Fuzzy C-means clustering algorithm based on adaptive neighbors information

Traditional FCM algorithms cluster based on raw data, risking distortion from noise, outliers, or other disruptions, which can degrade clustering outcomes. To bolster FCM′s resilience, this study introduces a fuzzy C-means clustering algorithm that leverages adaptive neighbor information. This concept hinges on the similarity between data points, treating each point as a potential neighbor to others, albeit with varying degrees of similarity. By integrating the neighbor information of sample points, labeled GX, and that of cluster centers, labeled GV, into the standard FCM framework, the algorithm gains additional insights into data structure. This aids in steering the clustering process and enhances the algorithm′s robustness. Three iterative methods are presente to implement this enhanced clustering model. When compared to leading clustering techniques, our approach demonstrates over a 10% improvement in clustering efficacy on select benchmark datasets. It undergoes thorough evaluation across different dimensions, including parameter sensitivity, convergence rate, and through ablation studies, confirming its practicality and efficiency. © 2024 Chinese Academy of Sciences. All rights reserved.