A coupled schmitt trigger oscillator neural network for pattern recognition applications

Ting Zhang, Mohammad R. Haider, Iwan D. Alexander, Yehia Massoud

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

Abstract

This paper demonstrates a coupled Schmitt trigger oscillator based oscillator neural network (SMT-ONN) for pattern recognition applications. Unlike previous ONN models, the SMT-ONN can be easily realized in both hardware and software levels. A mathematical model of the Schmitt Trigger Oscillator as well as the corresponding CMOS circuit are presented to validate the mathematical model. The SMT-ONN can realize the pattern recognition task by considering the convergence time and frequency as the recognition indicators. A Kuramoto model based frequency synchronization approach is utilized, and simulation results indicate less than 160 ms convergence time and close frequency match for a simplified pattern recognition application.

Original languageEnglish (US)
Title of host publication2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages238-241
Number of pages4
ISBN (Electronic)9781538673928
DOIs
StatePublished - 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

Conference

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

Fingerprint

Pattern recognition
Neural networks
Mathematical models
Synchronization
Hardware
Networks (circuits)

All Science Journal Classification (ASJC) codes

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

Cite this

Zhang, T., Haider, M. R., Alexander, I. D., & Massoud, Y. (2019). A coupled schmitt trigger oscillator neural network for pattern recognition applications. In 2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018 (pp. 238-241). [8624010] (Midwest Symposium on Circuits and Systems; Vol. 2018-August). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MWSCAS.2018.8624010
Zhang, Ting ; Haider, Mohammad R. ; Alexander, Iwan D. ; Massoud, Yehia. / A coupled schmitt trigger oscillator neural network for pattern recognition applications. 2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 238-241 (Midwest Symposium on Circuits and Systems).
@inproceedings{0e284f69f93d4b8a80d74490142d75d7,
title = "A coupled schmitt trigger oscillator neural network for pattern recognition applications",
abstract = "This paper demonstrates a coupled Schmitt trigger oscillator based oscillator neural network (SMT-ONN) for pattern recognition applications. Unlike previous ONN models, the SMT-ONN can be easily realized in both hardware and software levels. A mathematical model of the Schmitt Trigger Oscillator as well as the corresponding CMOS circuit are presented to validate the mathematical model. The SMT-ONN can realize the pattern recognition task by considering the convergence time and frequency as the recognition indicators. A Kuramoto model based frequency synchronization approach is utilized, and simulation results indicate less than 160 ms convergence time and close frequency match for a simplified pattern recognition application.",
author = "Ting Zhang and Haider, {Mohammad R.} and Alexander, {Iwan D.} and Yehia Massoud",
year = "2019",
month = "1",
day = "22",
doi = "https://doi.org/10.1109/MWSCAS.2018.8624010",
language = "English (US)",
series = "Midwest Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "238--241",
booktitle = "2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018",
address = "United States",

}

Zhang, T, Haider, MR, Alexander, ID & Massoud, Y 2019, A coupled schmitt trigger oscillator neural network for pattern recognition applications. in 2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018., 8624010, Midwest Symposium on Circuits and Systems, vol. 2018-August, Institute of Electrical and Electronics Engineers Inc., pp. 238-241, 61st IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2018, Windsor, Canada, 8/5/18. https://doi.org/10.1109/MWSCAS.2018.8624010

A coupled schmitt trigger oscillator neural network for pattern recognition applications. / Zhang, Ting; Haider, Mohammad R.; Alexander, Iwan D.; Massoud, Yehia.

2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 238-241 8624010 (Midwest Symposium on Circuits and Systems; Vol. 2018-August).

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

TY - GEN

T1 - A coupled schmitt trigger oscillator neural network for pattern recognition applications

AU - Zhang, Ting

AU - Haider, Mohammad R.

AU - Alexander, Iwan D.

AU - Massoud, Yehia

PY - 2019/1/22

Y1 - 2019/1/22

N2 - This paper demonstrates a coupled Schmitt trigger oscillator based oscillator neural network (SMT-ONN) for pattern recognition applications. Unlike previous ONN models, the SMT-ONN can be easily realized in both hardware and software levels. A mathematical model of the Schmitt Trigger Oscillator as well as the corresponding CMOS circuit are presented to validate the mathematical model. The SMT-ONN can realize the pattern recognition task by considering the convergence time and frequency as the recognition indicators. A Kuramoto model based frequency synchronization approach is utilized, and simulation results indicate less than 160 ms convergence time and close frequency match for a simplified pattern recognition application.

AB - This paper demonstrates a coupled Schmitt trigger oscillator based oscillator neural network (SMT-ONN) for pattern recognition applications. Unlike previous ONN models, the SMT-ONN can be easily realized in both hardware and software levels. A mathematical model of the Schmitt Trigger Oscillator as well as the corresponding CMOS circuit are presented to validate the mathematical model. The SMT-ONN can realize the pattern recognition task by considering the convergence time and frequency as the recognition indicators. A Kuramoto model based frequency synchronization approach is utilized, and simulation results indicate less than 160 ms convergence time and close frequency match for a simplified pattern recognition application.

UR - http://www.scopus.com/inward/record.url?scp=85062213810&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062213810&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/MWSCAS.2018.8624010

DO - https://doi.org/10.1109/MWSCAS.2018.8624010

M3 - Conference contribution

T3 - Midwest Symposium on Circuits and Systems

SP - 238

EP - 241

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

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Zhang T, Haider MR, Alexander ID, Massoud Y. A coupled schmitt trigger oscillator neural network for pattern recognition applications. In 2018 IEEE 61st International Midwest Symposium on Circuits and Systems, MWSCAS 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 238-241. 8624010. (Midwest Symposium on Circuits and Systems). https://doi.org/10.1109/MWSCAS.2018.8624010