評估基於微陣列晶片資料之動態參數基因演算法（GADP）的最適分類器

Abstract

Recently, due to the factor that the microarray technology can be used to measure the expression levels of thousands of genes simultaneously, it has been widely applied in the areas of bioinformatics and clinical diagnosis. Although thousands of genes are measured simultaneously by using microarray, most of them are irrelevant or insignificant for clinical diagnosis or research. Therefore, several novel methods have been proposed to select relevant genes. Among those gene selection methods, the genetic algorithm with dynamic parameters (GADP) could select the fewer genes with higher prediction accuracy. However, the selected genes still need the classifier to verify the ability of the correct classification for the target category. Consequently, it is important to select the suitable classifier that can accurately judge the target category with the selected genes. In this study, six commonly used classifiers with the selected genes will be compared for selecting the suitable classifier based on the GADP algorithm, including support vector machine (SVM), k-nearest neighbor (KNN), artificial neural network (ANN), linear discriminant analysis (LDA), decision tree (DT), and naive Bayes classifier (NB).