Article,
Extreme Learning Machine for Microarray Cancer Classification
International Journal on Recent and Innovation Trends in Computing and Communication, 3 (1): 419--422 (January 2015)
DOI: 10.17762/ijritcc2321-8169.150183
Abstract
Cancer is a diseases in which a set of cells has not able controlled their growth, attack that interrupts upon and destroy the nearest tissues or spreading to other locations in the body. Cancer has become one of the perilous diseases in the present scenario. In this paper, the recently developed Extreme Learning Machine is used for classification problems in cancer diagnosis area. ELM is an available learning algorithm for single layer feed forward neural network. The advanced and developed methodology known for cancer multi classification using ELM microarray gene expression cancer diagnosis, this used for directing multi category classification problems in the cancer diagnosis area. ELM avoids many problems, improper learning rate and over fitting commonly faced by iterative learning methods and completes the training very fast. The performance of classification ELM on three benchmark microarray data for cancer diagnosis, namely Lymphoma data set, Leukemia data set, SRBCT data set. The results of experiments with RVM and ELM shows that for many categories of ELM still outperformer with RVM
