Fuzzy ants as a clustering concept
Parag M. Kanade, Lawrence Hall · 2004
We present a swarm intelligence approach to data clustering. Data is clustered without initial knowledge of the number of clusters. Ant based clustering is used to initially create raw clusters and then these clusters are refined using the Fuzzy C Means algorithm. Initially the ants move the individual objects to form heaps. The centroids of these heaps are taken as the initial cluster centers and the Fuzzy C Means algorithm is used to refine these clusters. In the second stage the objects obtained from the Fuzzy C Means algorithm are hardened according to the maximum membership criteria to form new heaps. These new heaps are then sometimes moved and merged by the ants. The final clusters formed are refined by using the Fuzzy C Means algorithm. Results from three small data sets show that the partitions produced are competitive with those obtained from FCM.