Authors : M. Faiza Abdulsalam and Azuraliza Abu Bakar
Abstract: The Artificial Bee Colony (ABC) algorithm was motivated by the intelligent foraging behavior of honey bee swarms. The ABC algorithm was developed to solve clustering problems and revealed promising results in processing time and solution quality although, no research has yet considered employing ABC for deviation detection. In this study, researchers propose modifying the ABC clustering algorithm for deviation detection. An outlier factor has been used to identify the top n outliers that deviate from the dataset. The proposed algorithm was tested on three UCI benchmark datasets. Experimental results have shown that the ABC deviation detection algorithm has performed with comparable results.
M. Faiza Abdulsalam and Azuraliza Abu Bakar, 2012. A Cluster-Based Deviation Detection Task Using the Artificial Bee Colony (ABC) Algorithm. International Journal of Soft Computing, 7: 71-78.