检索结果-内蒙古大学图书馆

10th SIAM International Conference on Data Mining, SDM 2010

作者： Yang, Wen-Yun Kwok, James T. Lu, Bao-Liang University of California Los Angeles CA United States Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Hong Kong Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University Shanghai China

CLUHSIC is a recent clustering framework that unifies the geometric, spectral and statistical views of clustering. In this paper, we show that the recently proposed discriminative view of clustering, which includes the DIFFRAC and DisKmeans algorithms, can also be unified under the CLUH-SIC framework. Moreover, CLUHSIC involves integer programming and one has to resort to heuristics such as iterative local optimization. In this paper, we propose two relaxations that are much more disciplined. The first one uses spectral techniques while the second one is based on semidefinite programming (SDP). Experimental results on a number of structured clustering tasks show that the proposed method significantly outperforms existing optimization methods for CLUHSIC. Moreover, it can also be used in semi-supervised classification. Experiments on real-world protein subcellu-lar localization data sets clearly demonstrate the ability of CLUHSIC in incorporating structural and evolutionary information. Copyright © by SIAM.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Emotional talking agent: System and evaluation

Emotional talking agent: System and evaluation

引用

International Conference on Natural Computation (ICNC)

作者： Shen Zhang Jia Jia Yingjin Xu Lianhong Cai Key Laboratory of Pervasive Computing Ministry of Education State Key Laboratory on Intelligent Technology and Systems Tsinghua National Laboratory of Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China

In this paper, we introduce a system that synthesizes the emotional audio-visual speech for a 3-D talking agent by adopting the PAD (Pleasure-Arousal-Dominance) emotional model. A GMM-based method is introduced to predict variation of acoustic features for emotional speech by PAD values, and a parametric framework of PAD-driven emotional facial expression synthesis is built. As the focus of this paper, we performed a series of perceptual evaluations to understand the reinforcement effect of vocal and facial expression of emotion, and investigated the usefulness and effectiveness of the emotional talking agent in human computer speech communications. Three questions are addressed: 1) To what extent do different interfaces affect human's comprehension of emotion? 2) How accurate the emotional information is conveyed by the talking agent? 3) Is the multimodal (audio-visual) interface helpful to human's emotion comprehension? An evaluation involving 19 participants was conducted to compare the effect of different interfaces (speech, mute agent and talking agent) on improving human's comprehension of emotion. The experimental results unveil the significant mutually reinforcing relationship between audio and video modality in emotion perception, and show that the users have a strong preference to multimodal interface for better comprehension of emotion. The results also prove the effectiveness of our PAD based emotional talking agent synthesis system.

关键词： Speech Visualization Humans Acoustics Speech synthesis Computers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A comparative study on two large-scale hierarchical text classification tasks' solutions

A comparative study on two large-scale hierarchical text cla...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Jian Zhang Hai Zhao Bao-Liang Lu Center of Brain-Like Computing and Machine Intelligence(ÇïêDepartment of Computer Science and Engineering Shanghai Jiaotong University Shanghai China MOE-Microsoft Key Laboratory of Intelligent Computing and Intelligent Systems Shanghai Jiaotong University Shanghai China

Patent classification is a large scale hierarchical text classification (LSHTC) task. Though comprehensive comparisons, either learning algorithms or feature selection strategies, have been fully made in the text categorization field, few work was done for a LSHTC task due to high computational cost and complicated structural label characteristics. For the first time, this paper compares two popular learning frameworks, namely hierarchical support vector machine (SVM) and k nearest neighbor (k-NN) that are applied to a LSHTC task. Experiment results show that the latter outperforms the former in this LSHTC task, which is quite different from the usual results for normal text categorization tasks. Then this paper does a comparative study on different similarity measures and ranking approaches in k-NN framework for LSHTC task. Conclusions can be drawn that k-NN is more appropriate for the LSHTC task than hierarchical SVM and for a specific LSHTC task. BM25 outperforms other similarity measures and List Weak gains a better performance than other ranking approaches. We also find an interesting phenomenon that using all the labels of the retrieved neighbors can remarkably improve classification performance over only using the first label of the retrieved neighbors.

关键词： Patents Support vector machines Text categorization Nearest neighbor searches Training Classification algorithms Taxonomy

来源：评论

学校读者我要写书评

暂无评论

Hedge detection and scope finding by sequence labeling with normalized feature selection

CoNLL-2010: Shared Task - Fourteenth Conference on Computat...

引用

CoNLL-2010: Shared Task - Fourteenth Conference on Computational Natural Language Learning, Proceedings of the Shared Task 2010年 92-99页

作者： Zhang, Shaodian Zhao, Hai Zhou, Guodong Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Dept of Computer Science and Engineering Shanghai Jiao Tong University China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University China School of Computer Science and Technology Soochow University China

This paper presents a system which adopts a standard sequence labeling technique for hedge detection and scope finding. For the first task, hedge detection, we formulate it as a hedge labeling problem, while for the second task, we use a two-step labeling strategy, one for hedge cue labeling and the other for scope finding. In particular, various kinds of syntactic features are systemically exploited and effectively integrated using a large-scale normalized feature selection method. Evaluation on the CoNLL-2010 shared task shows that our system achieves stable and competitive results for all the closed tasks. Furthermore, post-deadline experiments show that the performance can be much further improved using a sufficient feature selection. © 2010 Association for Computational Linguistics.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Multi-targets tracking based on SB/MHT theory

Multi-targets tracking based on SB/MHT theory

引用

作者： Ru, Qi Peng, Zhihong Zhang, Juan Chen, Xun School of Automation Beijing Institute of Technology Beijing 100081 China Education Ministry Key Laboratory of Intelligent Control of Complex Systems and Decision Beijing 100081 China

ISBN: (纸本)9787894631046

Multi-targets video tracking theory is introduced briefly, and the structured Branching MHT algorithm is applied in Multi-targets video tracking system. Connected with Kalman filter, hypotheses are built by SB/MHT using measures which are stretched by Bhattacharyya coefficient. In this way, Multi-targets video tracking can carry out. Feasibility of this method is validated by simulation.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Analysis of neural interaction in motor cortex during reach-to-grasp task based on Dynamic Bayesian Networks

Analysis of neural interaction in motor cortex during reach-...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Dong Sang Bin Lv Huiguang He Jiping He Feiyue Wang Key Laboratory of Complex Systems and Intelligent Science Institute of Automation Chinese Academy and Sciences Beijing China Harrington Department of Bioengineering and the Center of Neural Interface Design Arizona State University Tempe USA

In this work, we took the analysis of neural interaction based on the data recorded from the motor cortex of a monkey, when it was trained to complete multi-targets reach-to-grasp tasks. As a recently proved effective tool, Dynamic Bayesian Network (DBN) was applied to model and infer interactions of dependence between neurons. In the results, the gained networks of neural interactions, which correspond to different tasks with different directions and orientations, indicated that the target information was not encoded in simple ways by neuronal networks. We also explored the difference of neural interactions between delayed period and peri-movement period during reach-to-grasp task. We found that the motor control process always led to relatively more complex neural interaction networks than the plan thinking process.

关键词： Neurons Markov processes Bayesian methods Delay Neural networks Cathode ray tubes Encoding

来源：评论

学校读者我要写书评

暂无评论

Accelerated GPU computing technology for parallel management systems

Accelerated GPU computing technology for parallel management...

引用

World Congress on intelligent Control and Automation (WCICA)

作者： Feng Cui Changjian Cheng Feiyue Wang Wei Wei Lefei Li Yumin Zou The Key Laboratory of Complex Systems and Intelligent Science Institute of Automation Chinese Academy and Sciences Beijing China Department of Industrial Engineering Tsinghua University Beijing China Sinopec Maoming Company Maoming Guangdong China

GPU (Graphic Processing Unit) has the feature of a strong floating-point computing capability, suitable for large-scale intensive computing. This paper applies GPU acceleration technology for the parallel management of complex production system, focusing on the computing of human behavior based on fuzzy logic and equipment safety assessment of Monte Carlo algorithm. The implementation process of the GPU parallel computing on two kinds of algorithms are discussed in detail and the optimization method is proposed. With the experimental comparison, the accelerated calculation of GPU relative to CPU achieves a 47-fold.

关键词： Graphics processing unit Central Processing Unit Kernel Instruction sets Acceleration Nickel Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Design and motion control of a ping pong robot

Design and motion control of a ping pong robot

引用

World Congress on intelligent Control and Automation (WCICA)

作者： Ping Yang Zhengtao Zhang Huawei Wang De Xu Graduate School Chinese Academy and Sciences Beijing China Chinese Academy of Sciences Beijing Beijing CN Key Laboratory of Complex Systems and Intelligent Science Institute of Automation Chinese Academy and Sciences Beijing China

A ping pong robot with 5 degree of freedoms is designed in this paper. It consists of a PC, a high speed stereovision system with two smart cameras, AC servo motors and step motors. The hitting task of the ping pong robot is divided into three stages: the measurement and prediction stage, the planning stage and the execution stage. In the planning stage, we propose series of methods to plan the paddle trajectory, paddle posture, hitting speed according to the hitting information. Experiments of the robot versus a person are well conducted. The experimental results verify the effectiveness of the designed ping pong robot and the proposed methods.

关键词： Robots Planning Automation AC motors Trajectory intelligent control Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Online multiple instance learning with no regret

Online multiple instance learning with no regret

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Mu Li James T. Kwok Bao-Liang Lu Department of Computer Science and Engineering Shanghai Jiaotong University Shanghai China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiaotong University Shanghai China

Multiple instance (MI) learning is a recent learning paradigm that is more flexible than standard supervised learning algorithms in the handling of label ambiguity. It has been used in a wide range of applications including image classification, object detection and object tracking. Typically, MI algorithms are trained in a batch setting in which the whole training set has to be available before training starts. However, in applications such as tracking, the classifier needs to be trained continuously as new frames arrive. Motivated by the empirical success of a batch MI algorithm called MILES, we propose in this paper an online MI learning algorithm that has an efficient online update procedure and also performs joint feature selection and classification as MILES. Besides, while existing online MI algorithms lack theoretical properties, we prove that the proposed online algorithm has a (cumulative) regret of O(√T), where T is the number of iterations. In other words, the average regret goes to zero asymptotically and it thus achieves the same performance as the best solution in hindsight. Experiments on a number of MI classification and object tracking data sets demonstrate encouraging results.

关键词： Layout Image reconstruction Semiconductor device modeling Image segmentation Stereo vision Surface reconstruction Surface texture Surface fitting Stereo image processing Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

The distributed maximum power point tracking method and application in the PV grid-connected generation

The distributed maximum power point tracking method and appl...

引用

International Conference on intelligent System Design and Engineering Application (ISDEA)

作者： Zhao, Tingting Ju, Zhenhe Wang, Hongjiang Wei, Xiaopeng Li, Xiaoxiao Shi, Zhang School of Management Dalian University of Technology Dalian China New Energy Center Shenyang Institute of Engineering Shenyang China Department of Information and Engineering Shenyang Institute of Engineering Shenyang China Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian China Department of Study Liaoning Solar Energy R and D Co. Ltd. Shenyang China Institute of Systems Engineering Northeastern University Shenyang China

ISBN: (纸本)9780769542126

In the system of the PV grid-connected generation, because of the dispersion of the PV panel, difference of the sun radiation condition and the shadow of a part of the PV panel, they will cause the serious loss of energy for the parallel PV panel. In order to overcoming energy loss and raise the efficiency of the PV system, a new maximum power point tracking method called distributed variable step duty ratio perturb method is put forward. The distributed MPPT method overcomes the shortcomings to generate electricity quantity to descend because of the dispersion of the PV panel. The variable step duty ratio perturbing method speed quickly and is more suitable for this kind of distributed generation system. The hardware adopts DC/DC electric circuit to regulate PWM duty ratio. The software adopts TMS320-2812. An example is given to show that this method is able to realize distributed MPPT. In addition, the calculation speed of the approach is quick, accuracy of the approach is better, and the system has a high stability. © 2010 IEEE.

关键词： Maximum power point trackers

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：