检索结果-内蒙古大学图书馆

IEEE-RAS International Conference on Humanoid Robots

作者： Sang Hyoung Lee Il Hong Suh Sylvain Calinon Rolf Johansson Department of Electronics and Computer Engineering Hanyang University Seoul Korea Department of Computer Science and Engineering Hanyang University Seoul Korea Department of Advanced Robotics Istituto Italiano di Tecnologia (IIT) Genova Italy Department of Automatic Control Lund University Lund Sweden

Manipulation tasks are characterized by continuous motion trajectories containing a set of key phases. In this paper, we propose a probabilistic method to autonomously segment the motion trajectories for estimating the key phases embedded in such a task. The autonomous segmentation process relies on principal component analysis to adaptively project into one of the low-dimensional subspaces, in which a Gaussian mixture model is learned based on Bayesian information criterion and expectation-maximization algorithms. The basis skills are estimated by a set of Gaussians approximating quasi-linear key phases, and those times spent calculated from the segmentation points between two consecutive Gaussians representing the local changes of dynamics and directions of the trajectories. The basis skills are then used to build novel motion trajectories with possible motion alternatives and optional parts. After sequentially reorganizing the basis skills, a Gaussian mixture regression process is used to retrieve smooth motion trajectories. Two experiments are presented to demonstrate the capability of the autonomous segmentation approach.

关键词： Trajectory Motion segmentation Principal component analysis Joints Humanoid robots Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Tumour Segmentation in PET based on Local and Global Intensity Fitting Active Surface and Alpha Matting

Unsupervised Tumour Segmentation in PET based on Local and G...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society

作者： Ziming Zeng Tony Shepherd Reyer Zwiggelaar Faculty of Information and Control Engineering Shenyang Jianzhu University Shenyang China and with the Department of Computer Science Aberystwyth University UK Turku PET Center and Department of Oncology and Radiotherapy Turku University Hospital Finland. Department of Computer Science Aberystwyth University UK

ISBN: (纸本)9781424441198

This paper proposes an unsupervised tumour segmentation scheme for PET data. The method computes the volume of interests (VOIs) with subpixel precision by considering the limited resolution and partial volume e ect. Firstly, it uses local and global intensity active surface modelling to segment VOIs, then an alpha matting method is used to eliminate false negative classification and refine the segmentation results. We have validated our method on real PET images of head-andneck cancer patients as well as images of a custom designed PET phantom. Experiments show that our method can generate more accurate segmentation results compared with alternative approaches.

关键词： unsupervised segmentation approaches

来源：评论

学校读者我要写书评

暂无评论

Wireless MIMO Switching with Zero Forcing and Network Coding

引用

IEEE Journal on Selected Areas in Communications 2012年第8期30卷 1452-1463页

作者： Fanggang Wang Soung Chang Liew Dongning Guo State Key Lab of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China Department of Information Engineering Chinese University of Hong Kong HK SAR China Department of Electrical Engineering & Computer Science Northwestern University Evanston IL USA

A wireless relay with multiple antennas is called a multiple-input-multiple-output (MIMO) switch if it maps its input links to its output links using "precode-and-forward." Namely, the MIMO switch precodes the received signal vector in the uplink using some matrix for transmission in the downlink. This paper studies the scenario of K stations and a MIMO switch, which has full channel state information. The precoder at the MIMO switch is either a zero-forcing matrix or a network-coding matrix. With the zero-forcing precoder, each destination station receives only its desired signal with enhanced noise but no interference. With the network-coding precoder, each station receives not only its desired signal and noise, but possibly also self-interference, which can be canceled. Precoder design for optimizing the received signal-to-noise ratios at the destinations is investigated. For zero-forcing relaying, the problem is solved in closed form in the two-user case, whereas in the case of more users, efficient algorithms are proposed and shown to be close to what can be achieved by extensive random search. For network-coded relaying, we present efficient iterative algorithms that can boost the throughput further.

关键词： Relays Switches MIMO Noise Downlink Vectors

来源：评论

学校读者我要写书评

暂无评论

Evolving neural network using hybrid genetic algorithm and simulated annealing for rainfall-runoff forecasting

Evolving neural network using hybrid genetic algorithm and s...

引用

3rd International Conference on Swarm Intelligence, ICSI 2012

作者： Ding, Hong Wu, Jiansheng Li, Xianghui School of Information Engineering Wuhan University of Technology Wuhan 430070 Hubei China Department of Physics and Information Science Liuzhou Teachers College Guangxi Liuzhou 545004 China Department of Mathematics and Computer Liuzhou Teachers College Liuzhou 545004 Guangxi China Liuzhou City Flood Control and Drainage Project Management Office Liuzhou 545002 Guangxi China

ISBN: (纸本)9783642309755

Accurately rainfall-runoff forecasting modeling is a challenging task. Recent neural network (NN) has provided an alternative approach for developing rainfall-runoff forecasting model, which performed a nonlinear mapping between inputs and outputs. In this paper, an effective hybrid optimization strategy by incorporating the jumping property of simulated annealing (SA) into Genetic Algorithm (GA), namely GASA, is used to train and optimize the network architecture and connection weights of neural networks for rainfall-runoff forecasting in a catchment located Liujiang River, which is a watershed from Guangxi of China. This new algorithm incorporates metropolis acceptance criterion into crossover operator, which could maintain the good characteristics of the previous generation and reduce the disruptive effects of genetic operators. The results indicated that compared with pure NN, the GASA algorithm increased the diversity of the individuals, accelerated the evolution process and avoided sinking into the local optimal solution early. Results obtained were compared with existent bibliography, showing an improvement over the published methods for rainfall-runoff prediction. © 2012 Springer-Verlag.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Hierarchal Classifier for Identifying Independent Components

A Hierarchal Classifier for Identifying Independent Componen...

引用

International Joint Conference on Neural Networks

作者： Chin-Teng Lin Yu-Kai Wang Shi-An Chen Department of Electrical and Control Engineering and Brain Research Center National Chiao-Tung University Department of Computer Science and Brain Research Center National Chiao-Tung University

ISBN: (纸本)9781467314886

Brain-computer interface (BCI) has shown explosive growth for multiple applications in the recently years. Removing artifacts and selecting useful brain sources are essential in BCI research. Independent Component Analysis (ICA) has been proven as an effective technique to remove artifacts and many brain related researches are based on ICA. However, the useful independent components with brain sources are usually selected manually according to the scalp-plots. This is great inconvenience and a barrier for real-time BCI applications of EEG. In this investigation, a two-layer automatic identification model is proposed to select useful brain sources. It is based on neural network including support vector machine with radial basis function (SVMRBF) and self-organizing map (SOM). In the first layer, SVM discriminates useful independent components from the artifact effectively. In the second layer, these selected useful components are automatically classified to different spatial brain sources according to SOM. This study suggests this model to one general application for EEG study. It can reduce the effect of subjective judgment and improve the performance of EEG analysis.

关键词： Component Brain-computer interface Independent component analysis Electroencephalogram Neural network independent components Electroencephalography Independent component analysis self-organising feature maps Support Vector Network Artifacts Cerebrum islet cell antibody Scalp Classifiers

来源：评论

学校读者我要写书评

暂无评论

Rock-Paper-Scissors Prediction Experiments using Muscle Activations

Rock-Paper-Scissors Prediction Experiments using Muscle Acti...

引用

IEEE/RSJ International Conference on Intelligent Robotics and Systems

作者： Giho Jang Youngjin Choi Zhihua Qu Department of Electronic Electrical Control and Instrumentation Engineering Hanyang University Rep. of Korea Electrical Engineering and Computer Science University of Central Florida Orlando FL 32816 USA

ISBN: (纸本)9781467317375

Human motion prediction is becoming more and more important issue in the filed of wearable robots or biorobotics. This paper provides an initial experimental result for human motion prediction. In detail, the prediction method for ternary choice among rock-paper-scissors is presented using temporal patterns of muscle activations (Electromyography, in short EMG) controlling hand motion of subject. Initial burst part of EMG is prior to the onset of actual movement by dozens to hundreds milliseconds. Using this property, the proposed method makes the ternary choice prediction among rock-paper-scissors as soon as 10% motion variation of any finger is detected. It is shown experimentally that the success rate of the proposed prediction method is over 95%.

关键词： using EMG more

来源：评论

学校读者我要写书评

暂无评论

Research on SMT solder joint image segmentation

Research on SMT solder joint image segmentation

引用

International Conference on (ICEPT) Electronic Packaging Technology

作者： Yaqi Sun Yu Liu Department of Computer Science Hengyang Normal University Hunan 421008 China College of Mechanical and Control Engineering GuiLin University of Technology Guangxi 541004 China

Research on SMT solder joint image segmentation can formed feedback information of the products assembly which is used to control and adjust the SMT assembly, and is useful to guide SMT to improve the quality and process of SMT products. In our study, we improve a novel approach of SMT solder joint image segmentation. During our method, the process has three steps. At first, the RGB image of solder joint is converted into HSV image. Second, we segment the solder joint by color domain 2D histogram threshold. Last, mathematics morphology processing is used to improve the segment accuracy. Experimental results show that the proposed method retains the structure of the solder joint images leading to an effective segmentation.

关键词： Image segmentation Soldering Image color analysis Morphology Mathematics Histograms Morphological operations

来源：评论

学校读者我要写书评

暂无评论

Smart Grid Modeling Approach for Wide Area control Applications

Smart Grid Modeling Approach for Wide Area Control Applicati...

引用

IEEE Power and Energy Society General Meeting

作者： Aaron St. Leger John James Dean Frederick Electrical Engineering and Computer Science department at the United States Military Academy West Point NY 10996 USA Saratoga Control Systems Inc.

ISBN: (纸本)9781467327275

This paper describes an approach for modeling smart grids for wide area control applications. More specifically, it is proposed to model smart grids as a set of interdependent composite networks. A composite network is one whose evolution in time and/or space is described as a composition of more than one category of networks. This work proposes an interconnection of a communication network, information network, and a power system network to model smart grids. More specifically this work proposes a quantitative model focusing on bulk generation and transmission. The resulting model will be used for studying and simulating wide area measurement and control techniques and contingencies of components. The modeling methodology is based on the initial partitioning by the National Institute of Standards and Technology (NIST) of the smart grid domains. A basic example with control of load (demand response) and generator set points over a communication link is presented.

关键词： Smart Grid Communication Network Modeling Power System Modeling Wide Area Measurement and control Smart grids NIST Telecommunication links composite network system network Standing Orders Modeling Wide area measurement systems

来源：评论

学校读者我要写书评

暂无评论

Design of multiple anti-windup loops for multiple activations

引用

science China(Information sciences) 2012年第9期55卷 1925-1934页

作者： WU XiongJun 1,2 & LIN Zongli 3,1 1 department of Automation,Shanghai Jiao Tong University,and Key Laboratory of System control and Information Processing,Ministry of Education of China,Shanghai 200240,China 2 No.802 Institute of Shanghai Academy of Space Flight Technology,the Eighth Academy of China Aerospace science and Technology Corporation,Shanghai 200090,China 3 Charles L.Brown department of Electrical and computer engineering,University of Virginia,P.O.Box 400743,Charlottesville,VA 22904-4743,USA 1. Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China2. No. 802 Institute of Shanghai Academy of Space Flight Technology the Eighth Academy of China Aerospace Science and Technology Corporation Shanghai 200090 China3. Charles L. Brown Department of Electrical and Computer Engineering University of Virginia P.O. Box 400743 Charlottesville VA 22904-4743 USA

This paper considers anti-windup design for linear systems subject to actuator *** anti-windup gains are designed for activations immediately at the occurrence actuator saturation,after the saturation has reached a certain level and in anticipation of the occurrence of saturation,*** design is based on the minimization of L 2 gain from the disturbance to the controlled output of the resulting closed-loop *** anti-windup scheme involves a single anti-windup loop for immediate activation.A recent innovation is to design a single anti-windup loop for delayed or anticipatory activation,as well as to design two anti-windup gains,one for immediate activation and one for delayed *** design of three anti-windup gains for three different activations is shown through simulation to lead to significant further performance improvement over the previous activation schemes.

关键词： actuator saturation anti-windup anticipatory activation delayed activation L 2 gain nonlinear control

来源：评论

学校读者我要写书评

暂无评论

An Algorithm for Jammer Localization in Wireless Sensor Networks

An Algorithm for Jammer Localization in Wireless Sensor Netw...

引用

International Conference on Advanced Information Networking and Applications (AINA)

作者： Tianzhen Cheng Ping Li Sencun Zhu Laboratory for Mechatronic Engineering and Control BeiJing Institute of Technology BeiJing China Department of Computer Science and Engineering and College of Information Sciences and Technology Pennsylvania State University University Park USA

ISBN: (纸本)9781467307147

In wireless sensor networks (WSNs), jamming attacks have become a great concern recently. Finding the location of a jamming device is important so as to take security actions against the jammer and restore the network communication. In this paper, we take a comprehensive study on the jammer localization problem, and propose a simple while effective algorithm called Double Circle Localization (DCL). DCL is based on minimum bounding circle (MBC) and maximum inscribed circle (MIC). We implement and evaluate DCL under different conditions, including different node densities, jammer's transmission powers and antenna orientations, and compare it with three existing jammer localization algorithms through both simulation and experiments. Our evaluation results have demonstrated that, compared with all other approaches, DCL achieves the best accuracy in jammer localization.

关键词： Jamming Wireless sensor networks Microwave integrated circuits Auditory system Force Estimation Accuracy

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：