Integration of ANN and Statistical Method for Outlier Detection in Complex System

摘要：

In this paper, an outlier detection method based on radial basis functions-principal component analysis (RBF-PCA) approach and Prescott method, a statistical detection approach, is proposed to detect the outlier in the complex system without clear mechanisms. Making full use of the capacity of neural networks on nonlinear mapping and the effect of Prescott method on outlier detection in linear model, the integration of two approaches makes the outlier detection in complex nonlinear system more convenient, reliable, and precise. The experiments show us the satisfactory effects of the proposed method and its superiority over some distances based methods. Furthermore, some rules were discussed for the wide use of the proposed integrated method

关键词： outlier radial basis function networks principal component analysis statistics

作者: Weixiang Zhao Lide Wu

作者单位: Computer Science Department,Fudan University,Shanghai 200433, P. R. China

会议类型: 国际会议

会议名称: 8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)

会议地点: 上海

会议语种:英文

页码: 1652-1657

在线出版日期: 2001-11-14（万方平台首次上网日期，不代表论文的发表时间）