Current controlled neuro-fuzzy membership function generation

Anuar Dorzhigulov, Bhaskar Choubey, Alex James Pappachen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Neuro-fuzzy systems are encouraging new approaches to mimic human-like decision making in presence of the vagueness and imprecision in the input data. However, majority of current implementations of these systems are limited to small-scale software designs, ignoring the potential advantages of the analogue hardware. This paper presents a completely tunable membership function generator, which is a vital part of designing neuro-fuzzy systems. Designed using a 130nm CMOS process, this circuit provides the ability to modify the shape as well as the mid-point of a widely used bell-shaped membership function. The circuit uses 11 transistors and provides this control of the membership function with an area of 0.9 µm 2 and power consumption of 12 µW. More importantly, only three control voltages are used without the need of any external digital control. Extensive simulation results are presented to verify the circuit.

Original languageEnglish
Title of host publication2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages929-932
Number of pages4
ISBN (Electronic)9781538673928
DOIs
Publication statusPublished - Jan 22 2019
Event61st IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2018 - Windsor, Canada
Duration: Aug 5 2018Aug 8 2018

Publication series

NameMidwest Symposium on Circuits and Systems
Volume2018-August
ISSN (Print)1548-3746

Conference

Conference61st IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2018
CountryCanada
CityWindsor
Period8/5/188/8/18

Fingerprint

Membership functions
Fuzzy systems
Networks (circuits)
Function generators
Software design
Voltage control
Transistors
Electric power utilization
Decision making
Hardware

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Electrical and Electronic Engineering

Cite this

Dorzhigulov, A., Choubey, B., & James Pappachen, A. (2019). Current controlled neuro-fuzzy membership function generation. In 2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018 (pp. 929-932). [8623932] (Midwest Symposium on Circuits and Systems; Vol. 2018-August). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MWSCAS.2018.8623932

Current controlled neuro-fuzzy membership function generation. / Dorzhigulov, Anuar; Choubey, Bhaskar; James Pappachen, Alex.

2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 929-932 8623932 (Midwest Symposium on Circuits and Systems; Vol. 2018-August).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Dorzhigulov, A, Choubey, B & James Pappachen, A 2019, Current controlled neuro-fuzzy membership function generation. in 2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018., 8623932, Midwest Symposium on Circuits and Systems, vol. 2018-August, Institute of Electrical and Electronics Engineers Inc., pp. 929-932, 61st IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2018, Windsor, Canada, 8/5/18. https://doi.org/10.1109/MWSCAS.2018.8623932
Dorzhigulov A, Choubey B, James Pappachen A. Current controlled neuro-fuzzy membership function generation. In 2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 929-932. 8623932. (Midwest Symposium on Circuits and Systems). https://doi.org/10.1109/MWSCAS.2018.8623932
Dorzhigulov, Anuar ; Choubey, Bhaskar ; James Pappachen, Alex. / Current controlled neuro-fuzzy membership function generation. 2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 929-932 (Midwest Symposium on Circuits and Systems).
@inproceedings{1a07ee43b8014341a964664da93ab92d,
title = "Current controlled neuro-fuzzy membership function generation",
abstract = "Neuro-fuzzy systems are encouraging new approaches to mimic human-like decision making in presence of the vagueness and imprecision in the input data. However, majority of current implementations of these systems are limited to small-scale software designs, ignoring the potential advantages of the analogue hardware. This paper presents a completely tunable membership function generator, which is a vital part of designing neuro-fuzzy systems. Designed using a 130nm CMOS process, this circuit provides the ability to modify the shape as well as the mid-point of a widely used bell-shaped membership function. The circuit uses 11 transistors and provides this control of the membership function with an area of 0.9 µm 2 and power consumption of 12 µW. More importantly, only three control voltages are used without the need of any external digital control. Extensive simulation results are presented to verify the circuit.",
author = "Anuar Dorzhigulov and Bhaskar Choubey and {James Pappachen}, Alex",
year = "2019",
month = "1",
day = "22",
doi = "10.1109/MWSCAS.2018.8623932",
language = "English",
series = "Midwest Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "929--932",
booktitle = "2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018",
address = "United States",

}

TY - GEN

T1 - Current controlled neuro-fuzzy membership function generation

AU - Dorzhigulov, Anuar

AU - Choubey, Bhaskar

AU - James Pappachen, Alex

PY - 2019/1/22

Y1 - 2019/1/22

N2 - Neuro-fuzzy systems are encouraging new approaches to mimic human-like decision making in presence of the vagueness and imprecision in the input data. However, majority of current implementations of these systems are limited to small-scale software designs, ignoring the potential advantages of the analogue hardware. This paper presents a completely tunable membership function generator, which is a vital part of designing neuro-fuzzy systems. Designed using a 130nm CMOS process, this circuit provides the ability to modify the shape as well as the mid-point of a widely used bell-shaped membership function. The circuit uses 11 transistors and provides this control of the membership function with an area of 0.9 µm 2 and power consumption of 12 µW. More importantly, only three control voltages are used without the need of any external digital control. Extensive simulation results are presented to verify the circuit.

AB - Neuro-fuzzy systems are encouraging new approaches to mimic human-like decision making in presence of the vagueness and imprecision in the input data. However, majority of current implementations of these systems are limited to small-scale software designs, ignoring the potential advantages of the analogue hardware. This paper presents a completely tunable membership function generator, which is a vital part of designing neuro-fuzzy systems. Designed using a 130nm CMOS process, this circuit provides the ability to modify the shape as well as the mid-point of a widely used bell-shaped membership function. The circuit uses 11 transistors and provides this control of the membership function with an area of 0.9 µm 2 and power consumption of 12 µW. More importantly, only three control voltages are used without the need of any external digital control. Extensive simulation results are presented to verify the circuit.

UR - http://www.scopus.com/inward/record.url?scp=85062223661&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062223661&partnerID=8YFLogxK

U2 - 10.1109/MWSCAS.2018.8623932

DO - 10.1109/MWSCAS.2018.8623932

M3 - Conference contribution

T3 - Midwest Symposium on Circuits and Systems

SP - 929

EP - 932

BT - 2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -