检索结果-内蒙古大学图书馆

2011 8th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2011, Jointly with the 2011 7th International Conference on Natural Computation, ICNC'11

作者： Chen, Si-Bao Wang, Hai-Xian Zhang, Xing-Yi Luo, Bin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei 230039 China Key Lab of Child Development and Learning Science of Ministry of Education Research Center for Learning Science Southeast University Nanjing Jiangsu 210096 China

ISBN: (纸本)9781612841816

Fisher's linear discriminant analysis (FLDA) is one of the most well-known linear subspace selection methods. However, FLDA suffers from the class separation problem. The projection to a subspace tends to merge close class pairs. Recent results show that maximizing the geometric mean or harmonic mean of Kullback-Leibler (KL) divergences of class pairs can significantly reduce this problem. In this paper, to further reduce the class separation problem, the alpha-mean of divergences as a framework is proposed for subspace selection, with arithmetic mean, geometric mean and harmonic mean as special cases. We named it the maximization of the alpha-mean of all pairs of KL divergences (MAMD) criterion. A quasi-Newton method is applied to solve the optimization problem. Experiments on synthetic data and two datasets in UCI machine learning repository show the validity of MAMD. © 2011 IEEE.

关键词： Newton-Raphson method

来源：评论

学校读者我要写书评

暂无评论

Topic level sampling towards optimized locality sensitive vocabulary coding

Topic level sampling towards optimized locality sensitive vo...

引用

8th International Conference on Information, Communications and signal processing, ICICS 2011

作者： Chen, Jie Duan, Ling-Yu Li, Bing Ji, Rongrong Gao, Wen Institute of Digital Media School of Electronic Engineering and Computer Science Peking University Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781457700309

We propose a novel locality sensitive vocabulary coding scheme to extract compact descriptors for low bit rate visual search. We employ Latent Dirichlet Allocation (LDA) to learn the topic vocabularies of lower dimension to generate compact descriptors. To deal with diverse datasets, LDA model is introduced to subdivide a dataset into groups of images with a topic model, where the code word distributions in each group produce coherent statistics from generative learning. Moreover, our empirical study has shown that the original Bag-of-Word (BoW) is sparse, and the occurrences of non-zero words is coherent within a topic. Our proposed topic-wise vocabulary learning yields a more compact yet discriminative codebook to search images. Given a query image, multiple topics are determined, which is fed into the topic vocabularies to generate more compact topical descriptor. Comparison experiments show our topic-wise locality sensitive vocabulary coding produces more compact and discriminative descriptors than the state-of-the-arts. © 2011 IEEE.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Teaching reform and innovation of the course - Digital image processing experiments

Teaching reform and innovation of the course - Digital image...

引用

International Conference on computer Science and Education

作者： Zhao, Haifeng Tang, Jin Luo, Bin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei 230039 China

ISBN: (纸本)9781424460052

Digital image processing is an interdisciplinary course, which needs students have a strong background in mathematics. To help them change from passive learning to active learning, teaching reform and innovation of the course "Digital Image processing Experiments" is discussed in this paper. The combined platform of experiments includes TI DSP experimental box and three different kinds of programming languages. The six experimental projects cover the basic theories of digital image processing. The result can offer a significant reference for the teaching innovations in the other related specialties. ©2010 IEEE.

关键词： MATlab

来源：评论

学校读者我要写书评

暂无评论

Motor imagery classification based on the optimized SVM and BPNN by GA

Motor imagery classification based on the optimized SVM and ...

引用

2010 International Conference on intelligent Control and Information processing, ICICIP 2010

作者： Jiao, Yingying Wu, Xiaopei Guo, Xiaojing Key Laboratory of Intelligent Computing and Signal Processing of MOE Anhui University Hefei 230039 Anhui Province China School of Computer Science and Technology Anhui University China

ISBN: (纸本)9781424470488

Brain-computer interface (BCI) is a specific Human-computer interface in which the brain wave is employed as the carrier of control information. The ultimate goal of BCI is to build a direct communication pathway between human brain and external environment that does not depend on the limb mobility and language. In this paper, we carry out the experiment about the left or right hand motor imagery, and support vector machine with genetic algorithm(GA-SVM) and back propagation neural network with genetic algorithm (GA-BP) are employed to classify the μ. rhythm evoked by movement imagination. The experiment results prove that GA-SVM can easily find out the appropriate parameters of SVM and GA-BP can avoid getting into local minimization to great extend. So higher accuracy of classification is achieved. © 2010 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Efficient multi-resolution detection of binary object

引用

Information technology Journal 2010年第8期9卷 1641-1646页

作者： Fang, Xianyong Wu, Hao MOE Key Laboratory of Intelligent Computing and Signal Processing School of Computer Science and Technology Anhui University Anhui 230039 China

This study presents an efficient multi-resolution method to detect binary object directly. Both intensity and geometry differences are used to measure the similarity between the source object template and target objects inside the test image. Especially for the geometrical difference, the histogram of oriented gradients is proposed to measure the similarity of the edge images between the source object template and the target object. Based on these two measurements, a multi-resolution strategy is used to accurately locate the object position in a coarse-to-fine way, where intensity difference and geometry difference applied consequently in each layer. Experimental results demonstrate the efficiency of the proposed method. © 2010 Asian Network for Scientific Information.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

On dynamic weighting of data in clustering with K-alpha means

On dynamic weighting of data in clustering with K-alpha mean...

引用

2010 20th International Conference on Pattern Recognition, ICPR 2010

作者： Chen, Si-Bao Wang, Hai-Xian Luo, Bin Key Lab. of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei Anhui 230039 China Key Lab. of Child Development and Learning Science Research Center for Learning Science Southeast University Nanjing Jiangsu 210096 China

ISBN: (纸本)9780769541099

Although many methods of refining initialization have appeared, the sensitivity of K-Means to initial centers is still an obstacle in applications. In this paper, we investigate a new class of clustering algorithm, K-Alpha Means (KAM), which is insensitive to the initial centers. With K-Harmonic Means as a special case, KAM dynamically weights data points during iteratively updating centers, which deemphasizes data points that are close to centers while emphasizes data points that are not close to any centers. Through replacing minimum operator in K-Means by alpha-mean operator, KAM significantly improves the clustering performances. © 2010 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Subspace selection using semi-supervised harmonic mean of Kullback-Leibler divergences

Subspace selection using semi-supervised harmonic mean of Ku...

引用

2010 7th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2010

作者： Chen, Si-Bao Wang, Hai-Xian Luo, Bin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei Anhui 230039 China Key Lab of Child Development and Learning Science of Ministry of Education Research Center for Learning Science Southeast University Nanjing Jiangsu 210096 China

ISBN: (纸本)9781424459346

In many areas of pattern recognition and machine learning, subspace selection is an essential step. Fisher's linear discriminant analysis (LDA) is one of the most well-known linear subspace selection methods. However, LDA suffers from the class separation problem. The projection to a subspace tends to merge close class pairs. A recent result, named maximizing the geometric mean of Kullback-Leibler (KL) divergences of class pairs (MGMD), can significantly reduce the class separation problem. Furthermore, maximizing the harmonic mean of Kullback-Leibler (KL) divergences of class pairs (MHMD) emphasizes smaller divergences more than MGMD, and deals with the class separation problem more effectively. However, in many applications, labeled data are very limited while unlabeled data can be easily obtained. The estimation of divergences of class pairs is unstable using inadequate labeled data. To take advantage of unlabeled data for subspace selection, semi-supervised MHMD (SSMHMD) is proposed using graph Laplacian as normalization. Quasi-Newton method is adopted to solve the optimization problem. Experiments on synthetic data and real image data show the validity of SSMHMD. ©2010 IEEE.

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Motor imagery classification based on the optimized SVM and BPNN by GA

Motor imagery classification based on the optimized SVM and ...

引用

International Conference on intelligent Control and Information processing (ICICIP)

作者： Yingying Jiao Xiaopei Wu Xiaojing Guo Key Laboratory of Intelligent Computing & Signal Processing MOE Anhui University Hefei China School of Computer Science and Technology Anhui University China

Brain-computer interface (BCI) is a specific Human-computer interface in which the brain wave is employed as the carrier of control information. The ultimate goal of BCI is to build a direct communication pathway between human brain and external environment that does not depend on the limb mobility and language. In this paper, we carry out the experiment about the left or right hand motor imagery, and support vector machine with genetic algorithm (GA-SVM) and back propagation neural network with genetic algorithm (GA-BP) are employed to classify the μ rhythm evoked by movement imagination. The experiment results prove that GA-SVM can easily find out the appropriate parameters of SVM and GA-BP can avoid getting into local minimization to great extend. So higher accuracy of classification is achieved.

关键词： Support vector machines Classification algorithms Kernel Biological cells Accuracy Educational institutions Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

A Network-based Approach for Protein Functions Prediction Using Locally Linear Embedding

A Network-based Approach for Protein Functions Prediction Us...

引用

The 4th International Conference on Bioinformatics and Biomedical Engineering(第四届IEEE生物信息与生物医学工程国际会议 iCBBE 2010)

作者： Haifeng Zhao Dengdi Sun Rifeng Wang Bin Luo Key Lab of Intelligent Computing & Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei 230039 P.R.China

Inferring protein functions from different data sources is a challenging task in the post-genomic era, as a large number of crude protein structures from structural genomics project are now solved without their biochemical functions characterized. Recently, many different methods have been used to predict protein functions including those based on Protein-Protein Interaction (PPI), structure, sequence relationship, gene expression data, etc. Among these approaches, methods based on protein interaction data are very promising. In this paper, we studied a network-based method using locally linear embedding (LLE). LLE is a robust learning algorithm that manipulates dimensionality reduction, neighborhood-preserving embedding for high-dimensional data. We first embed both annotated and unannotated proteins in a low dimensional Euclidean space;then, we apply semi-supervised learning techniques to classify unannotated proteins into different functional groups. Finally, we made predictions to the unknown functional proteins in yeast. 5-fold cross validation is then applied to the GO terms to compare the performance of different approaches, and the proposed method performs significantly better than the others.

关键词： Bioinformatics Semisupervised learning Genomics Protein sequence Gene expression Learning systems Sun intelligent networks intelligent structures computer networks

来源：评论

学校读者我要写书评

暂无评论

Inferring Protein Annotation from Topological Structural Analysis on Protein Interaction Network

Inferring Protein Annotation from Topological Structural Ana...

引用

The 4th International Conference on Bioinformatics and Biomedical Engineering(第四届IEEE生物信息与生物医学工程国际会议 iCBBE 2010)

作者： Dengdi Sun Jin Fan Haifeng Zhao Bin Luo Key Lab of Intelligent Computing & Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei 230039 P.R.China

As more and more high-throughput protein-protein interactions data are collected, a large fraction of newly discovered proteins have an unknown functional role. A challenge to the scientific community is to assign these newly proteins with a biological function that can be verified by experiment. On the basis of thorough analysis of existing protein function prediction, we take double direction enumeration method combined with the distance constrains to find protein pathway, and propose a new predicting model based on topological structural of protein-protein interaction (PPI) network and protein pathway, which greatly increases the speed of the algorithm. To validate the method, the Yeast Saccharomyces cerevisiae protein-protein interaction network and corresponding protein pathways are analyzed. Comparing with other methods, our results can substantially improve the accuracy and robustness of functional annotation.

关键词： Proteins Fungi Databases computer networks Biological system modeling Predictive models Organisms signal analysis Sun intelligent networks

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：