Multiclass classification of leukemia cancer data using Fuzzy Support Vector Machine (FSVM) with feature selection using Principal Component Analysis (PCA)

Abstract Cancer is the second leading cause of death globally. According to WHO prediction (2015) cases cancer deaths will increase 21.6 million by 2030. Therefore, early detection necessary avoid spread and machine learning required performance in cancer. In general, microarray data consist many features. However, there are several features that did not have important information classification these be summarized from under some common underlying factors into fewer components using Principal Component Analysis (PCA) method. Then, we select most who for This paper focuses on comparison without PCA method coupled with Fuzzy Support Vectors Machines (FSVM) classification. The experimental results, FSVM accuracy 87.69 % 96.92 (obtained 60 features).