Title :
Negative Selection based method for Multi-Class problem classification
Author :
Markowska-Kaczmar, Urszula ; Kordas, Bartosz
Author_Institution :
Inst. of Appl. Informatics, Wroclaw Univ. of Technol.
Abstract :
Methods inspired by immune systems have recently shown their efficiency among other machine learning algorithms. This paper presents a new algorithm from the group of artificial immune systems (AIS) basing on a natural phenomenon taking place in human organism. The purpose of this work is to introduce to the negative selection approach for multi-class problems classification and investigate its efficiency
Keywords :
learning (artificial intelligence); pattern classification; artificial immune systems; machine learning; multiclass problem classification; negative selection approach; Artificial immune systems; Humans; Immune system; Informatics; Machine learning algorithms; Organisms; Pattern recognition; Protection; Supervised learning; Testing;
Conference_Titel :
Intelligent Systems Design and Applications, 2006. ISDA '06. Sixth International Conference on
Conference_Location :
Jinan
Print_ISBN :
0-7695-2528-8
DOI :
10.1109/ISDA.2006.253777
