Literature Review: Comparison of K-Means and Fuzzy C-Means Algorithms in Clustering Analysis

Abstract

The increasing volume and complexity of data across sectors such as healthcare, business, education, and security necessitates analytical methods capable of handling uncertainty and structural variability. One widely used approach is clustering, which groups data based on similarity. Two commonly applied algorithms are K-Means and Fuzzy C-Means (FCM), each with distinct characteristics: K-Means applies hard clustering, while FCM adopts soft clustering using degrees of membership. This study presents a literature review of 12 national scientific journals that implemented both algorithms in contexts such as employee performance evaluation, patient classification, spatial disease analysis, and customer segmentation. The findings show that algorithm selection depends heavily on data characteristics and analytical objectives. K-Means excels in computational efficiency and interpretability, while FCM offers greater flexibility for modeling complex data. Several studies also suggest that combining both algorithms can enhance clustering accuracy and robustness. Thus, this review is expected to serve as both an academic and practical reference in selecting appropriate clustering methods.

Keywords: Clustering, K-Means, Fuzzy C-Means, Literature Review, Data Analysis.