检索结果-内蒙古大学图书馆

2nd International Conference on Information Technology and Electronic Commerce, ICITEC 2014

作者： An, Lei-Lei Xing, Hong-Jie Key Laboratory of Machine Learning and Computational Intelligence College of Computer Science and Technology Hebei University Baoding Hebei Province071002 China

ISBN: (纸本)9781479952984

In this paper, linear discriminant analysis (LDA) based on Lp-norm (LDA-Lp) optimization method is proposed. The objective function utilizing the Lp-norm with arbitrary p value is studied. By maximizing the Lp-norm-based ratio between the between-class scatter and the within-class scatter, LDA-Lp can construct a set of local optimal projection vectors. Moreover, the optimal projection vectors can be obtained by the gradient ascent method. Experimental results on the two synthetic and fourteen benchmark datasets demonstrate that the better performance of LDA-Lp can be achieved by choosing the optimal value of p. © 2014 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Efficient image representation for object recognition via pivots selection

引用

Frontiers of Computer Science 2015年第3期9卷 383-391页

作者： Bojun XIE Yi LIU HuiZHANG Jian YU Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University Beijing 100044 China Key Lab of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071000 China

Patch-level features are essential for achieving good performance in computer vision tasks. Besides well- known pre-defined patch-level descriptors such as scalein- variant feature transform （SIFT） and histogram of oriented gradient （HOG）, the kernel descriptor （KD） method [1] of- fers a new way to ＂grow-up＂ features from a match-kernel defined over image patch pairs using kernel principal compo- nent analysis （KPCA） and yields impressive results. In this paper, we present efficient kernel descriptor （EKD） and efficient hierarchical kernel descriptor （EHKD）, which are built upon incomplete Cholesky decomposition. EKD au- tomatically selects a small number of pivot features for gener- ating patch-level features to achieve better computational effi- ciency. EHKD recursively applies EKD to form image-level features layer-by-layer. Perhaps due to parsimony, we find surprisingly that the EKD and EHKD approaches achieved competitive results on several public datasets compared with other state-of-the-art methods, at an improved efficiency over KD.

关键词： efficient kernel descriptor efficient hierarchi-cal kernel descriptor incomplete Cholesky decomposition,patch-level features image-level features

来源：评论

学校读者我要写书评

暂无评论

Optimization methods for resources allocation in real-time strategy games

Optimization methods for resources allocation in real-time s...

引用

2011 International Conference on machine learning and Cybernetics, ICMLC 2011

作者： Tong, Xiao-Lei Li, Yan Li, Wen-Liang Zhang, Lei Key Lab. In Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071002 Hebei Province China Handan Hospital of Traditional Chinese Medicine Handan 056000 China

ISBN: (纸本)9781457703065

In order to meet the demands of the real time strategy (RTS) games, two learning methods are proposed based on genetic algorithm (GA) and Particle swarm optimization (PSO) to handle the problem of multi-team weapon target assignment (MT-WTA) and distribution of defensive position with restrictive limit of weapon resource. The goal is to take the greatest destruction on the targets. Firstly, we use GA to assign different types of weapons under limited resources. Secondly, we put the optimal results from the first stage into a random game's map to obtain final defensive locations. Then GA and PSO are used to achieve the best distribution of defensive positions respectively and their performance is compared in RTS Games. Both of these two methods have provided efficient, interesting AI to solve real-time strategy games problems, the experimental results can well support this point. © 2011 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Incremental approach for updating approximations of variable precision rough set based on dominance relations 3

Incremental approach for updating approximations of variable...

引用

3rd International Conference on Information Technology and Management Innovation, ICITMI 2014

作者： Li, Yan Hou, Jia Jia Liu, Xiao Qing Key Lab of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding China

ISBN: (纸本)9783038352396

Variable precision rough set (VPRS) based on dominance relation is an extension of traditional rough set by which can handle preference-ordered information flexibly. This paper focuses on the maintenance of approximations in dominance based VPRS when the objects in an information system vary over time. The incremental updating principles are given as inserting or deleting an object, and some experimental evaluations validates the effectiveness of the proposed method. © 2014 Trans Tech Publications, Switzerland.

关键词： Rough set theory

来源：评论

学校读者我要写书评

暂无评论

Maintaining dynamic information systems using incremental dominance-based rough set approach 3

Maintaining dynamic information systems using incremental do...

引用

3rd International Conference on Information Technology and Management Innovation, ICITMI 2014

作者： Li, Yan Liu, Xiao Qing Hou, Jia Jia Key Lab of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding China

ISBN: (纸本)9783038352396

Dominance-based rough sets approach (DRSA) is an effective tool to deal with information with preference-ordered attribute domain. In practice, many information systems may evolve when attribute values are changed. Updating set approximations for these dynamic information systems is a necessary step for further knowledge reduction and decision making in DRSA. The purpose of this paper is to present an incremental approach when the information system alters dynamically with the change of condition attribute values. The updating rules are given with proofs, and the experimental evaluations on UCI data show that the incremental approach outperforms the original non-incremental one. © 2014 Trans Tech Publications, Switzerland.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

Robust feature extraction for novelty detection based on regularized correntropy criterion

Robust feature extraction for novelty detection based on reg...

引用

IEEE International Conference on Systems, Man, and Cybernetics (SMC)

作者： Ren, Huan-Ru Xing, Hong-Jie Hebei Univ Coll Math & Comp Sci Key Lab Machine Learning & Computat Intelligence Baoding 071002 Hebei Province Peoples R China

ISBN: (纸本)9781467317146

In this paper, a robust feature extraction method based on regularized correntropy criterion (RCC) is proposed for novelty detection. In RCC, the criterion aims to maximize the difference between the correntropy of the normal data with their mean and the correntropy of the novel data with the mean of normal data. Moreover, the optimal projection vectors in the proposed objective function can be obtained by the half-quadratic (HQ) optimization technique with an iterative manner. Experimental results on one synthetic data set and nine benchmark data sets for novelty detection demonstrate that the proposed method is superior to its related approaches.

关键词： Correntropy half-quadratic optimization feature extraction novelty detection

来源：评论

学校读者我要写书评

暂无评论

A fast positive-region reduction method based on dominance-equivalence relations

A fast positive-region reduction method based on dominance-e...

引用

2016 International Conference on machine learning and Cybernetics, ICMLC 2016

作者： Jin, Yongfei Li, Yan He, Qiang Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding Hebei Province071002 China School of Science Beijing University of Civil Engineering and Architecture Beijing102616 China

ISBN: (纸本)9781509003891

In this paper, we consider decision systems which consist of preference ordered conditional attributes and symbolic decision attributes. Thus, dominance relations and equivalence relations can be respectively defined on the conditional attribute set and decision attribute set. Based on this combined dominance-equivalence relations, a fast positive-region reduction (FPR) algorithm is developed by introducing the concept of positive approximation together with positive region reduction. The computation load of attribute reduction has been greatly reduced when compared with the original positive-region reduction algorithm (PR). Finally, the experimental results on 9 UCI data are demonstrated to make comparisons between the PR and the FPR method. © 2016 IEEE.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Feature extended short text categorization based on theme ontology

Feature extended short text categorization based on theme on...

引用

2012 9th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2012

作者： Zhan, Yan Chen, Hao Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding China College of Mathematics and Computer Science Hebei University Baoding China

ISBN: (纸本)9781467300223

Short text classification problem as text classification a branch, in addition to the same with traditional text classification to a certain degree, still need to face some special problems to be solved, because of short text length, features sparse, measuring the words difficultly. Due to the nature of ontology emphasize related field concept, which has the defect of few characteristics in short text, it is necessary to emphasize the relationship between semantic. This paper uses the feature extended method based on theme Ontology. As considering the semantic relations, it can get better classification performance compared to the conventional method. Meanwhile, using Case-Base Maintenance learning via the GC (Generalization Capability) algorithm, which can reduce the case number into K-NN algorithm, can improve efficiency when indexing near neighbor in K-Nearest Neighbor algorithm. The numerical experiments prove the validity of this learning algorithm. © 2012 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Chinese text categorization study based on CBM learning

Chinese text categorization study based on CBM learning

引用

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

ISBN: (纸本)9781424459346

Text Categorization (TC) is an important component in many information organization and information management tasks. In many TC applications, the case-base grows at a fast rate and this causes inefficiency in the case retrieval process. Using Case-Base Maintenance learning via the GC (Generalization Capability) altorithm, which can reduce the case number into KNN algorithm, can improve efficiency when indexing near neighbor in K-Nearest Neighbor algorithm. The numerical experiments prove the validity of this learning algorithm. Since K-NN algorithm is used extensively to a variety of areas, we can improve classification performance further in TC. ©2010 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

A comparative study of four Fuzzy Integrals for classifier fusion

A comparative study of four Fuzzy Integrals for classifier f...

引用

International Conference on machine learning and Cybernetics

作者： Feng, Hui-Min Li, Xue-Fei Chen, Jun-Fen Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071002 China College of Science Agricultural University of Hebei Baoding 071001 China

ISBN: (纸本)9781424465262

Fuzzy Integral is widely accepted and applied in multi-classifier fusion to express the importance of individual classifiers and the interaction among classifiers. In this fusion model, there are two keys to determine. One is determining the fuzzy measure. Many researchers have done much work and proposed many types of fuzzy measure and methods to determine fuzzy measures. Another is selecting from four types of fuzzy integral: Sugeno integral, Choquet integral, upper integral and lower integral. Usually, the type of fuzzy integral is specified in advance. Choquet integral is often the choice. This paper is to compare comprehensively four fuzzy integrals in multiple-classifier fusion and hope to give the foundation for selecting Choquet integral. According the theoretical and experimental analysis, it gives the conclusion that Choquet integral is the best suitable for classifier fusion. © 2010 IEEE.

关键词： Integral equations

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：