检索结果-内蒙古大学图书馆

Generative Adversarial Networks:Introduction and Outlook

IEEE/CAA Journal of Automatica Sinica 2017年第4期4卷 588-598页

作者： Kunfeng Wang Chao Gou Yanjie Duan Yilun Lin Xinhu Zheng Fei-Yue Wang IEEE State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Qingdao Academy of Intelligent Industries State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences University of Chinese Academy of Sciences Department of Computer Science and Engineering University of Minnesota Research Center for Computational Experiments and Parallel Systems Technology National University of Defense Technology

Recently, generative adversarial networks(GANs)have become a research focus of artificial intelligence. Inspired by two-player zero-sum game, GANs comprise a generator and a discriminator, both trained under the adversarial learning *** goal of GANs is to estimate the potential distribution of real data samples and generate new samples from that *** their initiation, GANs have been widely studied due to their enormous prospect for applications, including image and vision computing, speech and language processing, etc. In this review paper, we summarize the state of the art of GANs and look into the future. Firstly, we survey GANs' proposal background,theoretic and implementation models, and application ***, we discuss GANs' advantages and disadvantages, and their development trends. In particular, we investigate the relation between GANs and parallel intelligence,with the conclusion that GANs have a great potential in parallel systems research in terms of virtual-real interaction and integration. Clearly, GANs can provide substantial algorithmic support for parallel intelligence.

关键词： ACP approach adversarial learning generative adversarial networks(GANs) generative models parallel intelligence zero-sum game

来源：评论

学校读者我要写书评

暂无评论

Model-based detection of actuator faults in the presence of modelling errors 6

Model-based detection of actuator faults in the presence of ...

引用

6th European control Conference, ECC 2001

作者： Juricic, D. Zele, M. Department of Computer Automation and Control Jožef Stefan Institute Jamova 39 Ljubljana1000 Slovenia

ISBN: (纸本)9783952417362

The problem of detecting actuator faults in the presence of modelling errors is addressed. A likelihood-ratio test is derived such that the effects of undermodelling are properly taken into account via a stochastic embedding technique. The resulting test takes form of the quadratic sum of prediction errors which has to be compared with a particular threshold value. Systematic choice of the threshold amounts to a demanding problem of approximating the distribution of the test statistics with normal distribution. The effectiveness of the test is demonstrated on a simulated motor-generator system. © 2001 EUCA.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Robust detection of faults in command inputs 15th

Robust detection of faults in command inputs

引用

15th World Congress of the International Federation of Automatic control, 2002

作者： Juričić, Dani Žele, Mina Department of Computer Automation and Control Jožef Stefan Institute Jamova 39 Ljubljana1000 Slovenia

ISBN: (纸本)9783902661746

The problem of robust fault detection in command inputs in the presence of modelling errors in linear time-invariant systems is addressed. The problem leads to a hypothesis test with a test statistic taking form of a weighted quadratic sum of independent normally distributed variables. It is rather difficult to compute the threshold for such a test and the corresponding error probabilities in an exact manner. Instead, the approximative results are derived by assuming assymptotic distribution of the test statistic towards normal distribution. Convergence conditions in case of growing number of summands are presented. Performance of the resulting detector is demonstrated on a simulated DC motor-generator rig. Copyright © 2002 IFAC.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Qualitative diagnostic toolbox employing propagation models

Qualitative diagnostic toolbox employing propagation models

引用

1999 European control Conference, ECC 1999

作者： Kavcic, M. Juricic, D. Department of Computer Automation and Control J. Stefan Institute Jamova 39 Ljubljana1000 Slovenia

ISBN: (纸本)9783952417355

The main motivation of the presented work is to realise a prototype of the CAD tool that supports the whole life cycle of the diagnostic system development process. In the proposed approach, the fault trees are automatically derived from component models. The automatic synthesis incorporates the feedback control loop structure. Fault trees are then transformed into diagnostic rules. The implemented CAD tool allows for rule processing by using the Transferable Belief Model (TBM). The limitations of the component-based synthesis of fault trees are discussed. © 1999 EUCA.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

A graphical Petri net based editor for a visualization of distributed and parallel systems 2nd

A graphical Petri net based editor for a visualization of di...

引用

2nd Joint International Conference on Vector and Parallel Processing, CONPAR 1992

作者： Anisimov, Nikolay Kovalenko, Aleksey Postupalski, Pavel Simanchuk, Aleksey Laboratory of Computer Networks Institute of Automation & Control Processes 5 Radio Street Vladivostok690032 Russia

ISBN: (纸本)9783540558958

This paper is a presentation of the ongoing research project being under development at the institute of automation and control processes (Vladivostok, Russia). The main purpose of the project is to develop a prototype of computer aided tools for specification development in a graphical mode based on Petri nets. The project includes a development of two-level editor that consists of a Petri net editor with algebraic facilities and an architectural editor. Some outcomes of the project are reported. © Springer-Verlag Berlin Heidelberg 1992.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

Recognize User Intents in Online Interactions from Massive Social Media Data 2

Recognize User Intents in Online Interactions from Massive S...

引用

2017 IEEE 2nd International Conference on Big Data Analysis（ICBDA 2017）

作者： Chenxi Cui Wenji Mao State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Computer and Control Engineering University of Chinese Academy of Sciences

ISBN: (纸本)9781509036202

Online interactions,especially user generated contents on social events,reveal a variety of communicative purposes ranging from expressing feelings to proposing *** intents in users' online interactive behavior from massive social media data can effectively identify users' motives and intents behind communication and provide important information to aid monitoring,analysis and decision making for a variety of ***,user intents recognition from online communication is inherently challenging due to the ambiguity in semantic processing and diversity of syntax ***,the massive online data are usually unlabeled,which greatly hinders the usage of typical machine learning based methods that can automate the recognition *** this paper,we tackle this problem by proposing a Speech Act Theory guided classification scheme,which regards online communication as performative actions of users and classifies user utterances according to their pragmatic *** the basis of this,we construct a dictionary of performative words,expand it using external knowledge sources and refine it by word embedding and similarity *** then use this dictionary to automatically label the online textual data with *** a large amount of the labeled data,we train feature based classifiers to identify user intents in their online *** experimental study using a microblog dataset on social events from Sina Weibo shows the effectiveness of our proposed method.

关键词： user intent recognition speech act theory online communication social media big data

来源：评论

学校读者我要写书评

暂无评论

Motion Detection Based on Improved Sobel and ViBe Algorithm 35

Motion Detection Based on Improved Sobel and ViBe Algorithm

引用

第35届中国控制会议

作者： ZHANG Yujia ZHAO Xiaoguang TAN Min State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences University of Chinese Academy of Sciences School of Computer and Control Engineering

ISBN: (纸本)9781509009107

Motion detection plays a crucial role in most video based applications.A particular background subtraction technique called ViBe(Visual Background Extractor) is commonly used to obtain foreground objects from the background due to its high detection rate and low computational ***,the performance is not very ***,this paper presents an improved ViBe algorithm to increase the accuracy and robustness of motion ***,a foreground feature map is created by optimizing the result of ViBe *** the edge detection of the original video frames is achieved after pre-sharpening using improved Sobel operator and Otsu ***,by feature fusion(of the foreground and background feature maps) and contour filling,the motion detection results can be *** experiments demonstrate the improvements of the proposed modifications at a limited additional cost.

关键词： Motion detection Otsu algorithm Sobel operator Visual Background Extractor(ViBe)

来源：评论

学校读者我要写书评

暂无评论

A Residual Merged Neutral Network for Multimodal Sentiment Analysis 2

A Residual Merged Neutral Network for Multimodal Sentiment A...

引用

2017 IEEE 2nd International Conference on Big Data Analysis（ICBDA 2017）

作者： Nan Xu Wenji Mao State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Computer and Control Engineering University of Chinese Academy of Sciences

ISBN: (纸本)9781509036202

With the continuous development of social networking sites,the volume of social media data has exploded and the user-generated content is becoming more and more *** a result,the modality of massive social media data is no longer confined to the single text *** brings new challenges to social media analytics in general and its examplar field such as sentiment analysis in *** sentiment analysis has become an increasingly important research topic in recent years,especially in the context of social media big *** of the previous work only focuses on single modality content such as text,image or ***,as the traditional sentiment analysis methods often lack the support of scalable deep models,this hinders their usage in processing large amount of online *** overcome the limitations in the previous work,in this paper,we propose an end-to-end framework for multimodal sentiment analysis based on deep neural *** propose a Merged Neural Network(MNN) model that utilizes CNNs to extract representations of text and image *** fuse the multimodal features,we introduce the residual model and propose two combined merged strategies,namely the EarlyRMNN(*** Residual MNN) and Late-RMNN(*** Residual MNN),to get deeper and more discriminative features than the previous *** experiments on two public available datasets demonstrate the effectiveness of our models for multimodal sentiment analysis in comparison with the related methods.

关键词： multimodal sentiment analysis convolutional neural network residual model feature fusion social media big data

来源：评论

学校读者我要写书评

暂无评论

The state of VLSI testing

引用

IEEE Potentials 2002年第3期21卷 12-16页

作者： Patnaik, L.M. Jamadagni, H.S. Agrawal, V.K. Varaprasad, B.K.S.V.L. Indian Institute of Science Bangalore India Department of Computer Science and Automation Bangalore India Indian Institute of Science Bangalore India Control Systems Group ISRO Satellite Centre India

No abstract available

关键词： Very large scale integration Circuit testing Circuit faults Clocks Logic Power supplies Circuit noise Crosstalk Propagation delay Digital circuits

来源：评论

学校读者我要写书评

暂无评论

Nonlinear observability of grinding mill conditions

引用

IFAC-PapersOnLine 2016年第20期49卷 13-18页

作者： le Roux, J.D. Steinboeck, A. Kugi, A. Craig, I.K. Department of Electrical Electronic and Computer Engineering University of Pretoria Pretoria South Africa Automation and Control Institute Vienna University of Technology Gußhausstraße 27-29 Vienna1040 Austria Christian Doppler Laboratory for Model-Based Control in the Steel Industry Automation and Control Institute Vienna University of Technology Gußhausstraße 27-29 Vienna1040 Austria

A nonlinear observer model of a grinding mill is developed. The model distinguishes between the volumetric hold-up of water, solids, rocks and balls in the mill, where solids are all ore small enough to discharge through the end-discharge grate, and rocks are all ore too large to discharge. The model includes the discharge rate, abrasion rate of rocks and the abrasion rate of balls as parameters. It is shown that with mill discharge flow-rate, discharge density and volumetric hold-up measurements the model states and parameters are locally (weakly) nonlinearly observable, but not linearly observable. Although instrumentation at the mill discharge is not yet included in industrial circuits because of space restrictions, this study motivates the benefits to be gained from including instrumentation at the mill discharge. If mills are fitted with adequate measurement instrumentation at the discharge, important mill states and parameters can be estimated. © 2016

关键词： Ball mills Abrasion Comminution Flow rate Grinding (comminution) Grinding (machining) Grinding mills Observability Parameter estimation State estimation Abrasion rates Discharge density Discharge flow rates Discharge rates Industrial circuits Measurement instrumentation Non linear observer Nonlinear observability

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：