Anisotropic-Gaussian-Kernel-Based Fuzzy Clustering Algorithm for Feature Selection

• Published in: IEEE transactions on fuzzy systems Vol. 33; no. 9; pp. 3061 - 3075
• Main Authors: Liu, Jun, Wu, Mengyuan, Lin, Mingwei, Xu, Zeshui
• Format: Journal Article
• Language: English
• Published: IEEE 01.09.2025
• Subjects: Accuracy; Adaptive weights; Anisotropic; anisotropic Gaussian kernel (AGK); Classification algorithms; Clustering algorithms; Feature extraction; feature reduction; fuzzy C-means (FCM); Kernel; Linear programming; Machine learning algorithms; Noise; particle swarm optimization (PSO) algorithm with time-varying acceleration coefficients (PSO-TVAC); Vectors
• ISSN: 1063-6706; 1941-0034
• DOI: 10.1109/TFUZZ.2025.3581918

Soft clustering algorithms based on fuzzy C-means (FCM) have been extensively applied to complex data analysis. However, existing FCM variants still encounter key limitations: a large number of iterations due to slow convergence on high-dimensional data, equal weights of all samples, which increases sensitivity to noise, and strong dependence on empirically chosen fuzzy parameters, often resulting in suboptimal solutions. In order to address these challenges, in this work, we propose an adaptive FCM clustering algorithm based on anisotropic Gaussian kernel function, which facilitates the process of feature selection for multidimensional data with fewer iterations after feature reduction based on updating the kernel width vector. In order to enhance the classification accuracy, we assign adaptive weights to each sample and adjust these weights to mitigate the impact of outliers on classification accuracy. Unlike traditional fuzzy clustering algorithms, we employ the particle swarm optimization algorithm with time-varying acceleration coefficients to determine the global optimal parameters, thus reducing the computational resources and enhancing the algorithm's efficiency. The experimental results based on 16 publicly available datasets validate that the proposed algorithm achieves higher classification accuracy with minimal number of iterations.