<![CDATA[Clustering is a method that is used to divide the data into several groups of parts. K-means (KM) is an algorithm that is often used in clustering, only just the result of KM often times get stuck in local optima i.e. the optimal solution (both maximum or minimal) on the candidate solution in the nearest neighbor only, not the whole of all existing solutions or what is commonly called the global optima. In this study aims to do improve the cluster determination process on the Kmeans algorithm using the Bee Colony Optimization (BCO) algorithm. BCO is an algorithm that works based on the way the bees search for food , BCO is famous for being able to escape from the local optima trap by recognizing which results are best from a series of optimal results . Combining BCO with KM begins with selecting a source of food early in random and using KM to resolve all the problems of clustering at every step BCO next and keep sources of food best in each iteration. The result of this research is that the BCOKM method has been proven to be able to solve the problem of data sharing, where the BCOKM method is able to form a good cluster, as shown by the resulting fitness value (the lowest value is 1221.53 and the highest value is 1233.28) all of which are better than the fitness value using K-means (1251.42). Likewise in terms of accuracy, where the use of BCOKM all showed better results (83.16%-83.30%) than the use of only K-means (83.09%)]]>
Copyrights © 2022
