A support vector machine based on kernel k-means for detecting the liver cancer disease

Liver cancer can be caused by hepatitis B virus (HBV) infection. This genome virus inserts genetic material into its host. Moreover, each gene has numerous HBV DNA sequences due to its high mutation rate in replication. Thus, detecting virus is a difficult task. A support vector machine (SVM) is a robust machine-learning algorithm for detecting liver cancer disease. However, a high data volume can reduce its computation speed and performance measures. Therefore, we propose data simplification using Kernel k-means clustering method to construct the SVM classifier model by minimizing objective function as object distance. Based on experimental results, the proposed method's performance evaluation was higher than SVM algorithm without kernel k-means, especially for the sensitivity significantly increased. The accuracy rate and AUC of the proposed method were around 98% and 0.95. Furthermore, the performance of proposed method is also predominant of the other machine learning: Random Forest, Naive Bayes, Naural Network and C5.0.