检索结果-内蒙古大学图书馆

Online Adaption of Motion Paths to Time-Varying Constraints using Homotopies

IFAC-PapersOnLine 2017年第1期50卷 3331-3337页

作者： Kontny D. Stursberg O. Control and System Theory Dept. of Electrical Engineering and Computer Science University of Kassel Germany

This paper presents a method for optimal point-to-point control of linear discrete-time systems with time-varying non-convex state constraints, as arising for problems of avoiding moving obstacles. While common approaches like MPC with mixed-integer programming (MIP) can quickly become time-demanding, the presented approach efficiently computes circumventing near-optimal trajectories by using homotopy properties. In a first step, a range of offline selected trajectories is used to span a region of homotopic trajectories, for which the transitioning behavior between these is determined by semi-definite programming (SDP). The online part then determines with low computational effort a collision-free and near-optimal homotopic trajectory. The procedure maps the moving obstacles for relevant collision-critical time steps into the homotopy space, and determines a suitable trajectory by a tree-search of moderate size. The circumventing trajectories and the resulting computation times are illustrated by simulation. © 2017

关键词： constrained control model predictive control non-convex optimization obstacle avoidance optimal trajectory Real-time control

来源：评论

学校读者我要写书评

暂无评论

Verification code recognition based on active and deep learning

arXiv

引用

arXiv 2019年

作者： Xu, Dongliang Wang, Bailing Du, XiaoJiang Zhu, Xiaoyan Guan, Zhitao Yu, Xiaoyan Liu, Jingyu School of Computer Science and Technology Shandong University Weihai China School of Computer Science and Technology Harbin Institute of Technology Weihai China Department of Computer and Information Sciences Temple University PhiladelphiaPA United States Computer information center Xidian University Xi'an China School of Control and Computer Engineering North China Electric Power University Beijing China Dept. of Computer Science and Technology Capital Normal University Beijing China Computer information center Intermediate People's Court Weihai China

A verification code is an automated test method used to distinguish between humans and computers. Humans can easily identify verification codes, whereas machines cannot. With the development of convolutional neural networks, automatically recognizing a verification code is now possible for machines. However, the advantages of convolutional neural networks depend on the data used by the training classifier, particularly the size of the training set. Therefore, identifying a verification code using a convolutional neural network is difficult when training data are insufficient. This study proposes an active and deep learning strategy to obtain new training data on a special verification code set without manual intervention. A feature learning model for a scene with less training data is presented in this work, and the verification code is identified by the designed convolutional neural network. Experiments show that the method can considerably improve the recognition accuracy of a neural network when the amount of initial training data is small. Copyright © 2019, The Authors. All rights reserved.

关键词： Testing

来源：评论

学校读者我要写书评

暂无评论

Application of the Generalized Demodulation Time-Frequency Analysis Method to Vibration Signals Under Varying Speed

Application of the Generalized Demodulation Time-Frequency A...

引用

International Conference on Image, Vision and Computing (ICIVC)

作者： Yan Li Li Du Dept. Computer Liaoning Equipment Manufacturing Vocational and Technical College Shenyang China Dept. Control Science and Engineering Shenyang University Shenyang China

ISBN: (纸本)9781538649923

Instantaneous frequency is a primary parameter used for analyzing vibration signals of rolling bearings under harsh working conditions, which contains rich information besides the rotating speeds of the shaft. Such vibration signals exhibits characteristics of non-stationary and multi-components. The generalized demodulation time-frequency analysis approach is a novel signal processing method, which is suitable for processing non-stationary and multi-component signals. Its novelty lies in that the signal whose time-frequency distributions are curved paths can be transformed into that whose time-frequency distributions are linear paths paralleling time axis by using generalized demodulation. In this paper, to deal with the vibration signals under variable working speed condition, the generalized demodulation as well as a band-pass filter is used to separate the interested component from original vibration signal. The analysis results demonstrate the validity of the proposed approach.

关键词： Time-frequency analysis Demodulation Vibrations Rolling bearings Frequency estimation Transforms

来源：评论

学校读者我要写书评

暂无评论

Detection and Tracking of Astral Microtubules in Fluorescence Microscopy Images

Detection and Tracking of Astral Microtubules in Fluorescenc...

引用

IEEE International Conference on Image Processing

作者： Joshua Levine Marco Grangetto Marilena Varrecchia Gabriella Olmo Computer Science dept. Università degli Studi di Torino Torino Italy Dept. of Control and Computing Engineering Politecnico di Torino Torino Italy

In this paper we explore detection and tracking of astral micro-tubules, a sub-population of microtubules which only exists during and immediately before mitosis and aids in the spindle orientation by connecting it to the cell cortex. Its analysis can be useful to determine the presence of certain diseases, such as brain pathologies and cancer. The proposed algorithm focuses on overcoming the problems regarding fluorescence microscopy images and microtubule behaviour by using various image processing techniques and is then compared with three existing algorithms, tested on consistent sets of images.

关键词： Microscopy Standards Image segmentation Signal to noise ratio Heuristic algorithms Fluorescence Drugs

来源：评论

学校读者我要写书评

暂无评论

An Economic Tracking Scheme for GPS-GSM Based Moving Object Tracking System

An Economic Tracking Scheme for GPS-GSM Based Moving Object ...

引用

International Conference for engineering, Technology and Sciences of Al-Kitab (ICETS)

作者： Fatima Nadhim Ameen Ziad Saeed Mohammed Abdulrahman Ikram Sddiq Dept. of Computer Engineering Technical College Northern Technical University Mosul Iraq Dept. of Electronic and Control Eng. Northern Technical University Kirkuk Iraq

ISBN: (纸本)9781538635797

Many tracking systems are based on the Global Positioning System (GPS), Global System for Mobile communications (GSM) and smart phones, due to their wide availability and reliability. A moving object to be tracked, it sends its GPS coordinates to the observer via SMS. However, the economic feasibility of these systems mainly depends on the total cost of the used SMS messages. In this paper, an economic tracking scheme is proposed to reduce the tracking cost. A GPS-GSM tracking system that uses the proposed scheme is implemented and tested together with two classical tracking systems under two practical test cases. The first test case is a 121 km vehicle trip and the second is a 2.4 km walking journey. The results showed the effectiveness and economic feasibility of the proposed system, which achieved a saving in tracking cost up to about 64% with respect to the tested classical systems.

关键词： Tracking Servers Global Positioning System GSM Economics Smart phones Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

Deep autoencoder for off-line design-space dimensionality reduction in shape optimization

Deep autoencoder for off-line design-space dimensionality re...

引用

AIAA/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference, 2018

作者： D’Agostino, Danny Serani, Andrea Diez, Matteo Campana, Emilio F. Dept. of Computer Control and Management Engineering ‘A. Ruberti’ Sapienza University of Rome CNR-INSEAN Via Ariosto 25 Rome00185 Italy CNR-INSEAN National Research Council-Marine Technology Research Institute Via di Vallerano 139 Rome00128 Italy CNR-DIITET National Research Council-Dept. of Engineering ICT and Technologies for Energy and Transportation Piazzale Aldo Moro 7 Rome00185 Italy University of Iowa United States

ISBN: (数字)9781624105326

ISBN: (纸本)9781624105326

In shape optimization, design improvements significantly depend on the dimension and variability of the design space. High dimensional and variability spaces are more difficult to explore, but also usually allow for more significant improvements. The assessment and breakdown of design-space dimensionality and variability are therefore key elements to shape optimization. A linear method based on the principal component analysis has been developed in earlier research to build a reduced-dimensionality design-space, resolving the 95% of the original geometric variance. The paper presents an extension of the method to more efficient nonlinear approaches. Specifically, the use of a deep autoencoder is presented and discussed. The method is demonstrated for the design-space dimensionality reduction and hydrodynamic optimization of the hull form of a USS Arleigh Burke-class destroyer. A comparison with the linear method is finally shown and discussed. © 2018, (publisher Name). All Rights reserved.

关键词： Shape optimization

来源：评论

学校读者我要写书评

暂无评论

Structured learning for context-aware spoken language understanding of robotic commands 1

Structured learning for context-aware spoken language unders...

引用

1st Workshop on Language Grounding for Robotics, RoboNLP 2017 at the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017

作者： Vanzo, Andrea Croce, Danilo Basili, Roberto Nardi, Daniele Sapienza University of Rome Dept. of Computer Control and Management Engineering "Antonio Ruberti" Italy University of Roma Tor Vergata Dept. of Enterprise Engineering Italy

ISBN: (纸本)9781945626647

Service robots are expected to operate in specific environments, where the presence of humans plays a key role. A major feature of such robotics platforms is thus the ability to react to spoken commands. This requires the understanding of the user utterance with an accuracy able to trigger the robot reaction. Such correct interpretation of linguistic exchanges depends on physical, cognitive and language-dependent aspects related to the environment. In this work, we present the empirical evaluation of an adaptive Spoken Language Understanding chain for robotic commands, that explicitly depends on the operational environment during both the learning and recognition stages. The effectiveness of such a context-sensitive command interpretation is tested against an extension of an already existing corpus of commands, that introduced explicit perceptual knowledge: This enabled deeper measures proving that more accurate disambiguation capabilities can be actually obtained. © 2017 Proceedings of the 1st Workshop on Language Grounding for Robotics, RoboNLP 2017 at the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017. All rights reserved.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

IoT Software Infrastructure for Remote Monitoring of Patients with Chronic Metabolic Disorders

IoT Software Infrastructure for Remote Monitoring of Patient...

引用

International Conference on Future Internet of Things and Cloud (FiCloud)

作者： Edoardo Patti Maria Donatelli Enrico Macii Andrea Acquaviva Dept. of Control and Computer Engineering Politecnico di Torino Torino Italy Biomedical Dept. of Internal and Specialistic Medicine University of Palermo Palermo Italy Interuniversity Dept. of Regional and Urban Studies and Planning Politecnico di Torino Torino Italy

ISBN: (纸本)9781538675045

Novel Information and Communication Technologies, such as Internet-of-Things (IoT), middleware and cloud computing, are providing innovative solutions ranging in different contexts. Smart health is one of these scenarios. Indeed, there is a rising interest in developing new healthcare services for remote patient assistance and monitoring. Among all, the main promised benefits consist on improving the patients' quality of life, speeding up therapeutic interventions and reducing hospitalizations' costs. This is also known as Telemedicine. In this paper, we present a novel distributed software infrastructure for remote monitoring of patients with chronic metabolic disorders: i) it collects and and makes available information coming from IoT devices, ii) it performs analysis to help medical diagnosis and iii) it promotes a bidirectional communication among the end-users (i.e. medical personnel and patients). In this paper, we also present our experimental results performed in a laboratory test environment to validate the proposed solution.

关键词： Medical services Medical diagnostic imaging Cloud computing Monitoring Middleware Telemedicine

来源：评论

学校读者我要写书评

暂无评论

Considerations regarding security issues impact on systems availability

arXiv

引用

arXiv 2018年

作者： Pricop, Emil Mihalache, Sanda Florentina Paraschiv, Nicolae Fattahi, Jaouhar Zamfir, Florin Automatic Control Computers and Electronics Department Petroleum-Gas University of Ploiesti Ploiesti Romania Dept. of Computer Science and Software Engineering Université Laval QC Canada Automatic Control Computers and Electronics Dept. Petroleum-Gas University of Ploiesti Ploiesti Romania

control systems behavior can be analyzed taking into account a large number of parameters: Performances, reliability, availability, security. Each control system presents various security vulnerabilities that affect in lower or higher measure its functioning. In this paper the authors present a method to assess the impact of security issues on the systems availability. A fuzzy model for estimating the availability of the system based on the security level and achieved availability coefficient (depending on MTBF and MTR) is developed and described. The results of the fuzzy inference system (FIS) are presented in the last section of the paper. Copyright © 2018, The Authors. All rights reserved.

关键词： Availability

来源：评论

学校读者我要写书评

暂无评论

Refining Dynamics Identification for Co-Bots: Case Study on KUKA LWR4+

引用

IFAC-PapersOnLine 2017年第1期50卷 14626-14631页

作者： Kolyubin, Sergey A. Shiriaev, Anton S. Jubien, Anthony Dept. of Computer Science and Control Systems ITMO University St. Petersburg197101 Russia Dept. of Engineering Cybernetics NTNU TrondheimNO-7491 Norway Nantes Digital Sciences Laboratory LS2N Nantes44300 France

This paper presents an attempt to improve dynamic identification procedure for robotic manipulators, such that obtained models are appropriate for trajectory planning and motion control. In addition to algorithms development, authors bring new insights and arguments for the experiments organisation and analysis of the collected data. Significant part of the work is devoted to a case study in calibrating of a collaborative robot (co-bot) KUKA LWR4+, which represents a powerful tool for modern manufacturing systems. Therefore, refined models compared to the ones relied on CAD data provided by the manufacturer can be beneficial for various applications. © 2017

关键词： Robot programming

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：