Improved DBSCALE Algorithm by using Ant Colony Optimization

The DBSCALE [1] algorithm is a popular algorithm in Data Mining field as it has the ability to mine the noiseless arbitrary shape Clusters in an elegant way. Such metaheuristic algorithms include Ant Colony Optimization Algorithms, Particle Swarm Optimizations and Genetic Algorithm has received increasing attention in recent years. Ant Colony Optimization (ACO) is a technique that was introduced in the early 1990’s and it is inspired by the foraging behavior of ant colonies. This paper presents an application aiming to cluster a dataset with ACO-based optimization algorithm and to increase the working performance of colony optimization algorithm used for solving data-clustering problem, proposed two new techniques and shows the increase on the performance with the addition of these techniques [5]. We bring out a new clustering initialization algorithm which is scale-invariant to the scale factor. Instead of using the scale factor while the cluster initialization, in this research we determine the number and position of clusters according to the changes of cluster density with the division an agglomeration processes. Experimental results indicate that the proposed DBSCALE has a lower execution time than DBSCAN, and IDBSCAN clustering algorithms. IDBSCALE-ACO has a maximum deviation in clustering correctness rate. This algorithm is proposed to solve combinatorial optimization problem by using Ant Colony algorithm.