A construction method and a refinement method of fuzzy knowledge are proposed in order to apply them to intelligent multi-modal interfaces. This paper supposes that the interface requires the following three functions at least: 1) a function that constructs knowledge using instances instead of if-then rules; 2) a function that transforms mutually between the upper conceptual label represented by words and the lower conceptual label represented by physical values in order to realize multi-modality; and 3) a function that refines the knowledge using qualitative instruction such as a learning process. This paper proposes the methods using fuzzy associative memory organizing units system (FAMOUS) in order to realize these functions and applies them to estimation of human movements. Experimental results show proposed methods provide functions and are suitable to intelligent multi-modal.
展开▼
