Fuzzy-associative-memory-based knowledge construction with an application to a human-machine interface

Abstract

A fuzzy knowledge construction method is proposed for application to human-machine interfaces. This paper considers a human movement estimation system to be one of the interfaces. This estimation system transforms human physical movements into qualitative linguistic labels. For example, the degrees of magnitude and speed of the physical movement are represented by qualitative words. It is difficult to construct the transformation knowledge because the relation between the movements and the labels is fuzzy. This paper proposes a method of constructing the knowledge. This proposed method uses a fuzzy associative memory organizing units system and is applied to estimating human sports movements. Experimental results show that the proposed method is suitable for application to human-machine interfaces.