Improved the Correctness and Reduce the Error of DBSCAN using Ant Colony Optimization

The processing and mining of spatial data is very challenging task in current research trend. The process of mining faced a lost due to diversity of data. The most part of spatial data contains a noise outlier, boundary point and core point. DBSCAN clustering faced a problem of noise of data and some boundary point of data. If the value of noise and boundary point reduces then we improved the correctness and performance of DBSACN algorithm. In this we improved the performance of DBSCAN algorithm using ANT colony optimization technique. Our experimental result shows that better performance instead of DBSCAN and IDBSCAN algorithm.