EOG Signal Processor: An SVM-based Multiclass Classifier to Detect Eye Movements

Diba Das; Mehdi Hasan Chowdhury; Aditta Chowdhury; Quazi Delwar Hossain; Ray C. C. Cheung

doi:10.1007/s11265-024-01936-5

EOG Signal Processor: An SVM-based Multiclass Classifier to Detect Eye Movements

Diba Das, Mehdi Hasan Chowdhury^*, Aditta Chowdhury, Quazi Delwar Hossain, Ray C. C. Cheung

^*Corresponding author for this work

Department of Electrical Engineering

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

1 Citation (Scopus)

Abstract

This paper aims to design a hardware optimized machine learning based Electrooculogram (EOG) signal processor to classify eye movements. EOG is the recording of the resting potential of the retina and cornea. This recording may help to recognize eye movements which can be utilized in many Human-Computer Interface (HCI) applications. In this work, EOG signals are used to identify six different eye movements (up, down, normal, right, left, and blink) adopting a linear support vector machine (SVM) classifier with a software accuracy of 97.92%. The system is implemented in Zynq UltraScale+ FPGA SoC. The whole system is designed with a combination of serial-parallel processing for hardware optimization. At the end, the performance of the proposed design is outlined. The average hardware accuracy of the implemented system is 95.56%. The resource and power utilization of the implemented system is analyzed. The on-chip power consumption for this design is 1.446 watts, in which dynamic power is 0.850 watts, and static power is 0.596 watts. The comparative study confirmed the efficacy of the prototype.

© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024

Original language	English
Number of pages	14
Journal	Journal of Signal Processing Systems
Online published	12 Oct 2024
DOIs	https://doi.org/10.1007/s11265-024-01936-5
Publication status	Online published - 12 Oct 2024

Research Keywords

Classification
Electrooculogram (EOG)
Eye movements
Field programmable gate array (FPGA)
Support vector machine (SVM)

Publisher's Copyright Statement

COPYRIGHT TERMS OF DEPOSITED POSTPRINT FILE: This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/s11265-024-01936-5.

Access Output

10.1007/s11265-024-01936-5

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{87cfb56a8ab746349227dc0181238a05,

title = "EOG Signal Processor: An SVM-based Multiclass Classifier to Detect Eye Movements",

abstract = "This paper aims to design a hardware optimized machine learning based Electrooculogram (EOG) signal processor to classify eye movements. EOG is the recording of the resting potential of the retina and cornea. This recording may help to recognize eye movements which can be utilized in many Human-Computer Interface (HCI) applications. In this work, EOG signals are used to identify six different eye movements (up, down, normal, right, left, and blink) adopting a linear support vector machine (SVM) classifier with a software accuracy of 97.92%. The system is implemented in Zynq UltraScale+ FPGA SoC. The whole system is designed with a combination of serial-parallel processing for hardware optimization. At the end, the performance of the proposed design is outlined. The average hardware accuracy of the implemented system is 95.56%. The resource and power utilization of the implemented system is analyzed. The on-chip power consumption for this design is 1.446 watts, in which dynamic power is 0.850 watts, and static power is 0.596 watts. The comparative study confirmed the efficacy of the prototype.{\textcopyright} The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024",

keywords = "Classification, Electrooculogram (EOG), Eye movements, Field programmable gate array (FPGA), Support vector machine (SVM)",

author = "Diba Das and Chowdhury, {Mehdi Hasan} and Aditta Chowdhury and Hossain, {Quazi Delwar} and Cheung, {Ray C. C.}",

year = "2024",

month = oct,

day = "12",

doi = "10.1007/s11265-024-01936-5",

language = "English",

journal = "Journal of Signal Processing Systems",

issn = "1939-8018",

publisher = "Springer New York",

}

TY - JOUR

T1 - EOG Signal Processor

T2 - An SVM-based Multiclass Classifier to Detect Eye Movements

AU - Das, Diba

AU - Chowdhury, Mehdi Hasan

AU - Chowdhury, Aditta

AU - Hossain, Quazi Delwar

AU - Cheung, Ray C. C.

PY - 2024/10/12

Y1 - 2024/10/12

N2 - This paper aims to design a hardware optimized machine learning based Electrooculogram (EOG) signal processor to classify eye movements. EOG is the recording of the resting potential of the retina and cornea. This recording may help to recognize eye movements which can be utilized in many Human-Computer Interface (HCI) applications. In this work, EOG signals are used to identify six different eye movements (up, down, normal, right, left, and blink) adopting a linear support vector machine (SVM) classifier with a software accuracy of 97.92%. The system is implemented in Zynq UltraScale+ FPGA SoC. The whole system is designed with a combination of serial-parallel processing for hardware optimization. At the end, the performance of the proposed design is outlined. The average hardware accuracy of the implemented system is 95.56%. The resource and power utilization of the implemented system is analyzed. The on-chip power consumption for this design is 1.446 watts, in which dynamic power is 0.850 watts, and static power is 0.596 watts. The comparative study confirmed the efficacy of the prototype.© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024

AB - This paper aims to design a hardware optimized machine learning based Electrooculogram (EOG) signal processor to classify eye movements. EOG is the recording of the resting potential of the retina and cornea. This recording may help to recognize eye movements which can be utilized in many Human-Computer Interface (HCI) applications. In this work, EOG signals are used to identify six different eye movements (up, down, normal, right, left, and blink) adopting a linear support vector machine (SVM) classifier with a software accuracy of 97.92%. The system is implemented in Zynq UltraScale+ FPGA SoC. The whole system is designed with a combination of serial-parallel processing for hardware optimization. At the end, the performance of the proposed design is outlined. The average hardware accuracy of the implemented system is 95.56%. The resource and power utilization of the implemented system is analyzed. The on-chip power consumption for this design is 1.446 watts, in which dynamic power is 0.850 watts, and static power is 0.596 watts. The comparative study confirmed the efficacy of the prototype.© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024

KW - Classification

KW - Electrooculogram (EOG)

KW - Eye movements

KW - Field programmable gate array (FPGA)

KW - Support vector machine (SVM)

UR - https://www.webofscience.com/wos/woscc/full-record/WOS:001330203400001

U2 - 10.1007/s11265-024-01936-5

DO - 10.1007/s11265-024-01936-5

M3 - RGC 21 - Publication in refereed journal

SN - 1939-8018

JO - Journal of Signal Processing Systems

JF - Journal of Signal Processing Systems

ER -

EOG Signal Processor: An SVM-based Multiclass Classifier to Detect Eye Movements

Abstract

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Embargoed Document

Fingerprint

Cite this