期刊名称:Journal of Theoretical and Applied Information Technology
印刷版ISSN:1992-8645
电子版ISSN:1817-3195
出版年度:2014
卷号:68
期号:3
出版社:Journal of Theoretical and Applied
摘要:The research studies the suitability of Extreme Learning Machines (ELM) for resolving bioinformatics and biomedical classification problems. It is used for some direct multicategory classification to solve those problems. The cancer diagnosis has three benchmark microarray datasets for evaluated the multi-category classification performance of ELM. In order to test their overall performance, an experimental study is presented based on three gene microarray datasets found in bioinformatics and biomedical domains. This research work use this ELM for quick performance and it is better accuracies. The result can be produces with minimum time compared to artificial neural networks methods. This method shows promising classification accuracy for all the test data sets. It also shows the relevance of the selected genes in terms of their biological functions.
关键词:Cancer classification; DNA microarray gene expression data; Extreme learning machine.