检索结果-内蒙古大学图书馆

Learning from imbalanced data sets with a Min-Max modular support vector machine

中国电气与电子工程前沿 2011年第1期6卷 56-71页

作者： Bao-Liang LU Xiao-Lin WANG Yang YANG Hai ZHAO Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and EngineeringShanghai Jiao Tong UniversityShanghai 200240China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong UniversityShanghai 200240China Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and EngineeringShanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Engineering Shanghai Maritime UniversityShanghai 201306China

Imbalanced data sets have significantly unequal distributions between *** between-class imbalance causes conventional classification methods to favor majority classes,resulting in very low or even nO detection of minority classes.A Min-Max modular support vector machine(M3-SVM)approaches this problem by decomposing the training input sets of the majority classes into subsets of similar size and pairing them into balanced two-class classification *** approach has the merits of using general classifiers,incorporating prior knowledge into task decomposition and parallel *** on two real-world pattern classification problems,international patent classification and protein subcellar localization,demonstrate the effectiveness of the proposed approach.

关键词： imbalanced data Min-Max modular network(M3-network) prior knowledge parallel learning support vector machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

A vision system with multiple cameras designed for humanoid robots to play table tennis

A vision system with multiple cameras designed for humanoid ...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Ping Yang De Xu Zhengtao Zhang Guodong Chen Min Tan State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy of Sciences (CAS) Beijing China State Key Laboratory of Intelligent Control and Management of Complex Systems Chinese Academy of Sciences Beijing P.R.C.

Two humanoid robots are used to play table tennis with each other. For each humanoid robot, three cameras and a computer are equipped to form a stereovision system and a monocular vision system. The stereovision system consisting of two smart cameras and a computer measures the 3-dimensional position of the table tennis ball. It adopts parallel processing mode in order to realize hundred frames level measurement per second. A high-speed digital camera and the computer compose the monocular vision system, which measures the pose of the robot relative to the table via a color mark attached on the robot. The two smart cameras in each stereovision system are synchronized via I/O signals. The vision systems for the two robots are synchronized by time verification. Experimental results verify the effectiveness of the designed vision system and the proposed methods.

关键词： Cameras Computers Robot vision systems Smart cameras Robot kinematics Trajectory

来源：评论

学校读者我要写书评

暂无评论

Edgel index for large-scale sketch-based image search

Edgel index for large-scale sketch-based image search

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yang Cao Changhu Wang Liqing Zhang Lei Zhang MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiaotong University China Microsoft Research Asia Beijing China

Retrieving images to match with a hand-drawn sketch query is a highly desired feature, especially with the popularity of devices with touch screens. Although query-by-sketch has been extensively studied since 1990s, it is still very challenging to build a real-time sketch-based image search engine on a large-scale database due to the lack of effective and efficient matching/indexing solutions. The explosive growth of web images and the phenomenal success of search techniques have encouraged us to revisit this problem and target at solving the problem of web-scale sketch-based image retrieval. In this work, a novel index structure and the corresponding raw contour-based matching algorithm are proposed to calculate the similarity between a sketch query and natural images, and make sketch-based image retrieval scalable to millions of images. The proposed solution simultaneously considers storage cost, retrieval accuracy, and efficiency, based on which we have developed a real-time sketch-based image search engine by indexing more than 2 million images. Extensive experiments on various retrieval tasks (basic shape search, specific image search, and similar image search) show better accuracy and efficiency than state-of-the-art methods.

关键词： Image edge detection Indexing Shape Search problems Search engines

来源：评论

学校读者我要写书评

暂无评论

Motion vehicles tracking in intelligent transportation visual surveillance systems

引用

Nanjing Li Gong Daxue Xuebao/Journal of Nanjing University of Science and Technology 2012年第SUPPL.2期36卷 216-222页

作者： Wu, Lin-Feng Xiong, Gang Qian, Shou-Yi Xie, Li Zhejiang Provincial Key Lab. of Information Network Technology Department of Information Science and Electronic Engineering Zhejiang University Hangzhou 310027 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China Cloud Computing Industrial Technology Innovation and Incubation Center Dongguan Research Institute of CASIA Chinese Academy of Sciences Dongguan 523808 China Wenzhou Research Institute of Electronics and Information Wenzhou 325003 China

In terms of the difficulty of vehicle tracking in complex environment of the visual surveillance system, an object tracking algorithm is proposed for the applications in practical visual surveillance systems for intelligent traffic. A block-based Gaussian mixture background modeling method for object detection is presented to reduce the computational complexity of moving vehicle object abstraction. An adaptive tracking algorithm fused with color features and texture features is described to better adapt the traffic scene variation. The experimental results show that the proposed algorithm can effectively deal with the complex urban traffic conditions and the tracking performance is better than the conventional particle filter method and single feature based non-adaptive object tracking method.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

A multi-target tracking approach combined with occlusion segmentation

A multi-target tracking approach combined with occlusion seg...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Huan Ding Wensheng Zhang State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Multiple-target tracking in complex scenes is one of the most complicated problems in computer vision. Handling the occlusion between objects is the key issue in multiple target tracking. This paper presents an occlusion segmentation-based method to track multiple people in complex situations which are captured by static monocular cameras. In the proposed method, we calculate the probabilistic histogram of each object's optical flow vector, then use this motion statistic information along with the color and appearance information to construct a new expression of pixel distance. Finally, a stepwise classification and K-means clustering method are taken advantages of to accomplish occlusion segmentation. Object tracking is handled by a particle filter-based tracking framework, and a probabilistic appearance model is used to find the best particle. Experiments are conducted using public challenging data set PETS 2009. Results show that our approach can improve the performance of the existing tracking approach and handle dynamic occlusions better.

关键词： Computer vision Image motion analysis Probabilistic logic Optical reflection Target tracking Optical filters Histograms

来源：评论

学校读者我要写书评

暂无评论

ACP theory based plant human machine interaction evaluation

ACP theory based plant human machine interaction evaluation

引用

IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI

作者： Xiwei Liu Xiaowei Shen Dong Fan State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy and Sciences Beijing China

It's an important need for a large chemical plant to roundly and deeply evaluate the design prototype of plant human machine interaction (HMI) using in the control room. To meet this need, we propose an evaluation method based on the ACP (Artificial system, Computational experiment, and Parallel execution) theory. A plant operator agent is created in the method and it is composed of perception, cognition, and execution processors, short-term memory, and long-term memory. The operator agent is used as a virtual subject, and the HMI can be evaluated by behavior simulation, from the viewpoints of shortening fault detection and isolation (FDI) track and decreasing operator's physical and mental workloads. The proposed method shows that the ACP theory is useful for the HMI evaluation.

关键词： Pipelines Switches Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

A case study for traffic signal control system evaluation based on artificial transportation systems

A case study for traffic signal control system evaluation ba...

引用

IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI

作者： Fenghua Zhu Zhenjiang Li State Key Laboratory for Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy and Sciences Beijing China

This paper proposes a novel method to evaluate Traffic Signal Control System(TSCS) based on Artificial Transportation systems(ATS). Using this method, we can generate travel demand based on individual's activities and construct artificial traffic scenarios using basic rules. While interacting with ATS, TSCS can be evaluated by observing and analyzing the traffic status that emerged. The cost of the evaluation is decreased as artificial traffic environment can be constructed in the laboratory to substitute real environment and the evaluation can be carried out before the installation on site. Furthermore, as reasonable travel demand can be generated based on individual's activities, the reliability of evaluation results can be guaranteed. Finally, the effectiveness of this method is verified by experiments.

关键词： Business

来源：评论

学校读者我要写书评

暂无评论

Research on bus rapid transit (BRT) and its real-time scheduling

Research on bus rapid transit (BRT) and its real-time schedu...

引用

IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI

作者： Xisong Dong Gang Xiong Dong Fan Fenghua Zhu Yisheng Lv State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy and Sciences Beijing China

With the fast development of the economy, the urban traffic demands increases rapidly, Bus rapid transit (BRT) system, a new type and high efficient bus operator system and a comprehensive mass transit system between the metro and regular bus systems, can alleviate traffic congestion, reduce resident traffic cost effectively, and improve transportation quality and efficiency, with its advantages becomes an effective way to improve urban traffic status. In this article, the definition, major elements, advantages, functions and development of BRT are provided, and a new real-time scheduling is given which is going to be applied to the Zhongshan Avenue BRT system in Guangzhou China.

关键词： Optimization Rails Compounds Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

A novel image deblurring method based on high-order MRF prior

A novel image deblurring method based on high-order MRF prio...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Bo Zhao Wensheng Zhang State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

A novel image deblurring method based on high-order non-local range Markov Random Field (NLR-MRF) prior is proposed in the paper. NLR-MRF is an effective statistical framework to model prior knowledge of natural images which leads to excellent performance in some low-level vision problems. In our work, the framework is extended to image deblurring. To overcome some limitations of maximum a-posteriori (MAP) estimation, we adopt Bayesian minimum mean squared error (MMSE) estimation to perform deblurring. The high-order NLR-MRF prior can be easily integrated into this framework. Then, an efficient Gibbs sampling algorithm is employed to compute MMSE estimation. The proposed method frees the user from determining regularization parameter beforehand, which relies on unknown noise level. Our deblurring method shows superior or comparable results to the state-of-art deblurring methods.

关键词： Kernel Estimation Image restoration PSNR Filter banks Noise level

来源：评论

学校读者我要写书评

暂无评论

Recognizing vehicle-contours with a compositional deformable model

Recognizing vehicle-contours with a compositional deformable...

引用

IEEE International Conference on Vehicular Electronics and Safety (ICVES)

作者： Gu Yuan Fei-Yue Wang State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy and Sciences Beijing China

This paper illustrates a compositional deformable model for detecting vehicle and recognizing vehicle-contours. To overcome the difficulties that vehicles in an image have various sizes, shapes, colors and poses, this model has two main characteristics: first, the model is made up of constituent parts which shared by vehicles. The locality of parts give the model the ability to recognize vehicles with different types (e.g., although vehicles have various sizes and shapes, they are usually composed by roof, windscreen, windows, etc.). Second, the spatial relationships of these parts are represented by Markov Random Field (MRF). The model is deformable to adapt to vehicles of different shapes and poses because of the appropriately changing of combinations of these parts in the MRF. Experimental results with real world images show that this method is effective in vehicle detection and vehicle-contours recognition.

关键词： Vehicles Bars Shape Image edge detection Adaptation models Computational modeling Deformable models

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：