Genetic Algorithm for Variable Selection and Parameter Optimization in SVM and Fuzzy SVM for Colon Cancer Microarray Classification

Colon cancer is the second leading cause of cancer-related deaths in the world, hence research on that topic needs to be undertaken with improvement. Recent advanced in microarray technology allows the monitoring of the expression level of a large set of genes simultaneously. Microarray data is a type of high-dimensional data with hundreds or even thousands number of genes (features), while usually the number of patients observed (observations) is much smaller than the number of features. This study uses a colon cancer microarray dataset contains two class of genes, normal and tumor. The aims of this study is to develop a classification model using fuzzy support vector machines (FSVM) hybridized with genetic algorithm (GA) for classifying individuals based on gene expression. Fuzzy memberships was used in SVM in order to deal with the case of imbalanced microarray data. Meanwhile, the role of genetic algorithm is, firstly, to select the relevant genes as the features and, secondly, to optimize the parameter of FSVM as GA is able to handle the problem of nonlinear optimization that has a high dimension, adaptable, and easily combined with other methods. The classification using FCBF selection has a higher accuracy value than the ones without the selection. The results also show that FSVM that has been optimized using GA has the highest accuracy value compared to other classification methods used in this study.

Gene Microarray Cancer Classification using Correlation Based Feature Selection Algorithm and Rules Classifiers

Gene microarray classification problems are considered a challenge task since the datasets contain few number of samples with high number of genes (features). The genes subset selection in microarray data play an important role for minimizing the computational load and solving classification problems. In this paper, the Correlation-based Feature Selection (CFS) algorithm is utilized in the feature selection process to reduce the dimensionality of data and finding a set of discriminatory genes. Then, the Decision Table, JRip, and OneR are employed for classification process. The proposed approach of gene selection and classification is tested on 11 microarray datasets and the performances of the filtered datasets are compared with the original datasets. The experimental results showed that CFS can effectively screen irrelevant, redundant, and noisy features. In addition, the results for all datasets proved that the proposed approach with a small number of genes can achieve high prediction accuracy and fast computational speed. Considering the average accuracy for all the analysis of microarray data, the JRip achieved the best result as compared to Decision Table, and OneR classifier. The proposed approach has a remarkable impact on the classification accuracy especially when the data is complicated with multiple classes and high number of genes.