基于支持向量机的分类算法及其应用（英文版）

　　SVM基于结构风险最小化，克服了传统方法的过度拟合和陷于局部最小化问题，具有泛化能力强等优点；使用核函数将数据映射到高维空间，在不增加计算复杂度的情况下，有效地克服了维数灾难问题。当然，当前SVM的研究也存在一些局限性。本书理论详实、实验结果丰富，很好将理论研究与应用研究结合起来，对读者学习与研究SVM具有一定的帮助。

暂缺《基于支持向量机的分类算法及其应用（英文版）》作者简介

Chapter I Introduction of SVM
1.1 SVM
1.2 Binary Classification
Chapter II Sample Reduction and Attribute Selection in SVM
2.1 The Design and Performance of Intrusion Detection System Classifier Based
on the Time Series Windows
2.2 Application of PSVM and Data Processing for Intrusion Detection
2.3 Less is More:Data Processing with SVM for Intrusion Detection
Chapter III Parameter Selection of SVM
3.1 Principle of BSA
3.2 BSA-SVM Algorithm Design
3.3 BSA-SVM Algorithm Principle
3.4 BSA-SVM Algorithm Simulation Experiment
3.5 Conclusion
Chapter IV Fusion Classification Based on SVM
4.1 Intrusion Detection Using Ensemble of SVM Classifiers
4.2 An Integrated Decision System for Intrusion Detection
4.3 Intrusion Detection in Ad-hoc Networks
Chapter V Intelligence Classification Based on SVM
5.1 Introduction
5.2 An Overview of Active Learning
5.3 Methodology
5.4 Experiments
5.5 Conclusion
Chapter VI SVM Based on Privileged Information
6.1 Support Vector Classification Using Partial Privileged Information
6.2 A New Learning Paradigm:Learning Using Partial Privileged Information
References