Hybrid clustering algorithm

The paper presents a new graph based clustering algorithm. Traditional clustering algorithms have the drawback that it takes large number of iterations in order to come up with the desired number of clusters. The advantage of this approach is that the size of the dataset is reduced using graph based clustering approach and the required number of clusters is generated using K means algorithm. The proposed algorithm consists of two phases, the first phase being constructing the graph and de-associating the graphs into connected sub graphs which denote the number of sub groups within the data. In the second phase in order to group the sub graphs that are close to each other K means algorithm is employed.