Data mining based on gene expression programming and clonal selection

Karakasis, VK; Stafylopatis, A

dc.contributor.author	Karakasis, VK	en
dc.contributor.author	Stafylopatis, A	en
dc.date.accessioned	2014-03-01T02:43:59Z
dc.date.available	2014-03-01T02:43:59Z
dc.date.issued	2006	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31599
dc.subject	Benchmark Problem	en
dc.subject	Clonal Selection	en
dc.subject	Clonal Selection Algorithm	en
dc.subject	Computational Efficiency	en
dc.subject	Convergence Rate	en
dc.subject	Data Mining	en
dc.subject	Gene Expression Programming	en
dc.subject	Prediction Accuracy	en
dc.subject.other	Clonal Selection Principles	en
dc.subject.other	Gene Expression Programming (GEP)	en
dc.subject.other	Computational methods	en
dc.subject.other	Disease control	en
dc.subject.other	Evolutionary algorithms	en
dc.subject.other	Gene expression	en
dc.subject.other	Genetic programming	en
dc.subject.other	Logic programming	en
dc.subject.other	Problem solving	en
dc.subject.other	Data mining	en
dc.title	Data mining based on gene expression programming and clonal selection	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/CEC.2006.1688353	en
heal.identifier.secondary	http://dx.doi.org/10.1109/CEC.2006.1688353	en
heal.identifier.secondary	1688353	en
heal.publicationDate	2006	en
heal.abstract	A hybrid evolutionary technique is proposed for data mining tasks, which combines the Clonal Selection Principle with Gene Expression Programming (GEP). The proposed algorithm introduces the notion of Data Class Antigens, which is used to represent a class of data. The produced rules are evolved by a clonal selection algorithm, which extends the recently proposed CLONALG algorithm. In the present algorithm, among other new features, a receptor editing step has been incorporated. Moreover, the rules themselves are represented as antibodies, which are coded as GEP chromosomes, in order to exploit the flexibility and the expressiveness of such encoding. The algorithm is tested on some benchmark problems of the UCI repository, and in particular on the set of MONK problems and the Pima Indians Diabetes problem. In both problems, the results in terms of prediction accuracy are very satisfactory, albeit slightly less accurate than those obtained by a standard GEP technique. In terms of convergence rate and computational efficiency, however, the technique proposed here markedly outperforms the standard GEP algorithm. © 2006 IEEE.	en
heal.journalName	2006 IEEE Congress on Evolutionary Computation, CEC 2006	en
dc.identifier.doi	10.1109/CEC.2006.1688353	en
dc.identifier.spage	514	en
dc.identifier.epage	521	en