检索结果-内蒙古大学图书馆

Gabor face recognition by multi-channel classifier fusion of supervised kernel manifold learning

NEUROCOMPUTING 2012年 97卷 398-404页

作者： Zhao, Zeng-Shun Zhang, Li Zhao, Meng Hou, Zeng-Guang Zhang, Chang-Shui Shandong Univ Sci & Technol Shandong Prov Key Lab Robot & Intelligent Technol Coll Informat & Elect Engn Qingdao 266590 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Tsinghua Univ Dept Automat Tsinghua Natl Lab Informat Sci & Technol State Key Lab Intelligent Technol & Syst Beijing 100084 Peoples R China

Motivated by the multi-channel nature of the Gabor feature representation and the success of the multiple classifier fusion, and meanwhile, to avoid careful selection of parameters for the manifold learning, we propose a face recognition framework under the multi-channel fusion strategy. The Gabor wavelet endows the algorithm in a similar way as the human visual system, to represent face features. To solve the curse of dimensionality due to multi-channel Gabor feature, as well as to preserve nonlinear labeled intrinsic structure of the sample points, the manifold learning is applied to model the nonlinear labeled intrinsic structure. Each of the filtered multi-channel Gabor features, is treated as an independent channel. Classification is performed in each channel by the component classifier and the final result is obtained using the decision fusion strategy. The experiments on three face datasets show effective and encouraging recognition accuracy compared with other existing methods. (C) 2012 Elsevier B.V. All rights reserved.

关键词： Face recognition Supervised kernel manifold learning Classifier fusion Gabor wavelet

来源：评论

学校读者我要写书评

暂无评论

Data-Wave-Based Features Extraction and Its Application in Symbol Identifier Recognition and Positioning Suitable for Multi-Robot systems Regular Paper

引用

INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC systemS 2012年第6期9卷

作者： Liu, Xilong Qian, Hanbo Cao, Zhiqiang Zhou, Chao Yang, Yuequan Tan, Min Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China SASTIND Ctr Coordinat & Support Beijing Peoples R China Yangzhou Univ Coll Informat Engn Yangzhou Peoples R China

In this paper, feature extraction based on data-wave is proposed. The concept of data-wave is introduced to describe the rising and falling trends of the data over the long-term which are detected based on ripple and wave filters. Supported by data-wave, a novel symbol identifier with significant structure features is designed and these features are extracted by constructing pixel chains. On this basis, the corresponding recognition and positioning approach is presented. The effectiveness of the proposed approach is verified by experiments.

关键词： Data-wave Symbol identifier Structure features Pixel chain Recognition and positioning

来源：评论

学校读者我要写书评

暂无评论

Measuring Driving Behaviors from Live Video

引用

IEEE INTELLIGENT systemS 2012年第5期27卷 75-80页

作者： Wang, Kunfeng Huang, Wuling Tian, Bin Wen, Ding Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing 100864 Peoples R China Natl Univ Def Technol Ctr Mil Computat Expt & Parallel Syst Technol Changsha Hunan Peoples R China

Because of the technical and cost constraints on traditional measurement methods, there is a lack of long-term driving behavior data from natural traffic scenes, and this situation has been hindering research progress into driving behavior modeling and other related topics. Thanks to high-definition cameras and advanced visual measurement methods, traffic visual detection is entering a new stage of traffic visual measurement, and thus we can expect to achieve accurate segmentation, positioning, and measurement for road vehicles from live video to meet the requirement for field test data in behavior modeling. To measure driving behaviors in a cost-effective manner, the authors propose a comprehensive visual measurement approach that could perform well in complex traffic scenes. Specifically, they describe a procedure for traffic visual measurement, some preliminary algorithms, and some representative experimental results. Comparisons between the proposed method and three traditional ones (driving simulator, in-vehicle data recorder, and remote-sensing camera) indicate that the biggest advantage of the proposed method is it can measure driving behaviors from live video. Hence, the ongoing research will greatly benefit cognition in driving behavior models.

关键词： Cameras Image Segmentation Measurement Object Detection Road Traffic Traffic Engineering Computing Video Signal Processing Driving Behavior Measurement Live Video Technical Constraints Cost Constraints Long Term Driving Behavior Data Natural Traffic Scenes Driving Behavior Modeling Advanced Visual Measurement Methods Traffic Visual Detection Traffic Visual Measurement Road Vehicle Segmentation Road Vehicle Positioning Road Vehicle Measurement Comprehensive Visual Measurement Approach Driving Simulator In Vehicle Data Recorder Remote Sensing Camera Intelligent Transportation systems Intelligent Vehicles Costs Road Vehicles Visualization Data Models Cameras Remote Sensing Cognition Computer Vision Traffic Visual Measurement Driving Behaviors Vehicle Segmentation Live Video

来源：评论

学校读者我要写书评

暂无评论

A k-Nearest Neighbor Locally Weighted Regression Method for Short-Term Traffic Flow Forecasting

A <i>k</i>-Nearest Neighbor Locally Weighted Regression Meth...

引用

15th International IEEE Conference on Intelligent Transportation systems (ITSC)

作者： Li, Shuangshuang Shen, Zhen Xiong, Gang Chinese Acad Sci State Key Lab Management & Control Complex Syst Beijing Engn Res Ctr Intelligent Syst & Technol Inst Automat Beijing 100190 Peoples R China

ISBN: (纸本)9781467330633

In this paper, a k-nearest neighbor locally weighted regression method (k-LWR) is proposed to forecast the short-term traffic flow. Inspired by k-nearest neighbor (k-NN) method, the traffic flows which have the same clock time with the current traffic flow are viewed as neighbors. The traffic flows which have the same clock time with the predicted traffic flow are viewed as the outputs of the neighbors. The neighbors most similar to the current traffic flow are viewed as nearest neighbors. It is observed that each nearest neighbor has different similarity with the current traffic flow, and the similarity is relevant to the contribution of the nearest neighbor's output to predicted traffic flow. The greater the similarity is, the greater the contribution is. These contributions of the nearest neighbors' outputs are obtained by the locally weighted regression (LWR) method. In this way, k-LWR uses less data, but uses it more effectively. We use the root mean square error (RMSE) between the actual traffic flow and the predicted traffic flow as the measurement. The proposed method is tested on the actual data from Xingye intersection and Feihu intersection in Jiangsu Province in China. The experimental results show that k-LWR has 20% and 24% improvement over the pattern recognition algorithm (PRA), 26% and 30% improvement over k-NN, for the two intersections, respectively.

关键词： Vectors Forecasting Clocks Databases Pattern recognition Prediction algorithms Equations

来源：评论

学校读者我要写书评

暂无评论

Discrete-time Stochastic Iterative Learning control: A Brief Survey

Discrete-time Stochastic Iterative Learning Control: A Brief...

引用

10th World Congress on Intelligent control and Automation (WCICA)

作者： Shen, Dong Xiong, Gang Chinese Acad Sci Beijing Engn Res Ctr Intelligent Syst & Technol Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

ISBN: (纸本)9781467313988

This note gives a brief survey on discrete-time stochastic iterative learning control (SILC) from three aspects, namely, SILC for linear system, nonlinear system and system with other stochastic signal. Two major approaches, stochastic Kalman filtering approach and stochastic approximation approach, for SILC are proposed. Some open questions are also included.

关键词： Discrete-time Stochastic system Iterative Learning control Linear system Nonlinear system

来源：评论

学校读者我要写书评

暂无评论

Sentimental Spidering: Leveraging Opinion Information in Focused Crawlers

引用

ACM TRANSACTIONS ON INFORMATION systemS 2012年第4期30卷 1–30页

作者： Fu, Tianjun Abbasi, Ahmed Zeng, Daniel Chen, Hsinchun Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Google Inc Mountain View CA 94043 USA Univ Virginia Informat Technol Area Charlottesville VA 22904 USA Univ Arizona Dept Management Informat Syst Tucson AZ 85721 USA

Despite the increased prevalence of sentiment-related information on the Web, there has been limited work on focused crawlers capable of effectively collecting not only topic-relevant but also sentiment-relevant content. In this article, we propose a novel focused crawler that incorporates topic and sentiment information as well as a graph-based tunneling mechanism for enhanced collection of opinion-rich Web content regarding a particular topic. The graph-based sentiment (GBS) crawler uses a text classifier that employs both topic and sentiment categorization modules to assess the relevance of candidate pages. This information is also used to label nodes in web graphs that are employed by the tunneling mechanism to improve collection recall. Experimental results on two test beds revealed that GBS was able to provide better precision and recall than seven comparison crawlers. Moreover, GBS was able to collect a large proportion of the relevant content after traversing far fewer pages than comparison methods. GBS outperformed comparison methods on various categories of Web pages in the test beds, including collection of blogs, Web forums, and social networking Web site content. Further analysis revealed that both the sentiment classification module and graph-based tunneling mechanism played an integral role in the overall effectiveness of the GBS crawler.

关键词： Algorithms Experimentation Design Performance Web crawlers focused crawlers sentiment analysis opinion mining classification graph similarities random walk path

来源：评论

学校读者我要写书评

暂无评论

A Successful Change from TNN to TNNLS and a Very Successful Year

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systemS 2013年第1期24卷 1-7页

作者： Anderson, Charles Azar, Ahmad Taher Battistelli, Giorgio Bayro-Corrochano, Eduardo Cervellera, Cristiano Elizondo, David Filippone, Maurizio Gnecco, Giorgio Hu, Xiaolin Huang, Tingwen Liu, Weifeng Lu, Wenlian Madureira, Ana Maria Skrjanc, Igor Villmann, Thomas Wu, Jonathan Xie, Shengli Xu, Dong Liu, Derong Colorado State Univ Ft Collins CO 80523 USA Misr Univ Sci & Technol Giza Egypt Univ Florence I-50121 Florence Italy CINVESTAV Unidad Guadalajara Guadalajara Jalisco Mexico De Montfort Univ Leicester LE1 9BH Leics England Univ Glasgow Glasgow G12 8QQ Lanark Scotland Univ Genoa I-16126 Genoa Italy Tsinghua Univ Beijing Peoples R China Jump Trading Chicago IL USA Fudan Univ Shanghai Peoples R China Polytech Porto ISEP IPP Oporto Portugal Univ Ljubljana Ljubljana 61000 Slovenia Univ Appl Sci Mittweida Germany Univ Windsor Windsor ON N9B 3P4 Canada Guangdong Univ Technol Guangzhou Guangdong Peoples R China Nanyang Technol Univ Singapore Singapore Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Illinois Dept Elect & Comp Engn Chicago IL 60607 USA

来源：评论

学校读者我要写书评

暂无评论

Emergency Traffic Evacuation control based on the Orthogonal Experimental Design Method

Emergency Traffic Evacuation Control based on the Orthogonal...

引用

15th International IEEE Conference on Intelligent Transportation systems (ITSC)

作者： Lv Yisheng Zhu Fenghua Miao Qinghai Ye Peijun Chen Songhang Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Chinese Acad Sci Grad Univ Beijing Peoples R China

ISBN: (纸本)9781467330633

Evacuees' behaviors have a significant impact on evacuation efficiency. Evacuation clearance time is one of the key indicators in the evacuation planning and management. Evacuees' departure time choice, destination choice and route choice behavior based on real-time traffic information are three crucial factors used to estimate evacuation clearance time. In this paper, we use the orthogonal experimental design method to determine values of these three factors simultaneously, which can reduce evacuation clearance time significantly. Once we obtain these values, we can guide evacuees' departure time choice, destination choice and route choice behavior to approximate these values and evacuation efficiency will improve greatly. The dynamic traffic evacuation process is modeled using a rule-based multi-agent microscopic traffic simulation system called TransWorld. The simulation experiment results illustrate the effectiveness and reliability of the proposed method. The proposed methodology, computational results and discussions can be used for future emergency evacuation planning and management.

关键词： clearance time EVACUATION PLANS Evacuation design approach simulation test Departure time Route choice

来源：评论

学校读者我要写书评

暂无评论

Novel DR-tree Index Based on the Diagonal Line of MBR

Novel DR-tree Index Based on the Diagonal Line of MBR

引用

8th IEEE International Wireless Communications and Mobile Computing Conference (IWCMC)

作者： Tang, Jine Zhou, Zhangbing Liu, Zhi-Yong Wang, Qun China Univ Geosci Sch Informat Engn Beijing Peoples R China Chinese Acad Sci Beijing State Key Lab Management & Control Complex Syst I Beijing Peoples R China

ISBN: (纸本)9781457713798

The application of spatial database is increasingly widespread. How to effectively store and organize multidimensional space data and improve the processing efficiency of multidimensional data has become a central issue. R-tree is one of the most widely used spatial indexes. Due to the existing large overlap and coverage among the nodes of R-tree, the search path of a data object is not unique, and the search efficiency declines sharply when the amount of data increases. Based on the analysis and research of previous index trees, a novel DR-tree index based on the diagonal lines of MBR is proposed in this paper. DR-tree uses the diagonal line of MBR to indicate spatial data objects and construct R-tree, still adopt the endpoint coordinates of MBR diagonal to signify the location of leaf nodes or non-leaf nodes. Since MBR is simplified, the coverage and overlap among regions are also reduced. Experimental results show that the new index tree is superior to R-tree in performance. The query paths of data objects are single, the insertion, deletion, and query efficiency of data objects are significantly improved, and the performance of the new index tree becomes more apparent when the amount of data objects increases.

关键词： Spatial Database Spatial Indexes R-tree Diagonal Lines of MBR DR-tree

来源：评论

学校读者我要写书评

暂无评论

Compact visual control system for aligning and tracking narrow butt seams with CO₂ gas-shielded arc welding

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2012年第9-12期62卷 1157-1167页

作者： Xu, De Fang, Zaojun Chen, Haiyong Yan, Zhiguo Tan, Min Chinese Acad Sci State Key Lab Management & Control Complex Syst Inst Automat Beijing 100190 Peoples R China Hebei Univ Technol Dept Automat Tianjin 300130 Peoples R China Dongfang Elect Corp R&D Ctr Intelligent Equipment & Control Technol Inst Chengdu 611731 Peoples R China

In this paper, a visual control system is proposed to locate the start welding position and track the narrow butt welding seam in container manufacturing. It estimates the error between the welding torch and the welding seam with a camera and a panel computer. It adjusts the torch's position via a stepper motor to eliminate the error. A decision controller with three gates is designed to decide the working procedure. Feature extraction algorithms are designed according to the seams and pre-weld spots. The seam line and the position of the pre-weld spot are detected to locate the start welding position in initial aligning. Then the torch is aligned to the seam. In the welding stage, the reference feature is determined with many frames of images based on their statistical property. The current estimated feature is checked to ensure only normal features to be used for welding seam tracking. Experiments are well conducted to verify the effectiveness of the proposed system and methods.

关键词： Feature extraction Image feature statistics Start welding position Visual control Vision system Aligning Seam tracking Gas-shielded arc welding Container manufacturing

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：