检索结果-内蒙古大学图书馆

E-Health and Bioengineering Conference (EHB)

作者： Lavinia Ferariu Angela Mihalachi Dept. of Automatic Control and Applied Informatics “Gheorghe Asachis” Technical University of Iasi Iasi Romania

ISBN: (数字)9781665485579

ISBN: (纸本)9781665485586

Electroencephalogram (EEG) signals can be used for discriminating between ictal and non-ictal phases, to protect people affected by epilepsy. Recent studies show the ability of autoencoders (AEs) to learn valuable EEG abstractions that can be effectively processed by classifiers. To some extent, information from previous frames could be useful for detection. However, the design should avoid using AEs with large input sizes, to prevent unsuccessful feature learning. This paper discusses AE-based schemes which allow the investigation of multiple successive frames. A hierarchical feature extractor is introduced to correlate long-term information via AEs of reduced input sizes, to support easy training. The experimental results indicate improved detection accuracy for the classification based on the proposed multi-frame hierarchical feature extractor, compared to feature extractors that work on a single frame, or use a priori/ a posteriori aggregation of frames.

关键词： Training Representation learning Codes Memory management Epilepsy Feature extraction Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Navigating Language and Terminology in automatic control Literature ⁎

引用

IFAC-PapersOnLine 2024年第7期58卷 109-114页

作者： M. Bauer F. Norlund E. Westin S. Knorn Lund University Dept. Automatic Control Lund Sweden University of Applied Sciences Hamburg Germany Boliden AB Boliden Sweden Technische Universität Berlin Chair of Control Berlin Germany

Much of our understanding of automatic control relies on descriptions and words. While rooted in mathematical theory, control is generally explained using examples and abstraction. Different terminology is used in different textbooks which can lead to inadvertent miscommunication. Here, the terminology introduced in the most frequently used textbooks is collated. The paper addresses lecturers, students and industrial practitioners alike, who need to communicate, not only for understanding but also when building control systems. The focus is on English terminology of the single control loop and the PID controller. A section is dedicated to the Swedish and German language, highlighting helpful as well as obstructive vocabulary. This article provides an overview to raise awareness and to serve as a basis for discussion. It is not intended to be a complete list of words that should or should not be used.

关键词： automatic control terminology control language communication technology transfer control engineering education

来源：评论

学校读者我要写书评

暂无评论

control of the organizational System Configuration in the Context of Digital Transformation 6

Control of the organizational System Configuration in the Co...

引用

6th International Scientific Conference on Information, control, and Communication Technologies, ICCT 2022

作者： Protalinsky, Oleg M. Khanova, Anna A. Bondareva, Irina O. Nesterova, Evgeniya T. Moscow Power Engineering Institute Dept. of Automated Control Systems of Thermal Processes Moscow Russia Astrakhan State Technical University Dept. Applied Informatics Astrakhan Russia

ISBN: (数字)9781665493673

ISBN: (纸本)9781665493673

With the development of digitalization and digital transformation processes, there is a concern of consolidating strategic control methods based on the balanced scorecard (BSC), data envelopment analysis (DEA) and logical-and-probabilistic approach, as well as creating on their basis a conceptual control scheme of organizational systems configurations. The question of forming a strategic map of digital transformation based on artificial neural networks is considered. In order to assess the effectiveness it is proposed to use a bunch of BSC-DEA methods. To assess the risk of failure to achieve the strategic objectives of the digital transformation of organizational systems, a bundle of MTSP-logic-probabilistic model was proposed. It is proposed to use a digital twin of the organizational system based on a simulation model to test the feasibility of control decisions in the context of digital incrementation in various situations of operation of the organizational system, at various stages of the intra-configuration cycle. © 2022 IEEE.

关键词： Data envelopment analysis

来源：评论

学校读者我要写书评

暂无评论

Front-Office Management of Service Operations with Robotic Process Automation

Front-Office Management of Service Operations with Robotic P...

引用

International Conference on control Systems and Computer Science (CSCS)

作者： Radu-Florin Negoiţă Theodor Borangiu Doctoral School of Automatic Control and Computers University Politehnica of Bucharest Bucharest Romania Dept. of Automatic Control and Industrial Informatics University Politehnica of Bucharest Bucharest Romania

Coordinating service capacity with dynamic varying, market-driven customer demand in a service business imposes correlating and synchronizing front-office and back-office processes - the first addressing customer relationship management and the second inventory planning, forecasting demand, analytics, and strategic decision making. Front office management (FOM) contributes substantially in coordinating the services requested by guests, and needs to be integrated in an Operations Management Software system specific for hotel business. Research efforts are currently directed towards automating repetitive, time consuming operations included in front office processes that are in great number, initiated by random events and customer actions with variable timing. The paper presents a solution to automate FOM operations that are kept consistent with the business strategy of the organization, and assist front-office workflows involving customers (service requests, service quality assessment) and front line personnel (registration, check in, check out, taxation and invoicing). The solution is based on the Robotic Process Automation (RPA) technology extended with AI-based functionalities for the intelligent process automation and integration with back-office workflows.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A latent representation of brain networks based on EEG ⁎

引用

IFAC-PapersOnLine 2024年第15期58卷 414-419页

作者： Lucia Falconi Giulia Cisotto Mattia Zorzi Automatic Control Laboratory ETH Zurich Physikstrasse 3 8092 Zurich Switzerland Dept. of Informatics Systems and Communication University of Milano-Bicocca Milan Italy Dept. of Information Engineering University of Padova Italy Dept. of Information Engineering University of Padova Italy

Electroencephalography (EEG) is one of the most popular techniques to investigate normal as well as pathological cerebral mechanisms, as it allows to measure, non-invasively and in real-time, the brain activity. However, modeling EEG is still extremely challenging, because of its high-dimensionality, low signal-to-noise ratio, and high individual variability. This paper proposes a novel latent representation to study brain networks using EEG by means of a robust dynamic factor analysis (RDFA) approach. We investigate the ability of this latent representation to discriminate between two groups of subjects, i.e. alcoholic and healthy. By RDFA, we can extract a limited number of highly explanatory factors, as low as 8, significantly discriminating between the two groups. Also, we show that different brain patterns can be identified across different stimulation scenarios and EEG locations. Although preliminary, this work could give support to domain experts while providing some clinically-meaningful insights to identify common patterns as well as individual characteristics in different groups of healthy and pathological subjects.

关键词： EEG system identification dynamic factor analysis

来源：评论

学校读者我要写书评

暂无评论

Mobile Application for Visualizing the Measurements 5

Mobile Application for Visualizing the Measurements

引用

5th IEEE International Conference on Modern Electrical and Energy System, MEES 2023

作者： Kiresova, Simona Guzan, Milan Sobota, Branislav Melnykov, Viacheslav Yatsiuk, Rostyslav Peryvertailo, Bohdan Technical University of Košice Dept. of Theoretical and Industrial Electrical Engineering Košice Slovakia Technical University of Košice Dept. of Computers and Informatics Košice Slovakia Kremenchuk Mykhailo Ostrohradskyi National University Dept. of Systems of Automatic Control and Electric Drive Kremenchuk Ukraine National University Dept. of Computer Engineering and Electronics Kremenchuk Mykhailo Ostrohradskyi Kremenchuk Ukraine

ISBN: (纸本)9798350359787

This paper deals with the design of an Android mobile application and visualization of the measured values of particulate matter and meteorological factors from the measurement stations. The application can in principle be effectively used in any field of data visualization. The architecture of the mobile application, the security, the use of AWS services to access the data in the InfluxDB databases, as well as the user interface and graphical visualizations of the measured data are described and illustrated. The application is user tested and the paper documents their first experiences using the mobile application. © 2023 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Multi-robot Motion Planning based on Nets-within-Nets Modeling and Simulation

arXiv

引用

arXiv 2023年

作者： Hustiu, Sofia Robillard, Eva Ezpeleta, Joaquín Mahulea, Cristian Kloetzer, Marius Dept. of Automatic Control and Applied Informatics Technical University "Gheorghe Asachi" of Iasi Romania ENS Paris-Saclay Université Paris-Saclay France University of Zaragoza Spain

This paper focuses on designing motion plans for a heterogeneous team of robots that has to cooperate in fulfilling a global mission. The robots move in an environment containing some regions of interest, and the specification for the whole team can include avoidances, visits, or sequencing when entering these regions of interest. The specification is expressed in terms of a Petri net corresponding to an automaton, while each robot is also modeled by a state machine Petri net. With respect to existing solutions for related problems, the current work brings the following contributions. First, we propose a novel model, denoted High-Level robot team Petri Net (HLPN) system, for incorporating the specification and the robot models into the Nets-within-Nets paradigm. A guard function, named Global Enabling Function (gef), is designed to synchronize the firing of transitions such that the robot motions do not violate the specification. Then, the solution is found by simulating the HPLN system in a specific software tool that accommodates Nets-within-Nets. An illustrative example based on a Linear Temporal Logic (LTL) mission is described throughout the paper, complementing the proposed rationale of the framework. © 2023, CC BY.

关键词： Specifications

来源：评论

学校读者我要写书评

暂无评论

Tube-based coalitional MPC with plug-and-play features

引用

IFAC-PapersOnLine 2023年第2期56卷 7704-7709页

作者： E. Masero P.R. Baldivieso-Monasterios J.M. Maestre P.A. Trodden E.F. Camacho Dept. of Ingeniería de Sistemas y Automática Universidad de Sevilla Spain Dept. of Automatic Control and Systems Engineering University of Sheffield UK Dept. of Systems Science Graduate School of Informatics Kyoto University Japan

This paper presents a distributed setting of model predictive control (MPC) to manage linear multi-agent systems consisting of coupled subsystems. Specifically, local controllers can work in coalitions to improve performance and handle plug-and-play events. This study provides insight into a coalitional MPC strategy based on optimized tubes that handles plug-in and plug-out subsystems. Moreover, we explore an inherent robustness gap to absorb disturbances not covered by the tubes without having to group local controllers. A comparison of our approach with centralized and decentralized MPC is reported using an illustrative example.

关键词： Model predictive control distributed control multi-agent systems time-varying systems robust control plug-and-play events

来源：评论

学校读者我要写书评

暂无评论

Parallel Motion Execution and Path Rerouting for a Team of Mobile Robots

引用

IFAC-PapersOnLine 2022年第28期55卷 73-78页

作者： Sofia Hustiu Cristian Mahulea Marius Kloetzer Aragón Institute of Engineering Research (I3A) University of Zaragoza Spain Dept. of Automatic Control and Applied Informatics Technical University “Gheorghe Asachi” of Iasi Romania

This work achieves parallel movements and collision free paths for a team of identical robots evolving in a known environment while satisfying a global Boolean-based formula over a set of regions of interest. The movement capabilities of the robots within the grid-based environment are modeled as a Petri net system. The solution starts from initially known robot paths given by the approach in (Mahulea et al., 2020b). The main advantages of this work are two-folded: (i) it reduces the number of waiting states of the robots throughout their paths, (ii) it considers path rerouting action solved by a MILP problem, without generating new observations along their paths. The rerouting is triggered when the number of robots that are waiting is greater than a threshold, or when some stopped robots inhibit the movement of others. Thus, the proposed method yields parallel movement of robots and path rerouting when needed. The algorithm is integrated in the open-source toolbox RMTool (González et al., 2015).

关键词： Petri net Boolean-based specification Multi-robot system

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Loewner Matrices-Based Modeling and Model Predictive control of a Single Machine Infinite Bus Model 32

Data-Driven Loewner Matrices-Based Modeling and Model Predic...

引用

32nd Mediterranean Conference on control and Automation, MED 2024

作者： Ionescu, T.C. Iftime, O.V. Necoara, I. Politehnica Bucharest Dept. of Automatic Control & Systems Eng. Bucharest060042 Romania 'G. Mihoc-C. Iacob' Institute of Mathematical Statistics and Applied Mathematics The Romanian Academy Bucharest050711 Romania University of Groningen Faculty of Economics and Business Department of Economics Econometrics and Finance Groningen9747 AE Netherlands

ISBN: (纸本)9798350395440

In this paper, we consider the problem of data-driven modelling and model predictive control (MPC) of a single machine infinite bus system (SMIB). When a linear state-space model of the plant is not available, a pair of Loewner matrices is constructed from a set of measured input-output data and a set of prescribed poles. We prove that the Loewner matrices are the solutions of two Sylvester equations. We compute the unique linear model of an order equal to the dimension of the data sets, that interpolates the input-output data and that has all the poles prescribed at the selected locations. As an application we perform MPC on both the original system and its approximant. The simulation show that the linear data-driven model is a good approximation of the SMIB and achieves good closed-loop MPC performance. © 2024 IEEE.

关键词： Model predictive control

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：