Pattern recognition based on fuzzy logic

Author

Schmalzel, John L. ; Johnson, Jerald F.

Author_Institution

Div. of Eng., Texas Univ., San Antonio, TX, USA

fYear

1993

fDate

18-20 May 1993

Firstpage

681

Lastpage

684

Abstract

Fuzzy logic inference methods have been applied as a method for pattern recognition in a monitoring problem that required an alarm. Multiple input channels were available from an instrument based on an 8-bit microcontroller. Fuzzy logic methods were investigated as one method to avoid floating-point computations. For a single input variable, triangular membership functions using three sets were found to yield acceptable results for the selected test case. The result is an alarm algorithm that can be easily implemented on a low-cost microcontroller

Keywords

computerised instrumentation; fuzzy logic; inference mechanisms; microcomputer applications; pattern recognition; 8-bit microcontroller; alarm algorithm; fuzzy logic; inference methods; low-cost microcontroller; monitoring; mulitple input channels; particles density monitoring; pattern recognition; single input variable; triangular membership functions; Computerized monitoring; Control systems; Costs; Fluid flow; Fluid flow control; Fuzzy logic; Input variables; Instruments; Microcontrollers; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference, 1993. IMTC/93. Conference Record., IEEE

Conference_Location

Irvine, CA

Print_ISBN

0-7803-1229-5

Type

conf

DOI

10.1109/IMTC.1993.382557

Filename

382557