International Journal of Computational Engineering Research (IJCER)
The development of parallel and distributed data mining algorithms in various functionalities have been motivated by the huge size and wide distribution of the databases and also by the computational complexity of the data mining methods. Such algorithms make partitions of the huge database that is being used into segments that are processed in parallel. The results obtained from the processed segments of database are then merged; This paper reduces the computational complexity and improves the speed. This paper aims at introducing parallelism in data sanitization technique in order to improve the performance and throughput.