A Hybrid Approach for Data Clustering Using Data Mining Techniques

Data clustering is a process of arranging similar data into groups. Data clustering is a common technique for data analysis and is used in many fields, including data mining, pattern recognition and image analysis. In this paper a hybrid clustering algorithm based on K-mean is described. K-means clustering is a common and simple approach for data clustering but this method has some limitation such as local optimal convergence and initial point sensibility. The algorithm then extended to use k-means clustering to refined centroids and clusters. The experimental results showed the accuracy and capability of proposed algorithm to data clustering.