Application of machine learning on brain cancer multiclass classification
Authors:
- 1 January 2017
- conference paper
- Published by AIP Publishing in AIP Conference Proceedings
Abstract
Classification of brain cancer is a problem of multiclass classification. One approach to solve this problem is by first transforming it into several binary problems. The microarray gene expression dataset has the two main characteristics of medical data: extremely many features (genes) and only a few number of samples. The application of machine learning on microarray gene expression dataset mainly consists of two steps: feature selection and classification. In this paper, the features are selected using a method based on support vector machine recursive feature elimination (SVM-RFE) principle which is improved to solve multiclass classification, called multiple multiclass SVM-RFE. Instead of using only the selected features on a single classifier, this method combines the result of multiple classifiers. The features are divided into subsets and SVM-RFE is used on each subset. Then, the selected features on each subset are put on separate classifiers. This method enhances the feature selection ability of each single SVM-RFE. Twin support vector machine (TWSVM) is used as the method of the classifier to reduce computational complexity. While ordinary SVM finds single optimum hyperplane, the main objective Twin SVM is to find two non-parallel optimum hyperplanes. The experiment on the brain cancer microarray gene expression dataset shows this method could classify 71,4% of the overall test data correctly, using 100 and 1000 genes selected from multiple multiclass SVM-RFE feature selection method. Furthermore, the per class results show that this method could classify data of normal and MD class with 100% accuracy.Keywords
This publication has 8 references indexed in Scilit:
- Multiclass classification machines with the complexity of a single binary classifierSignal Processing, 2013
- An overview on twin support vector machinesArtificial Intelligence Review, 2012
- Perspectives on Systematic Analyses of Gene Function in Arabidopsis thaliana: New Tools, Topics and TrendsCurrent Genomics, 2011
- MSVM-RFE: extensions of SVM-RFE for multiclass gene selection on DNA microarray dataBioinformatics, 2007
- Twin Support Vector Machines for Pattern ClassificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Multiple SVM-RFE for Gene Selection in Cancer Classification With Expression DataIEEE Transactions on Nanobioscience, 2005
- Gene selection from microarray data for cancer classification—a machine learning approachComputational Biology and Chemistry, 2005
- Gene Selection for Cancer Classification using Support Vector MachinesMachine Learning, 2002