检索结果-内蒙古大学图书馆

International Conference on Information Science and Engineering (ICISE)

作者： Shu-xia Lu Gui-en Cao Jie Meng Hua-chao Wang Key Lab. of Machine Learning and Computational Intelligence Hebei University Baoding Hebei China

When the training dataset is very large, the learning process of potential support vector machine takes up so large memory that the training speed is very slow. To accelerate the training speed of the potential support vector machine (PSVM) for large-scale datasets, a new method is proposed, which introduces PSVM based on the reduced samples. The new method removes most non-support vectors, and keeps the samples on and near the boundary, which may be the support vectors, as the new training samples. This method is more suitable to large-scale datasets. The experimental results show that the proposed method performs well to decrease the consumption of computer memory, and accelerate the training speed of PSVM.

关键词： Support vector machines Classification algorithms Training Algorithm design and analysis Optimization Accuracy Acceleration

来源：评论

学校读者我要写书评

暂无评论

Markov property of Markov chains and its test

Markov property of Markov chains and its test

引用

International Conference on machine learning and Cybernetics (ICMLC)

作者： Yu-Fen Zhang Qun-Feng Zhang Rui-Hua Yu Key Lab. for Machine Learning and Computational Intelligence Hebei University Baoding China Department of Information Technology Baoding University Baoding China

Markov chains, with Markov property as its essence, are widely used in the fields such as information theory, automatic control, communication techniques, genetics, computer sciences, economic administration, education administration, and market forecasts. While using Markov chains to predict the future events, we must test the Markov property of random variable sequences of the past statistic data. Only when the random variable sequences satisfy the Markov property, can the prediction could be precise. This paper discusses the concept of Markov property and its features, studies its test method, and by example demonstrates the effectiveness of this prediction method.

关键词： Markov processes Random variables machine learning Biological system modeling Prediction methods Water resources

来源：评论

学校读者我要写书评

暂无评论

A HSC-based sample selection method for Support Vector machine

A HSC-based sample selection method for Support Vector Machi...

引用

International Conference on machine learning and Cybernetics

作者： He, Qing Li, Ning Shi, Zhong-Zhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Hebei University Baoding 071002 Hebei China Graduate University of Chinese Academy of Sciences Hebei University Baoding 071002 Hebei China Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071002 Hebei China

ISBN: (纸本)9781424465262

Support Vector machine (SVM) is a classification technique of machine learning based on statistical learning theory. A quadratic optimization problem needs to be solved in the algorithm, and with the increase of the samples, the time complexity will also increase. So it is necessary to shrink training sets to reduce the time complexity. A sample selection method for SVM is proposed in this paper. It is inspired from the Hyper surface classification (HSC), which is a universal classification method based on Jordan Curve Theorem, and there is no need for mapping from lower-dimensional space to higher-dimensional space. The experiments show that the algorithm shrinks training sets keeping the accuracy for unseen vectors high. © 2010 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A new instance selection algorithm based on contribution for nearest neighbour classification

A new instance selection algorithm based on contribution for...

引用

International Conference on machine learning and Cybernetics

作者： Cai, Yong-Hua Wu, Bo He, Yu-Lin Zhang, Ye Department of Mathematics and Computer Science Hebei Normal University for Nationalities Chengde067000 Hebei China Automation Department Chengde Iron and Steel Branch Hebei Iron and Steel Group Co. Ltd. Chengde 067000 Hebei China Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071002 Hebei China

ISBN: (纸本)9781424465262

Nearest Neighbor Classifier is one of the most classical lazy learning schemes. The basic nearest neighbor classifiers suffer from the common problem that the instances used to train the classifier are all stored indiscriminately, and as a result, the required memory storage is huge and response time becomes slow with a large database. In this paper, a new Instances Selection algorithm based on Classification Contribution Function shortly named ISCC is presented. In this algorithm, a function is introduced to evaluate the classification ability of the instances. For each instance, the function considers its contribution to the neighbor instances not only with same class but also with different class. Then an instance with the highest value of Classification Contribution Function is added to the condensed subset and the instances which can be classified correctly are deleted in each iteration. This process is repeated until the subset is no longer getting larger. The time complexity of ISCC is Ο (in2). The experimental results on two artificial databases and some real databases demonstrate the effectiveness and the feasibility of the proposed algorithm. Compared to traditional methods, such as MCS, ICF and ENN, the condensed sets obtained by ISCC is superior in storage and classification accuracy. © 2010 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

An improved cluster oriented fuzzy decision trees 1

引用

12th International Conference on Rough Sets, Fuzzy Sets, Data Mining and Granular Computing, RSFDGrC 2009

作者： Su, Shan Wang, Xizhao Zhai, Junhai Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071002 China

ISBN: (数字)9783642106460

ISBN: (纸本)3642106455

In this paper, an improved cluster oriented decision trees algorithm shortly named ICFDT is presented. In this algorithm, fuzzy C-means clustering algorithm (FCM) without instance lab.ls is used to split the nodes and two novel node expanding criteria are proposed. One criterion uses the ratio of homogenous samples in the node to split;the other splits the node by membership degree without lab.ls. The experimental results in artificial and machine learning datasets show that our method can achieve better performance comparing to standard decision tree named C4.5. © 2009 Springer-Verlag Berlin Heidelberg.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A fast support vector machine classification algorithm based on Karush-Kuhn-Tucker conditions 1

引用

12th International Conference on Rough Sets, Fuzzy Sets, Data Mining and Granular Computing, RSFDGrC 2009

作者： Zhang, Ying Wang, Xizhao Zhai, Junhai Key Lab. for Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071002 China

ISBN: (数字)9783642106460

ISBN: (纸本)3642106455

Although SVM have shown potential and promising performance in classification, they have been limited by speed particularly when the training data set is large. In this paper, we propose an algorithm called the fast SVM classification algorithm based on Karush-Kuhn-Tucker (KKT) conditions. In this algorithm, we remove points that are independent of support vectors firstly in the training process, and then decompose the remaining points into blocks to accelerate the next training. From the theoretical analysis, this algorithm can remarkably reduce the computation complexity and accelerate SVM training. And experiments on both artificial and real datasets demonstrate the efficiency of this algorithm. © 2009 Springer-Verlag Berlin Heidelberg.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An improved research method about the similarity calculation of ontology

An improved research method about the similarity calculation...

引用

2009 International Conference on Information Engineering and Computer Science, ICIECS 2009

作者： Li, Xin-Fu Yin, Peng Zheng, Mei Key Lab. in Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding China Institute of International Education Yanshan University Qinhuangdao China

ISBN: (纸本)9781424449941

Ontology mapping has been widely used in ontology application, but the similarity calculation becomes a thorny issue in the process of ontology mapping. In this paper, the different elements of ontology are considered. Semantic similarity and concept similarity are integrated to get the ontology similarity. During the similarity calculation of the concept attributes, filter strategy is used to reduce the number of concept attributes, and a method of attributes similarity calculation is proposed. In addition, comprehensive similarity calculation method is given including the semantic and the concept of ontology. The experiment results show that this approach can improve the precision effectively. ©2009 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection based on feature relevance

Unsupervised feature selection based on feature relevance

引用

International Conference on machine learning and Cybernetics (ICMLC)

作者： Feng Zhang Ya-Jun Zhao Jun-Fen Key Lab. of Machine Learning and computational Intelligence Hebei University Baoding China College of Physics Science and Technology Hebei University Baoding China Key Lab. of Machine Learning and computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071002 China

Feature selection is an essential technique used in data mining and machine learning. Many feature selection methods have been studied for supervised problems. However feature selection for unsupervised learning is rarely studied. In this paper, we proposed an approach to select features for unsupervised problems. Firstly, the original features are clustered according to their relevance degree defined by mutual information. And then the most informative feature is selected from each cluster based on the contribution-information of each feature. The experimental results show that the proposed method can match some popular supervised feature selection methods. And the features selected by our method do include most of the information hidden in the overall original features.

关键词： machine learning Mutual information Random variables Entropy Unsupervised learning Information theory Cybernetics Educational institutions Data mining computational intelligence

来源：评论

学校读者我要写书评

暂无评论

ON THE APPLICATION OF ROUGH SETS TO DATA MINING IN ECONOMIC PRACTICE

ON THE APPLICATION OF ROUGH SETS TO DATA MINING IN ECONOMIC ...

引用

2009 International Conference on machine learning and Cybernetics(2009机器学习与控制论国际会议)

作者： QUN-FENG ZHANG SU-YUN ZHAO YUN-CHAO BAI Key Lab.of Machine Learning and Computational Intelligence College of Mathematics and Computer Scie Key Lab.of Machine Learning and Computational Intelligence College of Mathematics and Computer Scie College of Economics Hebei University Baoding 071002 China

Mathematical models play an important role in the studies of modern economics. But in many fields of economics, it is difficult to build mathematical models for complex phenomena. So data mining is getting more and more popular in discovering the potential pattern of economic knowledge from databases. As a powerful tool for data mining, rough set theory has been widely used. In this research, we draw guidelines from several cases of rough set application in economic practice. Furthermore, to avoid the drawbacks of the existing methods, we develop a methodology for rough analysis in economic sector by combining the advantages of the fuzzy variable precision rough set model.

关键词： Data mining Rough sets Reducts Fuzzy variable precision rough sets

来源：评论

学校读者我要写书评

暂无评论

A text classification method based on the improved CR-tree and the weighted association rule

引用

Journal of computational Information Systems 2009年第6期5卷 1577-1584页

作者： Wang, Yu Zhao, Yao Yuan, Fang College of Mathematics and Computer Science Hebei University Baoding 071002 China Key Lab. in Machine Learning and Computational Intelligence of Hebei Province Baoding 071002 China

Classification based on association rules is a common and easily understand algorithm for text classification. To improve its classification accuracy, the key is to generate more effective rules. Sometimes, it will overdraw the role of some training texts. To avoiding this and generate more effective rules, this paper defines the Classification Path and proposes a new text classifier (CP-tree) based on CR-tree. When a new text is coming, to avoid overdrawing, association rules are generated through scanning Classification Path;in addition, to make the role of association rules in class prediction more reasonable, the association rules and weight for the new text are obtained not only according to the training texts, but also the new texts. Experimental results show that the accuracy of text classification is improved with the algorithm based on CP-tree. 1553-9105/ Copyright © 2009 Binary Information Press.

关键词： Classification (of information)

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：