This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Accurate clustering in data mining faces serious challenges, especially when the data is unbalanced. In unbalanced data, traditional Fuzzy Clustering Algorithms (FCM) usually do not have sufficient accuracy and do not correctly identify minority classes due to their tendency to create clusters of equal size. To reduce the effect of this limitation, in this research, a novel approach is presented in which the adaptive FCM is improved using the Whale Optimization Algorithm (WOA). By purposefully exploring the response space, the whale algorithm adjusts the parameters of the adaptive FCM optimally and therefore reduces the probability of the algorithm getting stuck in local optima. Experimental evaluations on standard Iris and Thyroid datasets show that the proposed method achieves values of 97.14% and 94.71% for F1-Score and Balanced Accuracy (BA) metrics, respectively. This improvement in evaluation criteria indicates that the proposed method has a higher ability to manage the side effects of data imbalance and maintain the true structure of clusters compared to FCM and other basic methods.
Null