Microarray data classification using automatic SVM kernel selection

Microarray classification is one of the most important emerging clinical applications in the medical community. Machine learning algorithms are most frequently used to complete this task. We selected one of the state-of-the-art kernel based algorithms, the Support Vector Machine (SVM), to classify microarray data. Among the large scale of kernels, a significant research question requires answering what is the best kernel for patient diagnosis based on microarray data using SVM?. We explain three solutions based on data visualization and quantitative measure. The proposed solution is then tested by different types of microarray problems. Finally, we find that the rule based approach can be useful for automatic kernel selection of SVM to classify microarray data.