An Efficient DBSCAN using Genetic Algorithm based Clustering
Lovely Sharma, K. Ramya · 2014
Abstract — Data mining is widely employed in business management and engineering. The major objective of data mining is to discover helpful and accurate information among a vast quantity of data, providing a orientation basis for decision makers. Data clustering is currently a very popular and frequently applied analytical method in data mining. DBSCAN is a traditional and widely-accepted density-based clustering method. It is used to find clusters of arbitrary shapes and sizes yet may have trouble with clusters of varying density. In this paper an efficient DBSCAN clustering using genetic algorithm is proposed. DBSCAN clustering provides some problem such as the algorithm is not efficient for noisy clusters; hence it is enhanced using genetic algorithm. The proposed technique is efficient in terms of accuracy and execution time.