Immune-evolutionary strategy and its application

Author

Jianguo, Zheng ; Fang, Liu ; Licheng, Jiao

Author_Institution

Key Lab. of Radar Signal Process., Xidian Univ., Xi´´an, China

Volume

2

fYear

2002

fDate

26-30 Aug. 2002

Firstpage

1819

Abstract

A novel global parallel algorithm, the immune-evolutionary strategy (IES), is proposed for rule extraction in data-mining; it combines the immune mechanism and the evolutionary mechanism. The main idea of IES is to utilize theoretically background knowledge and local characteristic information for seeking ways and means of finding the optimal solution when dealing with difficult problems. IES is illustrated to be able to improve the stability of the population, increase the holistic performance and make the rules extracted have higher precision.

Keywords

data mining; database management systems; evolutionary computation; knowledge based systems; parallel algorithms; background knowledge; data-mining; global parallel algorithm; holistic performance; immune-evolutionary strategy; knowledge discovery; large databases; local characteristic information; machine learning; optimal solution; population stability; rule extraction; Data mining; Delta modulation; Evolution (biology); Immune system; Neural networks; Organisms; Radar signal processing; Radar theory; Signal processing; Signal processing algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, 2002 6th International Conference on

Print_ISBN

0-7803-7488-6

Type

conf

DOI

10.1109/ICOSP.2002.1180157

Filename

1180157