检索结果-内蒙古大学图书馆

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Cristian Rusu Paul Irofti Faculty of Automatic Control and Computers University Politehnica Bucharest Bucharest Romania Faculty of Mathematics and Computer Science Research Center for Logic Optimization and Security (LOS) University of Bucharest Bucharest Romania

ISBN: (纸本)9781665408790

Separable, or Kronecker product, dictionaries provide natural decompositions for 2D signals, such as images. In this paper, we describe a highly parallelizable algorithm that learns such dictionaries which reaches sparse representations competitive with the previous state of the art dictionary learning algorithms from the literature but at a lower computational cost. We highlight the performance of the proposed method to sparsely represent image and hyperspectral data, and for image denoising.

关键词： Training Dictionaries Conferences Machine learning Computational efficiency Distributed algorithms Image denoising

来源：评论

学校读者我要写书评

暂无评论

Implementing a solution for monitoring SLA violations in Cloud 6

Implementing a solution for monitoring SLA violations in Clo...

引用

6th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, DependSys 2020

作者： Floricu, Andreea Buzatu, Razvan Negru, Catalin Pop, Florin Castiglione, Aniello University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Romania National Institute for Research and Development in Informatics-ICI Bucharest Romania University of Naples Dipartimento di Scienze e Tecnologie Parthenope Italy

ISBN: (纸本)9781728176512

Over time, the increased use of the Internet has led to the widespread adoption of web and cloud applications. More and more applications are coming to the aid of persons or companies to make their work easier. A Service Level Agreement (SLA) gathers information about all contracted services and their expected reliability in a single document and plays a very important role when it comes to IT (Information Technology) sales. This paper examines the extent to which the SLA is complied with through a series of specific reports and graphs. The usefulness of this application is to get an overview of web services to know the frequency of situations unforeseen and the moments when they deviated from the operation in good conditions. © 2020 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Simultaneously video-based heart-rate measurement for multiple participants - an improved tiny faces approach

Simultaneously video-based heart-rate measurement for multip...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Thomas Pursche Robert Roth Marcel Walz Roland Clauß Bernd Tibken Reinhard Möller School of Electrical Information and Media Engineering Automatic Control University of Wuppertal Wuppertal Germany School of Electrical Information and Media Engineering Automation/Computer Science University of Wuppertal Wuppertal Germany

A persons heart rate is not only important for medical applications, but also for various applications among sports, psychology and many more. The conventional ways to measure the heart rate like pulseoxymetry, electrocardiogram, wrist belts and many more all have in common, that they are obtrusive and more or less inconvenient for the applicant. Because of this circumstance many different methods to measure the heart-rate contactless were introduced and presented. The most promising technique is the video based heart-rate measurement, where video data of participants are analyzed to measure the heart-rate. Most of this techniques are limited merely to one participant, wherefore the extension on a huge amount of persons seems very interesting. At the same time the accuracy of the estimated heart-rate is decreasing immense. To solve this problem we propose a new approach using the so called tiny faces algorithm [1] to increase the detection accuracy of multiple peoples face. As a direct result of this we can show, that the overall estimation accuracy is increasing for a huge amount of participants in a relative huge distance. By using a combination of the new implemented tiny faces algorithm and the heart-rate estimation algorithm we are able to enhance accuracy for great distances as well as a larger number of people concurrently measured.

关键词： Heart rate Wrist Runtime Atmospheric measurements Current measurement Estimation Particle measurements

来源：评论

学校读者我要写书评

暂无评论

Applying Transformer-Based Neural Networks to Corpus Linguistic Data for Predictive Text Generation in Multilingual Environments

Applying Transformer-Based Neural Networks to Corpus Linguis...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Taufikin Myagmarsuren Orosoo Manikandan Rengarajan Gulnaz Fatma Dilyorjon Yuldashev I Infant Raj IAIN Kudus Indonesia Mongolian National University of Education Mongolia Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India University College Al Ardah Jazan University Jazan Saudi Arabia Automatic Control and Computer Engineering Department Turin Polytechnic University in Tashkent Tashkent Uzbekistan Department of CSE K. Ramakrishnan college of Engineering Trichy Tamil Nadu India

In the subject of corpus linguistics, this study explores the use of transformer-based neural networks to the problems of predictive text production in multilingual contexts. The Transformer architecture presents a viable framework for natural language processing problems because of its reputation for capturing complex patterns and long-range dependencies in sequential data. The research employs a two-phase approach, whereby the Transformer is first pre-trained using a variety of multilingual corpora. This helps the model learn representations that are independent of language, which makes it easier for it to adapt to various linguistic circumstances. The model is then fine-tuned using language-specific datasets to improve its ability to produce linguistically nuanced and contextually appropriate text. The study looks into how different model architectures, training methods, and hyperparameters affect how well the suggested multilingual predictive text generation system performs. Evaluation measures are used to evaluate the model's performance in several languages, including linguistic diversity measurements, BLEU scores, and perplexity. The overall accuracy, calculated across all languages, stands at 80.3%, indicating the model's robust cross-lingual generalization and its effectiveness in capturing diverse linguistic nuances The efficacy and generalization of Transformer-based models are improved across a wide range of languages to handle linguistic diversity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bounding the difference between model predictive control and neural networks

arXiv

引用

arXiv 2022年

作者： Drummond, Ross Duncan, Stephen R. Turner, Matthew C. Pauli, Patricia Allgöwer, Frank Department of Engineering Science University of Oxford 17 Parks Road OxfordOX1 3PJ United Kingdom Department of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom Institute for Systems Theory and Automatic Control University of Stuttgart Stuttgart70569 Germany

There is a growing debate on whether the future of feedback control systems will be dominated by data-driven or model-driven approaches. Each of these two approaches has their own complimentary set of advantages and disadvantages, however, only limited attempts have, so far, been developed to bridge the gap between them. To address this issue, this paper introduces a method to bound the worst-case error between feedback control policies based upon model predictive control (MPC) and neural networks (NNs). This result is leveraged into an approach to automatically synthesize MPC policies minimising the worst-case error with respect to a NN. Numerical examples highlight the application of the bounds, with the goal of the paper being to encourage a more quantitative understanding of the relationship between data-driven and model-driven control. © 2022, CC BY.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Stochastic Stability of Discrete-time Phase-coupled Oscillators over Uncertain and Random Networks

arXiv

引用

arXiv 2021年

作者： Jafarian, Matin Mamduhi, Mohammad H. Johansson, Karl H. The Delft Center for Systems and Control Delft University of Technology Netherlands The Automatic Control Laboratory ETH Zürich Switzerland The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Digital Futures Sweden

This article studies stochastic relative phase stability, i.e., stochastic phase-cohesiveness, of discrete-time phase-coupled oscillators. Stochastic phase-cohesiveness in two types of networks is studied. First, we consider oscillators coupled with 2π-periodic odd functions over underlying undirected graphs subject to both multiplicative and additive stochastic uncertainties. We prove stochastic phase-cohesiveness of the network with respect to two specific, namely in-phase and anti-phase, sets by deriving sufficient coupling conditions. We show the dependency of these conditions on the size of the mean values of additive and multiplicative uncertainties, as well as the sign of the mean values of multiplicative uncertainties. Furthermore, we discuss the results under a relaxation of the odd property of the coupling function. Second, we study an uncertain network in which the multiplicative uncertainties are governed by the Bernoulli process representing the well-known Erdös-Rényi network. We assume constant exogenous frequencies and derive sufficient conditions for achieving both stochastic phase-cohesive and phase-locked solutions, i.e., stochastic phase-cohesiveness with respect to the origin. For the latter case, where identical exogenous frequencies are assumed, we prove that any positive probability of connectivity leads to phase-locking. Thorough analyses are provided, and insights obtained from stochastic analysis are discussed, along with numerical simulations to validate the analytical results. © 2021, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

An exponential stability test for a messenger rna–micro rna ode model

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2020年第4期82卷 11-16页

作者： Olteanu, Mircea Ştefan, Radu Department of Mathematical Methods and Models Faculty of Applied Sciences University "Politehnica" of Bucharest Romania Department of Automatic Control and Systems Engineering Faculty of Automatic Control and Computer Science University "Politehnica" of Bucharest Romania

In this paper we obtain a numerically tractable test (sufficient condition) for the exponential stability of the unique positive equilibrium point of an ODE system. The result (Theorem 3.1) is based on Lyapunov theory and Linear Ma-trix Inequalities techniques. The ODE model is related to the messengerRNA-microRNA interaction. © 2020, Politechnica University of Bucharest. All rights reserved.

关键词： RNA

来源：评论

学校读者我要写书评

暂无评论

BrightBox — A rough set based technology for diagnosing mistakes of machine learning models

引用

Applied Soft Computing 2023年 141卷

作者： Janusz, Andrzej Zalewska, Andżelika Wawrowski, Lukasz Biczyk, Piotr Ludziejewski, Jan Sikora, Marek Ślęzak, Dominik QED Software sp. z o.o. Mazowiecka 11/49 Warsaw00-052 Poland Institute of Informatics University of Warsaw Banacha 2 Warsaw02-097 Poland Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 16 Gliwice44-100 Poland Research Network Lukasiewicz – Institute of Innovative Technologies EMAG ul. Leopolda 31 Katowice40–189 Poland

The paper presents a novel approach to investigating mistakes in machine learning model operations. The considered approach is the basis for BrightBox – a diagnostic technology that can be used for analyzing prediction models and identifying model- and data-related issues. The idea is to generate surrogate rough set-based models from data that approximate decisions made by monitored black-box models. Such approximators are used to compute neighborhoods of instances that undergo the diagnostic process — the neighborhoods consist of historical instances that were processed in a similar way by rough set-based models. The diagnostic process is then based on the analysis of mistakes registered in such neighborhoods. The experiments performed on real-world data sets confirm that such analysis can provide us with efficient and valid insights about the reasons for the poor performance of machine learning models. © 2023

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

RLS-based control algorithms for 3D zones of quiet 55

RLS-based control algorithms for 3D zones of quiet

引用

55th Open Seminar on Acoustics, OSA 2008

作者： Michalczyk, Malgorzata I. Serwin, Janusz Institute of Automatic Control Silesian University of Technology Akademicka 16 Gliwice44-100 Poland Graduated in Automatic Control and Robotics Department of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland

ISBN: (纸本)8392166302

The paper summarises research on application of RLS-based adaptive control algorithms for single-channel active noise control (ANC) system, used to create three dimensional (3D) local zones of quiet in a reverberant enclosure by attenuation of tonal disturbances. Three different ANC system structures are concerned: classical and modified 'filtered-x' and 'adjoint' structure. The problem of parameterisation of six RLS-based adaptive control algorithms is evaluated, firstly, in simulations with the use of nonsimplified plant models and tonal disturbances. Next, research results are proved in real-world experiments. Finally, the efficiency of ANC systems using different control structures and RLS-based control algorithms is compared. © AIChE Southwest Process Technology Conference *** right reserved.

关键词： Active noise control

来源：评论

学校读者我要写书评

暂无评论

Segmenting Alzheimer's Disease MRI Slices for Hippocampal Volume Calculation

Segmenting Alzheimer's Disease MRI Slices for Hippocampal Vo...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Hsiao-Chuan Tan Gilang Titah Ramadhan Wei-Cheng Shen Wen-Thong Chang Chih-Yang Lin Ben-Yi Liau Yih-Kuen Jan Yori Pusparani Chi-Wen Lung Department of Artificial Intelligence PhD Program Asia University Taichung Taiwan Department of Computer Science and Information Engineering Asia University Taichung Taiwan Department of Creative Product Design Asia University Taichung Taiwan Department of Mechanical Engineering National Central University Taoyuan Taiwan Department of Automatic Control Engineering Feng Chia University Taichung Taiwan Department of Kinesiology and Community Health University of Illinois Urbana America Department of Digital Media Design Asia University Taichung Taiwan

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

Alzheimer's is a neurodegenerative disease that quietly steals human memory. This study analyzed hippocampal volume in Alzheimer's Disease (AD), Mild Cognitive Impairment (MCI), and Normal Cognition (NC) using MRI image slices from the ADNI database and YOLOv8 instance segmentation. We used 300 images to segment the left and right hippocampal. This study focused on volume calculation from five MRI image slices. The results showed 0.98 (AD), 0.92 (MCI), and 0.90 (NC) and revealed significant volumetric differences showed in the NC class (P = 0.045). This suggests early neuroanatomical changes can occur without cognitive symptoms, highlighting the potential of deep learning in the early detection of neurodegenerative diseases.

关键词： Instance segmentation Deep learning Accuracy Databases Magnetic resonance imaging Cognition Alzheimer's disease

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：