Gene expression data classification using genetic algorithm-based feature selection

Abstract

In this study, hybrid methods are proposed for feature selection and classification of gene expression datasets.In the proposed genetic algorithm / support vector machine (GA-SVM) and genetic algorithm / k nearest neighbor (GA-KNN) hybrid methods, genetic algorithm is improved by Pearson correlation coefficient, Relief-F or mutual information.Crossover and selection operations of the genetic algorithm are specialized. Eight different gene expression datasets are used for classification process. The classification performances of proposed methods are compared with the traditional GA-KNN and GA-SVM wrapper methods and the other literature studies. Classification results demonstrate that higher accuracy rates are obtained with the proposed methods compared to the other methods for all datasets.

Penerapan Algoritma K-Nearest Neighbor Menggunakan Wrapper Sebagai Preprocessing untuk Penentuan Keterangan Berat Badan Manusia

“…Dengan demikian, algoritma heuristik atau evolusioner lebih disukai untuk pemilihan subset. Metode wrapper mempertimbangkan ketergantungan dan hubungan antar gen. Meskipun kompleksitas komputasinya lebih tinggi daripada metode filter, akurasi metode pembungkus jauh lebih baik [12]. Tujuan dari penelitian ini adalah menganalisis tingkat akurasi hasil prediksi berat badan menggunakan algoritma K-NN tanpa dan dengan wrapper preprocessing.…”