A CMOS analog to fuzzy signal converter

Author

Wong, Chiu-Kiu ; Hing-Yan To ; Ismail, Mohammed

Author_Institution

Intel Corp., Folsom, CA, USA

Volume

1

fYear

1997

fDate

9-12 Jun 1997

Firstpage

605

Abstract

A novel CMOS analog fuzzifier is designed, fabricated using a MOSIS 2 μm N-well process, and verified. Building blocks of Winner-Take-All circuits were developed to build the fuzzifier. The fuzzifier generates the membership functions of a fuzzy system by converting the input analog signals to their corresponding predetermined grad of memberships. It takes voltage-mode inputs and produces current mode outputs for easy manipulations of the output fuzzy signals by the arithmetic operations that follow. Furthermore, the fuzzifier is so flexible that it can be readily adapted into most fuzzy systems, including neural networks, by changing the reference voltages and the number of building blocks used. The high speed of analog implementation also makes this fuzzifier more attractive than software approaches

Keywords

CMOS analogue integrated circuits; VLSI; analogue processing circuits; convertors; fuzzy logic; fuzzy neural nets; neural chips; 2 micron; CMOS analog to fuzzy signal converter; MOSIS N-well process; WTA circuits; analog VLSI fuzzifier; current mode outputs; high speed operation; membership functions; reference voltages; voltage-mode inputs; winner-take-all circuits; Arithmetic; CMOS process; Circuits; Cities and towns; Fuzzy logic; Fuzzy sets; Fuzzy systems; Neural networks; Signal generators; Voltage;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1997. ISCAS '97., Proceedings of 1997 IEEE International Symposium on

Print_ISBN

0-7803-3583-X

Type

conf

DOI

10.1109/ISCAS.1997.608877

Filename

608877