Clustering is the process of locating patterns in large data sets. As databases continue to grow in size, efficient and effective clustering algorithms play a paramount role in data mining applications. Traditional clustering approaches usually analyze static datasets in which objects are kept unchanged after being processed, but many practical datasets are dynamically modified which means some previously learned patterns have to be updated accordingly. Re-clustering the whole dataset from scratch is not a good choice due to the frequent data modifications and the limited out-of-service time, so the development of incremental clustering approaches is highly desirable. In this paper, we propose an incremental algorithm, IPYRAMID: Incremental Parallel hYbrid clusteRing using genetic progrAmming and Multiobjective fItness with Density employs a combination of data parallelism, genetic programming (GP), special operators, and multi-objective density-based incremental fitness function. Although many incremental clustering algorithms have been proposed which can handle insertion of new record properly using incremental approach but cannot handle deletion of record properly. This issue is resolved in the proposed algorithm and density based incremental fitness function that helps to handle outliers. Use of parallelism increases the speed of execution as well as identifies clusters of arbitrary shapes. The incremental merge engine can dynamically determine the number of clusters. Preliminary experimental results show that it can increase the efficiency of clustering process.

Data Mining Clustering Genetic Programming Parallelism Density Incremental mining