A Novel IGA-based Approach for Outlier Detection
Outlier detection in large data sets is an active research field in data mining that has many applications in all those domains that can lead to illegal or abnormal behavior, such as fraud detection, network intrusion detection, insurance fraud, and the like. Now, a number of automated outlier detection methods are available. However, many of them are limited by assumptions of a distribution or require upper and lower predefined boundaries in which the data should exist. In this paper, an IGA-based outlier detection method is proposed. This method can detect multiple outliers at a time, not just one, and what we should do is nothing but specifying the number of outliers we want. Simulation results indicate that the proposed method can automatically detect outliers, and outperforms better than other related approaches.
Outlier detection Data mining Immune genetic algorithm (IGA)
Xueqin Zhang Zhaoxia Qu Lancang Yang Yuehui Chen
the School of Information Science and Engineering, University of Jinan, Jinan 250022, China the School of Control Science and Engineering, University of Jinan, Jinan 250022, China. the School of Computer Science and Technology, Shandong University, Jinan 250061, .China
国际会议
武汉
英文
2007-09-21（万方平台首次上网日期，不代表论文的发表时间）