检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Jun Miao Lijuan Duan Laiyun Qing Yuanhua Qiao Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (CAS) Beijing China College of Computer Science and Technology Beijing University of Technology Beijing China School of Information Science and Engineering Graduate University of Chinese Academy of Sciences Beijing China College of Applied Science Beijing University of Technology Beijing China

This paper presents an improved neural architecture for gaze movement control in target searching. Compared with the four-layer neural structure proposed in [14], a new movement coding neuron layer is inserted between the third layer and the fourth layer in previous structure for finer gaze motion estimation and control. The disadvantage of the previous structure is that all the large responding neurons in the third layer were involved in gaze motion synthesis by transmitting weighted responses to the movement control neurons in the fourth layer. However, these large responding neurons may produce different groups of movement estimation. To discriminate and group these neurons' movement estimation in terms of grouped connection weights form them to the movement control neurons in the fourth layer is necessary. Adding a new neuron layer between the third layer and the fourth lay is the measure that we solve this problem. Comparing experiments on target locating showed that the new architecture made the significant improvement.

关键词： Neurons Visualization Image coding Encoding Context Feature extraction Equations

来源：评论

学校读者我要写书评

暂无评论

DH-TRIE frequent pattern mining on Hadoop using JPA

DH-TRIE frequent pattern mining on Hadoop using JPA

引用

IEEE International Conference on Granular computing (GRC)

作者： Lai Yang Zhongzhi Shi Li D. Xu Fan Liang Ilan Kirsh Chinese Academy of Sciences Beijing China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Department of .ITDS Old Dominion University Norfolk VA USA The Academic College of Tel-Aviv Yafo Israel

The FPgrowth is a famous frequent pattern's algorithm in data mining when working with high-dimensional, large-scale data sets. It is also known as great complexity on memory for the recursively processing. In general, FPgrowth cannot handle large-scale data set unless dividing a whole data set into small blocks. Based on Hadoop, the open cloud computing model, a distributed DH-TRIE frequent pattern algorithm using JPA is proposed, which solved the three problems (globalization, random-write and duration). The algorithm is shown good flexibility and scalability by comparisons to mahout project. By applied to a virtualization platform Vega Cloud, the algorithm will be used in far-ranging situations.

关键词： Data mining Cloud computing Java Programming Data models Indexing

来源：评论

学校读者我要写书评

暂无评论

Margin Emphasized Metric Learning and its application to Gabor feature based face recognition

Margin Emphasized Metric Learning and its application to Gab...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Shaoxin Li Shiguang Shan Chinese Academy and Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computer Technology Chinese Academy and Sciences Beijing China Chinese Academy of Sciences Beijing Beijing CN

In addressing side information based face recognition scenario, a new Margin Emphasized Metric Learning (MEML) method is proposed. As an improvement of previous metric learning, MEML defines a new objective function for optimization, which adds more weights to sample pairs on the boundary thus hard to classify. To further improve face verification performance, MEML is applied to Gabor feature in a block dividing and combining mode. Experiments on LFW image-restricted setting illustrate very impressive performance compared with traditional methods. By combining multiple MEML classifiers on several features, performance comparable to the best known results on LFW is achieved.

关键词： Measurement Face Face recognition Accuracy Training Databases Robustness

来源：评论

学校读者我要写书评

暂无评论

Attention driven face recognition, learning from human vision system

引用

International Journal of Computer Science Issues 2011年第5 5-2期8卷 8-13页

作者： Fang, Fang Qing, Laiyun Wang, Chongxiu Miao, Jun Chen, Xilin Gao, Wen School of Computer Science and Technology Harbin Institute of Technology Harbin 150001 China Graduate University of Chinese Academy of Science Beijing 100049 China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Institute of Digital Media Peking University Beijing 100871 China

This paper proposes a novel face recognition algorithm inspired by Human Visual System (HVS). Firstly, we learn where people look by recording observers' eye movements when they are viewing face images. We find that the observers are consistent in the regions fixated and such fixated regions are selected as the salient regions. Secondly, we represent the face images by four scales of Local Binary Gabor Patterns (LGBPs) for the salient regions whereas one scale LGBPs for the others, inspired by the fact that fovea of HVS has a higher spatial acuity than the periphery. Thirdly, we integrate the global information of face images in face recognition. The experimental results demonstrate that the proposed method learning from human beings is comparable with those learned with machine learning algorithms, which shows that the characteristics of the HVS provide valuable insights into face recognition.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Sparsely Encoded Local Descriptor for face recognition

Sparsely Encoded Local Descriptor for face recognition

引用

International Conference on Automatic Face and Gesture Recognition

作者： Zhen Cui Shiguang Shan Xilin Chen Lei Zhang School of Computer Science and Technology Huaqiao University Xiamen China Chinese Academy and Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computer Technology Chinese Academy and Sciences Beijing China Chinese Academy of Sciences Beijing Beijing CN Department of Computing Hong Kong Polytechnic University Hong Kong China

In this paper, a novel Sparsely Encoded Local Descriptor (SELD) is proposed for face recognition. Compared with K-means or Random-projection tree based previous methods, sparsity constraint is introduced in our dictionary learning and sequent image encoding, which implies more stable and discriminative face representation. Sparse coding also leads to an image descriptor of summation of sparse coefficient vectors, which is quite different from existing code-words appearance frequency(/histogram)-based descriptors. Extensive experiments on both FERET and challenging LFW database show the effectiveness of the proposed SELD method. Especially on the LFW dataset, recognition accuracy comparable to the best known results is achieved.

关键词： Face Dictionaries Pixel Training Feature extraction Face recognition Databases

来源：评论

学校读者我要写书评

暂无评论

Assessment of genetically modified food security-first results

引用

Journal of information and Computational Science 2011年第12期8卷 2493-2500页

作者： Chai, Jie Wu, Jiyi Cong, Jiang Sun, Xiaohong Kang, Bingyi Deng, Yong School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai 200240 China Hangzhou Key Laboratory of E-Business and Information Security Hangzhou Normal University Zhejiang 310036 China College of Food Science and Technology Shanghai Ocean University Shanghai 201306 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan 411105 China Key Subject Laboratory of National Defense for Radioactive Waste and Environmental Security Southwest University of Science and Technology Mianyang 621010 China College of Computer and Information Sciences Southwest University Chongqing 400715 China

With the development of Genetically Modified (GM) food, security issue is being paid increasing attention. In this paper, a comprehensive model taking account factors which influencing GM food security is proposed. Analytical Hierarchy Process (AHP) is used to derive the weight of each attribute in different levels according to their importance. Basic Probability Assignment (BPA) function is generated by the safety degree of each element, then we use BPA function of the Dempster-Shafer evidence to represent the inclination of the elements. The safety degree of GM food will be get when weight was used as the discount factor and each attribute data was combined based on discount combination rule. 1548-7741/Copyright © 2011 Binary information Press.

关键词： Safety factor

来源：评论

学校读者我要写书评

暂无评论

A method for translating belief function models to probability models

引用

Journal of information and Computational Science 2011年第10期8卷 1817-1823页

作者： Xu, Peida Wu, Jiyi Li, Ya Cong, Jiang Sun, Xiaohong Kang, Bingyi Deng, Yong School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai 200240 China Hangzhou Key Laboratory of E-Business and Information Security Hangzhou Normal University Zhejiang 310036 China College of Food Science and Technology Shanghai Ocean University Shanghai 201306 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan 411105 China Key Subject Laboratory of National defense for Radioactive Waste and Environmental Security Southwest University of Science and Technology Mianyang 621010 China College of Computer and Information Sciences Southwest University Chongqing 400715 China

One of the key issues in the applications of Dempster-Shafer evidence theory is how to make a decision based on Basic Probability Assignment (BPA). The conventional method is Pignistic Probability Transformation (PPT), which transforms BPA to probability distribution with equally assignment. To solve the existing problems of pignistic probability transformation, a new transformation method using an optimization algorithm based on the conflict coefficient k is proposed in this paper. The obtained probability has the minimum conflict coefficient with the original BPA. Numerical examples are used to illustrate the efficiency of the proposed method. © 2011 by Binary information Press.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A more effective definition of evidential conflict combined with evidential distance

引用

Journal of information and Computational Science 2011年第9期8卷 1729-1734页

作者： Chen, Yuxin Wu, Jiyi Cong, Jian Jie, Wenjing Deng, Yong School of Electronics and Information Technology Shanghai Jiao Tong University Shanghai 20024 China Hangzhou Key Lab of E-Business and Information Security Hangzhou Normal University Hangzhou 310036 China College of Food Science and Technology Shanghai Ocean University 999 Hucheng Huan Road Shanghai 201306 China Key Subject Laboratory of National Defense for Radioactive Waste and Environment Security Southwest University of Science and Technology Mianyang 621010 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan Hunan 411105 China College of Computer and Information Sciences Southwest University Chongqing 400715 China

Evidence theory is widely used in many application systems such as information fusion and decision making under uncertainty environment. However, the classical Dempster combination rule is not efficient to deal with highly conflicting evidences. One of the open issues is how to determine the conflict degree in conflict evidence management. In this paper, a new conflict coefficient is proposed to measure the conflict degree between bodies of evidence. It can overcome some drawbacks of the classical conflict coefficient. The numerical example shows the efficiency of our proposed method. Copyright © 2011 Binary information Press.

关键词： information fusion

来源：评论

学校读者我要写书评

暂无评论

Optimal aggregation of interval numbers based on genetic algorithm in group decision

引用

Journal of information and Computational Science 2011年第5期8卷 842-849页

作者： Kang, Bingyi Zhang, Yajuan Deng, Xinyang Wu, Jiyi Sun, Xiaohong Li, Ya Deng, Yong College of Computer and Information Sciences Southwest University Chongqing 400715 China Hangzhou Key Lab of E-Business and Information Security Hangzhou Normal University Hangzhou 310036 China College of Food Science and Technology Shanghai Ocean University 999 Hucheng Huan Road Shanghai 201306 China Key Subject Laboratory of National Defense for Radioactive Waste and Environmental Security Southwest University of Science and Technology Mianyang 621010 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan Hunan 411105 China School of Electronics and Information Technology Shanghai Jiaotong University Shanghai 200240 China

A group of decision-makers may differ in their choice of alternatives while making a decision. As a result, how to aggregate opinions of different experts is still an open issue. Due to the uncertainty in the process of decision making, some mathematic tools such as fuzzy sets theory and evidence theory, are used to model uncertain information. In this paper, the experts' opinions are represented by interval numbers. A new optimal aggregation method to combine interval data is proposed based on genetic algorithm. The new method can deal with experts' opinions in an efficient manner. A numerical example on group decision making under uncertain environment is used to illustrate the efficiency of our proposed method. Copyright © 2011 Binary information Press.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Dense Sigma set representation for pedestrian detection

引用

ICIC Express Letters 2011年第3期5卷 835-840页

作者： Hong, Xiaopeng Chang, Hong Shan, Shiguang Chen, Xilin Gao, Wen School of Computer Science and Technology Harbin Institute of Technology No. 92 West Da-Zhi Street Harbin 150001 China Key Lab of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology No. 6 Kexueyuan South Road Zhongguancun Haidian District Beijing 100190 China Institute of Digital Media Peking University No. 5 Yiheyuan Road Haidian District Beijing 100871 China

This paper proposes an effective and efficient pedestrian detection method which is based on 2nd order statistics image representation and linear Support Vector Machine classifiers (SVMs). After arranging a sample image into a dense structure of regions, the key issue is how to represent each image region. Exploiting the traditional covariance matrix region descriptor is a feasible way. However, it requires the usage of computationally demanding non linear classifiers, such as the radial basis function kernel SVMs, because the distance metric between covariance matrices is not in Euclidean space. Instead, we propose Sigma set as the region descriptor to represent each image region. As a result, this representation, which is named dense Sigma set, together with the efficient linear classifier achieves high accuracy. Experimental results on the INRIA pedestrian detection dataset show that dense Sigma set is a powerful and discriminative image representation method for pedestrian detection. © 2011 ISSN 1881-803X.

关键词： Support vector machines

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：