A Simplex Method-Based Bacterial Colony Optimization Algorithm for Data Clustering Analysis
Abstract
Data clustering is the task of separating data samples into a set of clusters. K-means is a popular partitional clustering algorithm. However, it has a lot of weaknesses, including sensitivity to initialization and the ability to become stuck in local optima. Hence, nature-inspired optimization algorithms were applied to the clustering problem to overcome the limitations of the K-means algorithm. However, due to the high-dimensionality of a search space, the nature-inspired optimization algorithm suffers from local optima and poor convergence rates. To address the mentioned issues, this paper presents a simplex method-based bacterial colony optimization (SMBCO) algorithm. The simplex method is a stochastic variant approach that improves population diversity while increasing the algorithm’s local searching ability. The potential and effectiveness of the proposed SMBCO clustering algorithm are assessed using a variety of benchmark machine learning datasets and the generated groups were evaluated using different performance measures. When compared to several well-known nature-inspired algorithms, the experimental results reveal that the SMBCO model produces superior clustering efficiency and a faster convergence rate.