摘要
本文提出一种基于独立成分分析(ICA)与支持向量机(SVM)的孤立点挖掘模型——ISOM模型,用ICA时观测到的多维随机向量进行独立成分分解,用SVM估计独立成分的密度函数,克服了传统孤立点挖掘方法的一些缺点,为数据挖掘提供了一种有效的方法,并通过实验验证了该模型的合理性与正确性。
ISOM, Outlier Mining Model Based on ICA ＆ SVM, is presented in this paper. This model transforms an observed multidimensional random vector into mutually independent components by ICA and estimates independent components＇ density function by SVM. Overcoming the defects of traditional outlier mining, the model of ISOM provides an efficient method for data mining, and its correctness and reasonableness ars also validated by the experiment results in this paper.
出处
《计算机科学》
CSCD
北大核心
2006年第9期175-177,共3页
Computer Science
基金
国家自然科学基金项目(10371135)资助。
关键词
孤立点
ICA
SVM
密度函数估计
Outlier, ICA（independent component analysis）, SVM（Support Vector Machine）, Estimation of density function
