A clustering method for seismic zone identification and spatial data mining

This paper shows how it made possible in geographical science to observe the seismic zone, clustering of highly sensitive earthquake zone and spatial data clustering during important geographical processes. This paper shows simple density based and KMean clustering technique. Density-Based clustering is done here using density estimation and by searching regions which are denser than a given threshold and to form clusters from these dense regions by using connectivity and density functions. Also we defined some optimal no of K locations for K-Mean clustering where the sum of the distance from every point to each of the K centers is minimized what is called global optimization. With this dataset it forms clusters using density estimation and K-Mean clustering. Also it correlates the clustering pattern by applying co-relation algorithm and proximity measure algorithm; hence it easily removes noisy data. This scheme can extract clusters efficiently with reduced number of comparisons.