A novel multi-task support vector sample learning technique to predict classification of cancer

摘要

We have implemented a systematic method that can improve cancer classification. By extracting significant samples (which we refer to as support vector samples because they are located only on support vectors), we can let the back propagation neural networking (BPNN) to learn more tasks. We call this approach the multi-task support vector sample learning (MTSVSL) technique. We demonstrate experimentally that the genes selected by our MTSVSL method yield super classification performance by applying to leukemia and prostate cancer gene expression datasets. Our proposed MTSVSL method is a novel approach that is expedient and can produce very good performance in cancer diagnosis and clinical outcome prediction. Our method has been successfully applied to cancer type-based classifications on microarray gene expression. MTSVSL can improve the accuracy of traditional BPNN architecture.