Data clustering is an important technique of data mining in which the objective is to partition N data objects into K clusters that minimize the sum of intra‐cluster distances between each data object to its nearest centroid. This is an optimization problem, and various optimization algorithms have been suggested for capturing the position vectors of optimal centroids. However, in these approaches, the problem of local entrapment is very common due to weak exploration mechanism. In this paper, a novel approach based on a whale optimization algorithm (WOA) is suggested for data clustering. The performance of the suggested approach is validated using 14 benchmark datasets of the UCI machine learning repository. The experimental results and various statistical tests have justified the efficacy of the suggested approach.

中文翻译：

---

基于鲸鱼优化算法的数据聚类新方法

数据聚类是数据挖掘的一项重要技术，其目的是将N个数据对象划分为K个使每个数据对象与其最近的质心之间的群集内距离之和最小的群集。这是一个优化问题，已经提出了各种优化算法来捕获最佳质心的位置矢量。然而，在这些方法中，由于勘探机制薄弱，局部夹带问题非常普遍。本文提出了一种基于鲸鱼优化算法（WOA）的数据聚类新方法。建议的方法的性能已使用UCI机器学习存储库的14个基准数据集进行了验证。实验结果和各种统计测试证明了该方法的有效性。