The Hybrid of Kernel K-Means and Fuzzy Kernel C-Means Clustering Algorithm in Diagnosing Thalassemia

This study aims to investigate thalassemia detection using hybrid of Kernel K-Means and Fuzzy Kernel C-Means clustering algorithm using a Gaussian Radial Basis Function (RBF) and polynomial kernel function. The main advantage of the method is its simplicity and speed in the implementation of the algorithm because it is the mixture of two simple but powerful methods in clustering. The first step uses kernel k-means clustering to obtain the initial set of centroids. Then, the Fuzzy Kernel C-Means clustering algorithm is implemented to obtain the final set of centroids that are used to predict the diagnosis. Experimentation with this method is performed using the thalassemia dataset provided by Harapan Kita Hospital in Indonesia. Therefore, it was concluded that the proposed method increased the accuracy by 1.48% and reducing the computation time by 94.74% compared to the previous work. It is envisioned that the proposed hybrid method may be useful as a rapid and accurate predictor of the diagnosis of thalassemia.