A novel current-mode fuzzy processor for pattern recognition

A switched-current fuzzy processor for pattern recognition is proposed. It accepts multiple inputs that represent multiple features of an unknown pattern in a time-shared way. Membership function generators generate memberships corresponding to each standard pattern according to the input features, then different weights are used for different feature memberships. Switched-current accumulators accumulate multiple weighted memberships to get synthetic memberships. Finally, a MAX circuit finds the maximum synthetic membership and the recognition result is obtained. In this system, all the analog circuits employed are current-mode and switched-current mode circuits, so that the system can be directly fabricated in standard digital CMOS technology, and can be easily integrated into a mixed analog-digital system