Fuzzy Clustering-based Switching Non-negative Matrix Factorization and Its Application to Environmental Data Analysis

DOI

10.2991/asum.k.210827.014How to use a DOI?

Keywords

Fuzzy clustering, Non-negative matrix factorization, Switching analysis

Abstract

Non-negative matrix factorization (NMF) is a basic method for analyzing the intrinsic structure of non-negative matrices but cannot work well when datasets include some subsets drawn from different generative schemes. This paper proposes a novel switching NMF algorithm, which simultaneously estimates multiple NMF models supported by a fuzzy clustering concept. A fuzzy NMF reconstruction measure is modeled by introducing fuzzy memberships of each object and is also utilized as the fuzzy clustering criterion. Object fuzzy partition estimation and cluster-wise local NMF modeling are iteratively performed based on the iterative optimization principle. The characteristics of the proposed algorithm are demonstrated through numerical experiments using an artificial dataset and an environmental observation dataset.

Copyright

© 2021, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - K. Honda
AU  - T. Furukawa
AU  - S. Ubukata
AU  - A. Notsu
PY  - 2021
DA  - 2021/08/30
TI  - Fuzzy Clustering-based Switching Non-negative Matrix Factorization and Its Application to Environmental Data Analysis
BT  - Joint Proceedings of the 19th World Congress of the International Fuzzy Systems Association (IFSA), the 12th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT), and the 11th International Summer School on Aggregation Operators (AGOP)
PB  - Atlantis Press
SP  - 103
EP  - 108
SN  - 2589-6644
UR  - https://doi.org/10.2991/asum.k.210827.014
DO  - 10.2991/asum.k.210827.014
ID  - Honda2021
ER  -