Title: A multi-objective feature selection and classifier ensemble technique for microarray data analysis
Authors: Rasmita Dash; Bijan Bihari Misra
Addresses: Department of Computer Science & Engineering, Siksha 'O' Anusandhan Deemed to be University, Bhubaneswar 751030, Odisha, India ' Department of Computer Science & Engineering, Silicon Institute of Technology, Bhubaneswar 751024, Odisha, India
Abstract: Since last few years, microarray technology has got tremendous application in many biomedical researches. Many intelligent models have been developed with different biological interpretation. This work presents a multi-objective feature selection and classifier ensemble (MOFSCE) technique for microarray data. MOFSCE works in two phases. The first phase is a pre-processing step where bi-objective optimisation technique is used to identify the significant genes through Pareto front. Here seven feature ranking approaches are used to develop 21 bi-objective feature selection (BOFS) models. The performance of BOFS model varies with different datasets. Therefore, grading system is used to identify stable BOFS model. In the second phase a classifier ensemble is build up that receives selected features from the identified BOFS model. Output of the classifiers is presented to a harmony search based functional link artificial neural network (HSFLANN) for decision. Performance of MOFSCE is evaluated using seven publicly available microarray datasets.
Keywords: feature selection; Pareto optimisation; ensemble approaches; microarray data classification; functional link artificial neural network; harmony search; statistical test.
International Journal of Data Mining and Bioinformatics, 2018 Vol.20 No.2, pp.123 - 160
Received: 19 Sep 2017
Accepted: 03 May 2018
Published online: 27 Jul 2018 *