Hybrid Variable-Length Spider Monkey Optimization with Good-Point Set Initialization for Data Clustering
Athraa Qays Obaid, Maytham Alabbas · Informatica · 2023
Data clustering refers to grouping data points that are similar in some way. This can be done in accordance with their patterns or characteristics. It can be used for various purposes, including image analysis, pattern recognition, and data mining. The K-means algorithm, commonly used for clustering, is subject to limitations, such as requiring the number of clusters to be specified and being sensitive to initial center points. To address these limitations, this study proposes a novel method to determine the optimal number of clusters and initial centroids using a variable-length spider monkey optimization algorithm (VLSMO) with a hybrid proposed measure. Results of experiments on real-life datasets demonstrate that VLSMO performs better than the standard k-means in terms of accuracy and clustering capacity.