期刊名称：International Journal of Computer Science & Information Technology (IJCSIT)
印刷版ISSN：0975-4660
电子版ISSN：0975-3826
出版年度：2017
卷号：9
期号：4
页码：57
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：siRNA has become an indispensible tool for silencing gene expression. It can act as an antiviral agent inRNAi pathway against plant diseases caused by plant viruses. However, identification of appropriatefeatures for effective siRNA design has become a pressing issue for researchers which need to be resolved.Feature selection is a vital pre-processing technique involved in bioinformatics data set to find the mostdiscriminative information not only for dimensionality reduction and detection of relevance features butalso for minimizing the cost associated with features to design an accurate learning system. In this paper,we propose an ANN based feature selection approach using hybrid GA-PSO for selecting feature subset bydiscarding the irrelevant features and evaluating the cost of the model training. The results showed that theperformance of proposed hybrid GA-PSO model outperformed the results of general PSO.
