检索结果-内蒙古大学图书馆

Dynamic feature extraction for facial expression recognition based on optical flow

Information technology Journal 2013年第23期12卷 7305-7311页

作者： Jia, Xibin Liu, Shuangqiao Powers, David M. W. Beijing Municipal Key Laboratory for Multimedia and Intelligent Software Technology Beijing University of Technology Beijing 100124 China College of Computer Science Beijing University of Technology Beijing 100124 China School of Computer Science Engineering and Mathematics Flinders University of South Australia Adelaide 5042 Australia

Understanding facial expressions is a fundamental problem in affective computing that has the potential to impact both sides of a conversation with a computational agent. Currently static approaches based on techniques such as Gabor transformation represent the state of the art for identifying facial expressions but remain rather slow and unreliable. In this study we introduce and compare a dynamic technique based on optical flow versus this static Gabor baseline, as well as integrating information about static and dynamic facial characteristics into novel fused models. Rather than requiring complex Machine Learning, a simple and fast template model based on K-Means uses a Hidden Markov Model to provide context. The system is trained and evaluated on distinct subsets of the Cohn-Kanade database of adult faces which provides classifications into six basic expressions. Experimental results show that the dynamic expression feature extraction based on the optical flow for facial expression recognition has considerably improved recognition rate. Fusion of the optical flow dynamic expression features with Gabor static expression feature also increases recognition rate somewhat versus the static baseline but the hybrids tested are not competitive with the pure dynamic model. © 2013 Asian Network tor Scientific Information.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Dimensionality Reduction Assisted Tensor Clustering

Dimensionality Reduction Assisted Tensor Clustering

引用

International Joint Conference on Neural Networks

作者： Yanfeng Sun Junbin Gao Xia Hong Yi Guo Chris J. Harris Beijing Municipal Key Lab of Multimedia and Intelligent Software Technology Beijing University of Technology School of Computing and Mathematics Charles Sturt University School of Systems Engineering University of Reading CSIRO Mathematics Informatics and Statistics Electronics and Computer Science University of Southampton

ISBN: (纸本)9781479914821

This paper is concerned with tensor clustering with the assistance of dimensionality reduction approaches. A class of formulation for tensor clustering is introduced based on tensor Tucker decomposition models. In this formulation, an extra tensor mode is formed by a collection of tensors of the same dimensions and then used to assist a Tucker decomposition in order to achieve data dimensionality reduction. We design two types of clustering models for the tensors: PCA Tensor Clustering model and Non-negative Tensor Clustering model, by utilizing different regularizations. The tensor clustering can thus be solved by the optimization method based on the alternative coordinate scheme. Interestingly, our experiments show that the proposed models yield comparable or even better performance compared to most recent clustering algorithms based on matrix factorization.

关键词： Tensor Tucker Decomposition Tensor Clustering Matrix Factorization Tensor PCA

来源：评论

学校读者我要写书评

暂无评论

Output feedback tracking control for spacecraft relative translation subject to input constraints and partial loss of control effectiveness

Output feedback tracking control for spacecraft relative tra...

引用

American Control Conference

作者： Lin Zhao Yingmin Jia Junping Du Jun Zhang Seventh Research Division and the Department of Systems and Control Beihang University (BUAA) Beijing 100191 China Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer Science and Technology Beijing University of Posts and Telecommunications Beijing 100876 China School of Electronic and Information Engineering Beihang University (BUAA) Beijing 100191 China

ISBN: (纸本)9781479932757

In this paper, an adaptive output feedback tracking control scheme is proposed for spacecraft formation flying (SFF) in the presence of external disturbances, uncertain system parameters, input constraints and partial loss of control effectiveness. The proposed controller incorporates a pseudo-velocity filter to account for the unmeasured relative velocity, and the neural network (NN) technique is implemented to approximate the desired nonlinear function and bounded external disturbances. In order to guarantee that the output of the NN used in the controller is bounded by the corresponding bound of the approximated nonlinear function, a switch function is employed to generate a switching between the adaptive NN control and the robust controller. Moreover, a fault tolerant part is included in the controller to compensate the partial loss of actuator effectiveness fault. It is shown that the derived controller not only guarantees the tracking error in the closed-loop system to be uniformly ultimately bounded (UUB) but also ensures the control input can rigorously enforce actuator magnitude constraints. Simulation results are provided to demonstrate the effectiveness of the proposed method.

关键词： SFF UUB NN

来源：评论

学校读者我要写书评

暂无评论

Robust H_∞ Consensus Control of Uncertain Multi-Agent Systems with Nonlinear Dynamics and Time-Varying Delays

Robust H_∞ Consensus Control of Uncertain Multi-Agent Syste...

引用

American Control Conference

作者： Ping Wang Yingmin Jia Junping Du Jun Zhang Seventh Research Division and the Department of Systems and Control Beihang University (BUAA) Beijing 100191 China Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer Science and Technology Beijing University of Posts and Telecommunications Beijing 100876 China School of Electronic and Information Engineering Beihang University (BUAA) Beijing 100191 China

ISBN: (纸本)9781479932757

This paper is concerned with the H_∞ consensus control problem in undirected networks of autonomous agents with nonlinear dynamics, subject to parameter uncertainties and external disturbances. With the consideration of time-varying delays arising from communication among agents, a distributed protocol is proposed using the local delayed state information. Then, by defining an appropriate controlled output function, the consensus problem under the proposed protocol is converted into an H_∞ control problem. Based on robust H_∞ theory, sufficient conditions are derived to make all agents achieve consensus with desired H_∞ performance. Moreover, the feedback matrix in the proposed protocol is determined by solving two linear matrix inequalities (LMIs) with the same dimensions as a single agent. Finally, a numerical simulation is provided to demonstrate the effectiveness of our theoretical results.

关键词： Multi-agent systems Protocols Nonlinear dynamical systems Uncertain systems Linear matrix inequalities Robustness Delay effects

来源：评论

学校读者我要写书评

暂无评论

Autoregressive-based online backup scheme for small files

引用

Journal of China Universities of Posts and Telecommunications 2013年第SUPPL -2期20卷 40-46页

作者： Ye, Peng-Di Yao, Wen-Bin Li, Xiao-Yong Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications Beijing 100876 China School of Computer Science Beijing University of Posts and Telecommunications Beijing 100876 China

Reduce backup window with lower system overheads is a challenge for backup system in massive small files environment. In this article, a new autoregressive-based online backup scheme for small files (ABBSF) is presented to achieve the goal by enhancing the utilization ratio of bandwidth resource in normal times. ABBSF exploits single transfer pattern and package transfer pattern to deal with small files. ABBSF employs single transfer to send one small file to the backup side periodically, and collects the network situation in this procedure. According to these network performance information, it builds autoregressive-based model for predicting available network bandwidth in the next period. Meanwhile, it provides predictive step length control to make more utilization of predictive model for maintaining low system overheads. On the basis of prediction, ABBSF makes appropriate transfer policy for package transfer. Finally, it employs package transfer to pack several files and sent them to the backup side. Experiments show that ABBSF has a good performance of prediction with relatively low system overheads to make full use of network bandwidth when backup small files. © 2013 The Journal of China Universities of Posts and Telecommunications.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Cooperative Bicircular Target Tracking Using Multiple Unmanned Aerial Vehicles

Cooperative Bicircular Target Tracking Using Multiple Unmann...

引用

IEEE Annual Conference on Decision and Control

作者： Yueqian Liang Yingmin Jia Junping Du Fumitoshi Matsuno Seventh Research Division and the Department of Systems and Control Beihang University (BUAA) Beijing 100191 China Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer Science and Technology Beijing University of Posts and Telecommunications Beijing 100876 China Department of Mechanical Engineering and Science Kyoto University Kyoto 606-8501 Japan

ISBN: (纸本)9781467360890

This paper investigates the problem of tracking a moving target using multiple fixed-wing unmanned aerial vehicles (UAVs) under a new bicircular formation. This new formation for cooperative standoff target tracking is first developed by maximizing the amount of Fisher information. Guidance vector fields are designed, and based on them, a cooperation approach is proposed to adapt the unknown target velocity and achieve the cooperative bicircular tracking. Speed and heading rate are firstly controlled to track the guidance vector fields separately for each UAV, then the speed is further adjusted to maintain the desired angular separation between the UAVs. Simulation experiments are given to verify the effectiveness of the proposed approach.

关键词： bicircular Target tracking vehicle

来源：评论

学校读者我要写书评

暂无评论

An automatically privacy setting algorithm based on Rasch model

引用

Journal of China Universities of Posts and Telecommunications 2013年第SUPPL -2期20卷 17-20页

作者： Gu, Yong-Hao School of Computer Science Beijing University of Posts and Telecommunications Beijing 100876 China Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications Beijing 100876 China

In the application of mobile network and internet of things (IOT), users often set sensitive information to avoid the privacy disclosing. But sometimes users are not sure whether or not to set the sensitive information open or which item should be set open. An automatically privacy setting algorithm based on Rasch model with new parameters is proposed to solve the privacy settings automatically. The proposed algorithm statistically analyses the collected users' settings information and get the summary of each user's privacy rate and privacy settings. So, new users with their privacy concern levels can find the closest privacy rate and their best privacy settings in the summary table. © 2013 The Journal of China Universities of Posts and Telecommunications.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Percolation theory-based exposure-path prevention for wireless sensor networks coverage in internet of things

引用

IEEE Sensors Journal 2013年第10期13卷 3625-3636页

作者： Liu, Liang Zhang, Xi Ma, Huadong Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications Beijing 100876 China Networking and Information Systems Laboratory Department of Electrical and Computer Engineering Texas AandM University College Station TX 77843 United States

Deriving the critical density to achieve region coverage for random sensor deployment is a fundamentally important problem in the area of Internet of Things (IoT). Most of the existing works on sensor coverage mainly concentrate on the full coverage models, which ensure that all points in the deployment region are covered at the expense of high complexity and cost. In contrast, many applications of IoT focus on the exposure-path prevention, which does not require full coverage sensor deployment, and instead it only needs the partial coverage, because the exposure paths are prevented as long as no moving objects or phenomena can go through a deployment region without being detected. Finally, we focus on the partial coverage by applying the percolation theory to solve the exposure path problem for the network of sensors in IoT. Most of the existing percolation-based schemes apply the continuum-percolation theory, which, however, suffers from the loose lower and upper bounds on the critical density. To overcome this problem, we propose a bond-percolation theory based scheme by mapping the exposure path problem into a bond percolation model. Using this model, we derive the critical densities for both omnidirectional sensor networks and directional sensor networks under random sensor deployment where sensors are deployed according to a two-dimensional Poisson process. The rigorous modeling/analyses and extensive simulations show that our proposed scheme can yield much tighter upper and lower bounds on the critical densities as compared with those generated by continuum-percolation. © 2001-2012 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Bootstrapping-based Automatic Acquisition of Domain Concepts for Ontology Construction

引用

电子学报(英文版) 2013年第2期22卷 313-318页

作者： YANG Yuehua DU Junping ZI Lingling Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Beijing 100876 China School of Electronic and Information Engineering L iaoning Technical University Huludao 125105 China

The domain concept is one of the key el- ements of ontology. In order to automatically acquire the domain concepts during the domain ontology construction, we proposed a novel Bootstrapping-based automatic acqui- sition algorithm of domain concepts. In our work, the com- pound words are extracted according to the combination conditions of the mutual information and the information entropy. The candidate domain concepts determinant con- ditions based on the co-occurrence sentences frequency are presented. Besides, to avoid omitting the domain concepts with the lower frequency or semantically similar to other domain concepts, the semantic factor is introduced. The experiments results have demonstrated that the compound domain concepts and the semantically similar domain con- cepts with the lower sentences frequency can also be ex- tracted by using the proposed algorithm. And the pro- posed algorithm has obtained higher precision and recall, so it is effective and feasible.

关键词：领域本体自动获取自举位置算法语义相似引导过程组合条件信息熵

来源：评论

学校读者我要写书评

暂无评论

Detecting Photographic Cropping Based on Vanishing Points

引用

电子学报(英文版) 2013年第2期22卷 369-372页

作者： MENG Xianzhe NIU Shaozhang YAN Ru LI Yezhou School of Computer Science Beijing University of Posts and Telecommunications Beijing 100876 China Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia Beijing 100876 China School of Science Beijing University of Posts and Telecommunications Beijing 100876 China

Cropping is a common form of manipula- tion, it is indiscernible and hard to detect, since the inter- ception will not destroy most of the image’s original fea- tures. In this paper, how to detect cropping according to a single image is described, and a new camera calibration al- gorithm into digital forensics is proposed, which conducts the calibration according to orthometric vanishing points. Our method can estimate the principal point according to a single image, science the vanishing points only depends on the direction of the object. Experiments show that our method can identify asymmetric cropping of the im- age effectively, and also can estimate the principal points precisely, besides it is robust to smoothing and noise.

关键词：图像裁剪消失点检测原始特征数字取证精确估计不可分点估计

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：