Robust Switching Non-negative Matrix Factorization Based on Noise Fuzzy Clustering

Abstract

Non-negative matrix factorization (NMF) is a basic method for analyzing the intrinsic structure of such non-negative matrices as environmental observation data, but cannot work well when datasets include some noisy subsets drawn from different generative schemes. This paper proposes a novel robust switching NMF algorithm, which simultaneously estimates multiple NMF models in conjunction with noise cluster supported by a noise fuzzy clustering concept. The NMF least square measure is modified by introducing noise/non-noise fuzzy memberships of each object, and object fuzzy partition estimation and cluster-wise local NMF modeling are iteratively performed based on the iterative optimization principle utilizing noise cluster.