DBFCM: a Density-Based Fuzzy C-Means with Self-Regulated Fuzzy Clustering Parameters

As an interdisciplinary of fuzzy theory and clustering, Fuzzy C-Means (FCM) is widely applied for identifying categories with unlabeled data. However, its application to data which is hard to visualize rises the difficulty for users to determine the input parameters, especially for the number of clusters. In this paper, a kind of fuzzy clustering algorithm with self-regulated parameters named Density-Based Fuzzy C-Means (DBFCM) is proposed by integrating the idea of Density-Based Spatial Clustering of Application with Noise (DBSCAN) into FCM. Its advantage is using the inherit density characteristic of input data to self-determine the parameters of fuzzy clustering. The experimental results demonstrate that the proposed DBFCM can not only self-determine the proper parameters, but also accelerate the convergence process compared to the original FCM.