hepatocellular carcinoma (HCC), – the main form of liver cancer –, is the second global leading cause of cancer-related mortality. LI-RADS is considered the worldwide non-invasive standard method for imaging interpretation and reporting in patients with HCC eliminating the need for biopsy. However, it might be prone to interpretation subjectivity. Therefore, we develop an objective non-invasive AI-based grading system for HCC for appropriate etiology treatment plans. The developed system integrates potential image-based markers that represent the tumor’s morphology, functionality, and appearance/texture with the associated clinical biomarkers. The study encompasses 117 patients diagnosed with HCC and was divided into three different groups (group 1: benign low-grade (LR 1,2), N = 41;group 2: malignant high-grade (LR 4,5), N = 39;and group 3: malignant not HCC (LR-M), N = 37). Diffusion-weighted magnetic resonance imaging (DWI) was acquired for imaging-based markers identification. The developed grading system pipeline includes: i) estimation of morphological markers using a new parametric spherical harmonic model, ii) estimation of appearance/textural markers using a novel rotation invariant circular binary pattern model, iii) calculation of the functional markers by constructing the representative cumulative distribution functions of the estimated apparent diffusion coefficients, and iv) integrating the aforementioned imaging-based markers with the associated clinical biomarkers, known as Alpha-fetoprotein. The integrated markers were optimized to train and test multiple machine learning (ML) classifiers and a hyper-tuned custom CNN. On a randomly stratified train (80%) test (20%) split scheme, the developed obtained an overall accuracy of 88% in differentiating between the three groups using the integrated markers along with the CatBoost classifier, surpassing the diagnostic performance of individual marker sets, other ML classifiers, and the CNN as well. The obta

关键词： Noninvasive medical procedures

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：