Hybrid ABC–K Means for Optimal Cluster Number Determination in Unlabeled Data

This study presents the ABC K Means GenData algorithm, an enhancement over traditional K Means clustering that integrates the Artificial Bee Colony (ABC) optimization approach. The ABC K Means GenData algorithm addresses the issue of local optima commonly encountered in standard K Means algorithms, offering improved exploration and exploitation strategies. By utilizing the dynamic roles of employed, onlooker, and scout bees, this approach effectively navigates the clustering space for categorical data. Performance evaluations across several datasets demonstrate the algorithm's superiority. For the Zoo dataset, ABC K Means GenData achieved high Accuracy (0.8399), Precision (0.8089), and Recall (0.7286), with consistent performance compared to K Means and Fuzzy K Means. Similar results were observed for the Breast Cancer dataset, where it matched the Accuracy and Precision of K Means and surpassed Fuzzy K Means in Precision and Recall. In the Soybean dataset, the algorithm also performed excellently, showing top scores in Accuracy, Precision, Recall, and Rand Index (RI), outperforming both K Means and Fuzzy K Means.. The comprehensive results indicate that ABC K Means GenData excels in clustering categorical data, providing robust and reliable performance. Future research will explore its application to mixed data types and social media datasets, aiming to further optimize clustering techniques. .