Title :
Hybrid flexible neural tree approach for leukemia cancer classification
Author :
Zhang, Lei ; Chen, Zhenxiang ; Abraham, Ajith ; Zhenxiang Chen
Author_Institution :
Shandong Provincial Key Lab. of Network Based Intell. Comput., Univ. of Jinan, Jinan, China
Abstract :
In this paper, a novel method for improving flexible neural tree is proposed to classify the leukemia cancer data. The hybrid flexible neural tree with pre-defined instruction sets can be created and evolved. The structure and parameter of hybrid flexible neural tree are optimized using probabilistic incremental program evolution (PIPE) and particle swarm optimization (PSO) algorithm. The experimental results indicate that the proposed method illustrates feasible and efficient for the classifications of microarray data.
Keywords :
cancer; medical computing; neural nets; particle swarm optimisation; pattern classification; probability; hybrid flexible neural tree approach; instruction set; leukemia cancer classification; microarray data classification; particle swarm optimization; probabilistic incremental program evolution; Accuracy; Cancer; Computational modeling; Gene expression; Neurons; Optimization; Vectors; flexible neural tree; hybrid evolutionary method; leukemia cancer data; particle swarm optimization;
Conference_Titel :
Information and Communication Technologies (WICT), 2011 World Congress on
Conference_Location :
Mumbai
Print_ISBN :
978-1-4673-0127-5
DOI :
10.1109/WICT.2011.6141213
