Soft Multiprototype Clustering Algorithm via Two-Layer Semi-NMF

doi:10.1109/TFUZZ.2023.3329108

Soft Multiprototype Clustering Algorithm via Two-Layer Semi-NMF

2024-04-01

0

PRE

AI

DOI：10.1109/TFUZZ.2023.3329108

Original

Original request for help

Save

Abstract

En 中文

This article proposes a novel soft multiprototype clustering algorithm (SMP) for high-dimensional data clustering with noisy and complex structural patterns. SMP integrates dimensionality reduction, multiprototype clustering, and multiprototype merge clustering under a two-layer seminonnegative matrix factorization (semi-NMF) architecture. Specifically, the first semi-NMF layer performs multiprototype clustering, which solves the problem that a single prototype cannot represent complex data structures. Meanwhile, the multiprototype fuzzy clustering constraints ensure that the multiprototypes better characterize the original data structure. The second semi-NMF layer performs multiprototype merge clustering to mitigate the issues of heavy computation burden and poor antinoise performance of the spectral clustering algorithm. The introduction of the Laplace graph matrix regularization constraint in this layer assists SMP in completing the merging of multiprototypes with complex data structures. Comprehensive experiments demonstrate that the proposed method outperforms the state-of-the-art algorithms.

Keywords:

Clustering algorithms

Dimensionality reduction

Kernel

Prototypes

Switched mode power supplies

Partitioning algorithms

Merging

Fuzzy clustering

Laplace graph regularization

seminonnegative matrix factorization (semi-NMF)

soft multiprototype clustering

Soft Multiprototype Clustering Algorithm via Two-Layer Semi-NMF

Abstract

Journal

Organization