Computational model of perceptual information processing
Akira Inoue, Anca Ralescu · 1999
We study an intelligent information processing method based on users' perception, named perceptual information processing (PIP). This method consists of the following tasks: (a) acquisition of users' perception from examples, (b) recognition by sensing, and (c) refinement of the perception based on the recognition result. Fuzzy sets are used to represent perceptions and a soft computing method called mass assignment theory is used as PIP's computational core. The paper introduces the computational model of PIP and discusses the issues that arise in connection with this model.