Schizophrenia Classification Using Fuzzy Kernel C-Means

Abstract

Schizophrenia is a severe mental disorder that induces the mind, feeling, and behavior. Earlier treatment for this disease is essential; therefore, the ability to predict schizophrenia also becomes essential. Fuzzy kernel c-means was proposed in this research, utilizing the data obtained from Northwestern University, which consists of 171 schizophrenia and 221 non-schizophrenia samples. There are several kernel functions; however, RBF and polynomial kernel function were used. As the evaluation, k-fold cross-validation with k = 3, 5, 7, and 10 was used, and each of the performances was analyzed. From the experiments, it was concluded that fuzzy kernel c-means using RBF kernel with σ = 0.01 and σ = 1 provides better performance than polynomial kernel with a similar running time with fuzzy c-means.