An oscillatory neural network based local processing unit for pattern recognition applications

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

Research output: Contribution to journalArticle

Abstract

Prolific growth of sensors and sensor technology has resulted various applications in sensing, monitoring, assessment and control operations. Owing to the large number of sensing units the the aggregate data volume creates a burden to the central data processing unit. This paper demonstrates an analog computational platform using weakly coupled oscillator neural network for pattern recognition applications. The oscillator neural network (ONN) has been studied over the last couple of decades for it’s increasing computational efficiency. The coupled ONN can realize the classification and pattern recognition functionalities based on its synchronization phenomenon. The convergence time and frequency of synchronization are considered as the indicator of recognition. For hierarchical sensing, the synchronization is detected in the first layer, and then the classification is accomplished in the second layer. In this work, 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. An array of 10 sensors is considered to affect the coupling weights of the oscillating nodes, and demonstrate network level computation. Based on MATLAB simulations, the proposed ONN architecture can successfully detect the close-in-match pattern through synchronization, and differentiate the far-out-match pattern through loss of synchronization in the oscillating nodes.

Original languageEnglish (US)
Article number64
JournalElectronics (Switzerland)
Volume8
Issue number1
DOIs
StatePublished - Jan 1 2019

Fingerprint

Pattern recognition
Synchronization
Neural networks
Processing
Sensors
Computational efficiency
Network architecture
MATLAB
Monitoring

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

@article{16a03d7e344040239a7e9c56a23d8dc5,
title = "An oscillatory neural network based local processing unit for pattern recognition applications",
abstract = "Prolific growth of sensors and sensor technology has resulted various applications in sensing, monitoring, assessment and control operations. Owing to the large number of sensing units the the aggregate data volume creates a burden to the central data processing unit. This paper demonstrates an analog computational platform using weakly coupled oscillator neural network for pattern recognition applications. The oscillator neural network (ONN) has been studied over the last couple of decades for it’s increasing computational efficiency. The coupled ONN can realize the classification and pattern recognition functionalities based on its synchronization phenomenon. The convergence time and frequency of synchronization are considered as the indicator of recognition. For hierarchical sensing, the synchronization is detected in the first layer, and then the classification is accomplished in the second layer. In this work, 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. An array of 10 sensors is considered to affect the coupling weights of the oscillating nodes, and demonstrate network level computation. Based on MATLAB simulations, the proposed ONN architecture can successfully detect the close-in-match pattern through synchronization, and differentiate the far-out-match pattern through loss of synchronization in the oscillating nodes.",
author = "Ting Zhang and Haider, {Mohammad R.} and Yehia Massoud and Alexander, {J. Iwan D.}",
year = "2019",
month = "1",
day = "1",
doi = "https://doi.org/10.3390/electronics8010064",
language = "English (US)",
volume = "8",
journal = "Electronics (Switzerland)",
issn = "2079-9292",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "1",

}

An oscillatory neural network based local processing unit for pattern recognition applications. / Zhang, Ting; Haider, Mohammad R.; Massoud, Yehia; Alexander, J. Iwan D.

In: Electronics (Switzerland), Vol. 8, No. 1, 64, 01.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An oscillatory neural network based local processing unit for pattern recognition applications

AU - Zhang, Ting

AU - Haider, Mohammad R.

AU - Massoud, Yehia

AU - Alexander, J. Iwan D.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Prolific growth of sensors and sensor technology has resulted various applications in sensing, monitoring, assessment and control operations. Owing to the large number of sensing units the the aggregate data volume creates a burden to the central data processing unit. This paper demonstrates an analog computational platform using weakly coupled oscillator neural network for pattern recognition applications. The oscillator neural network (ONN) has been studied over the last couple of decades for it’s increasing computational efficiency. The coupled ONN can realize the classification and pattern recognition functionalities based on its synchronization phenomenon. The convergence time and frequency of synchronization are considered as the indicator of recognition. For hierarchical sensing, the synchronization is detected in the first layer, and then the classification is accomplished in the second layer. In this work, 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. An array of 10 sensors is considered to affect the coupling weights of the oscillating nodes, and demonstrate network level computation. Based on MATLAB simulations, the proposed ONN architecture can successfully detect the close-in-match pattern through synchronization, and differentiate the far-out-match pattern through loss of synchronization in the oscillating nodes.

AB - Prolific growth of sensors and sensor technology has resulted various applications in sensing, monitoring, assessment and control operations. Owing to the large number of sensing units the the aggregate data volume creates a burden to the central data processing unit. This paper demonstrates an analog computational platform using weakly coupled oscillator neural network for pattern recognition applications. The oscillator neural network (ONN) has been studied over the last couple of decades for it’s increasing computational efficiency. The coupled ONN can realize the classification and pattern recognition functionalities based on its synchronization phenomenon. The convergence time and frequency of synchronization are considered as the indicator of recognition. For hierarchical sensing, the synchronization is detected in the first layer, and then the classification is accomplished in the second layer. In this work, 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. An array of 10 sensors is considered to affect the coupling weights of the oscillating nodes, and demonstrate network level computation. Based on MATLAB simulations, the proposed ONN architecture can successfully detect the close-in-match pattern through synchronization, and differentiate the far-out-match pattern through loss of synchronization in the oscillating nodes.

UR - http://www.scopus.com/inward/record.url?scp=85060211050&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060211050&partnerID=8YFLogxK

U2 - https://doi.org/10.3390/electronics8010064

DO - https://doi.org/10.3390/electronics8010064

M3 - Article

VL - 8

JO - Electronics (Switzerland)

JF - Electronics (Switzerland)

SN - 2079-9292

IS - 1

M1 - 64

ER -