Classification of Electrooculography Signals Using Convolutional Neural Networks for Interaction with a Manipulator Robot

O. I. Pellico-Sánchez; P. A. Niño-Suárez; R. D. Hernández-Beleño; O. F. Avilés-Sánchez; M. H. Pérez-Bahena

doi:10.1007/978-981-19-6347-6_2

Classification of Electrooculography Signals Using Convolutional Neural Networks for Interaction with a Manipulator Robot

O. I. Pellico-Sánchez, P. A. Niño-Suárez, R. D. Hernández-Beleño, O. F. Avilés-Sánchez, M. H. Pérez-Bahena

Escuela Superior de Ingeniería Mecánica y Eléctrica (ESIME), Unidad Azcapotzalco

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Electrooculography (EOG) has been widely applied in human–machine interfaces (HMI) because it provides a reliable communication channel to assist people with disabilities. However, signal behavior under different conditions hinders eye movement classification when algorithms based on voltage threshold detection are used. Therefore, recalibration of the system is required for the classification algorithm to work correctly. Based on the above, a classification algorithm was developed to analyze the data vector corresponding to the entire EOG waveform, instead of just one characteristic value of the signal, thus avoiding the system recalibration process. A convolutional neural network (CNN) was implemented to classify six targets corresponding to different eye movements. The proposed model was compared with a feedforward neural network (FNN) to evaluate its performance. The results were implemented in an HMI for interaction with a manipulator robot.

Original language	English
Title of host publication	Communication and Applied Technologies - Proceedings of ICOMTA 2022
Editors	Paulo Carlos López-López, Ángel Torres-Toukoumidis, Andrea De-Santis, Óscar Avilés, Daniel Barredo
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	13-23
Number of pages	11
ISBN (Print)	9789811963469
DOIs	https://doi.org/10.1007/978-981-19-6347-6_2
State	Published - 2023
Event	International Conference on Communication and Applied Technologies, ICOMTA 2022 - Cuenca, Ecuador Duration: 7 Sep 2022 → 9 Sep 2022

Publication series

Name	Smart Innovation, Systems and Technologies
Volume	318
ISSN (Print)	2190-3018
ISSN (Electronic)	2190-3026

Conference

Conference	International Conference on Communication and Applied Technologies, ICOMTA 2022
Country/Territory	Ecuador
City	Cuenca
Period	7/09/22 → 9/09/22

Keywords

Convolutional neural networks
Deep learning
Electrooculography
Human machine interface

Access to Document

10.1007/978-981-19-6347-6_2

Cite this

Pellico-Sánchez, O. I., Niño-Suárez, P. A., Hernández-Beleño, R. D., Avilés-Sánchez, O. F., & Pérez-Bahena, M. H. (2023). Classification of Electrooculography Signals Using Convolutional Neural Networks for Interaction with a Manipulator Robot. In P. C. López-López, Á. Torres-Toukoumidis, A. De-Santis, Ó. Avilés, & D. Barredo (Eds.), Communication and Applied Technologies - Proceedings of ICOMTA 2022 (pp. 13-23). (Smart Innovation, Systems and Technologies; Vol. 318). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-19-6347-6_2

Pellico-Sánchez, O. I. ; Niño-Suárez, P. A. ; Hernández-Beleño, R. D. et al. / Classification of Electrooculography Signals Using Convolutional Neural Networks for Interaction with a Manipulator Robot. Communication and Applied Technologies - Proceedings of ICOMTA 2022. editor / Paulo Carlos López-López ; Ángel Torres-Toukoumidis ; Andrea De-Santis ; Óscar Avilés ; Daniel Barredo. Springer Science and Business Media Deutschland GmbH, 2023. pp. 13-23 (Smart Innovation, Systems and Technologies).

@inproceedings{e16328b4a62640d99297029dc3918472,

title = "Classification of Electrooculography Signals Using Convolutional Neural Networks for Interaction with a Manipulator Robot",

abstract = "Electrooculography (EOG) has been widely applied in human–machine interfaces (HMI) because it provides a reliable communication channel to assist people with disabilities. However, signal behavior under different conditions hinders eye movement classification when algorithms based on voltage threshold detection are used. Therefore, recalibration of the system is required for the classification algorithm to work correctly. Based on the above, a classification algorithm was developed to analyze the data vector corresponding to the entire EOG waveform, instead of just one characteristic value of the signal, thus avoiding the system recalibration process. A convolutional neural network (CNN) was implemented to classify six targets corresponding to different eye movements. The proposed model was compared with a feedforward neural network (FNN) to evaluate its performance. The results were implemented in an HMI for interaction with a manipulator robot.",

keywords = "Convolutional neural networks, Deep learning, Electrooculography, Human machine interface",

author = "Pellico-S{\'a}nchez, {O. I.} and Ni{\~n}o-Su{\'a}rez, {P. A.} and Hern{\'a}ndez-Bele{\~n}o, {R. D.} and Avil{\'e}s-S{\'a}nchez, {O. F.} and P{\'e}rez-Bahena, {M. H.}",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; International Conference on Communication and Applied Technologies, ICOMTA 2022 ; Conference date: 07-09-2022 Through 09-09-2022",

year = "2023",

doi = "10.1007/978-981-19-6347-6_2",

language = "Ingl{\'e}s",

isbn = "9789811963469",

series = "Smart Innovation, Systems and Technologies",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "13--23",

editor = "L{\'o}pez-L{\'o}pez, {Paulo Carlos} and {\'A}ngel Torres-Toukoumidis and Andrea De-Santis and {\'O}scar Avil{\'e}s and Daniel Barredo",

booktitle = "Communication and Applied Technologies - Proceedings of ICOMTA 2022",

address = "Alemania",

}

Pellico-Sánchez, OI, Niño-Suárez, PA, Hernández-Beleño, RD, Avilés-Sánchez, OF & Pérez-Bahena, MH 2023, Classification of Electrooculography Signals Using Convolutional Neural Networks for Interaction with a Manipulator Robot. in PC López-López, Á Torres-Toukoumidis, A De-Santis, Ó Avilés & D Barredo (eds), Communication and Applied Technologies - Proceedings of ICOMTA 2022. Smart Innovation, Systems and Technologies, vol. 318, Springer Science and Business Media Deutschland GmbH, pp. 13-23, International Conference on Communication and Applied Technologies, ICOMTA 2022, Cuenca, Ecuador, 7/09/22. https://doi.org/10.1007/978-981-19-6347-6_2

Classification of Electrooculography Signals Using Convolutional Neural Networks for Interaction with a Manipulator Robot. / Pellico-Sánchez, O. I.; Niño-Suárez, P. A.; Hernández-Beleño, R. D. et al.
Communication and Applied Technologies - Proceedings of ICOMTA 2022. ed. / Paulo Carlos López-López; Ángel Torres-Toukoumidis; Andrea De-Santis; Óscar Avilés; Daniel Barredo. Springer Science and Business Media Deutschland GmbH, 2023. p. 13-23 (Smart Innovation, Systems and Technologies; Vol. 318).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Classification of Electrooculography Signals Using Convolutional Neural Networks for Interaction with a Manipulator Robot

AU - Pellico-Sánchez, O. I.

AU - Niño-Suárez, P. A.

AU - Hernández-Beleño, R. D.

AU - Avilés-Sánchez, O. F.

AU - Pérez-Bahena, M. H.

PY - 2023

Y1 - 2023

N2 - Electrooculography (EOG) has been widely applied in human–machine interfaces (HMI) because it provides a reliable communication channel to assist people with disabilities. However, signal behavior under different conditions hinders eye movement classification when algorithms based on voltage threshold detection are used. Therefore, recalibration of the system is required for the classification algorithm to work correctly. Based on the above, a classification algorithm was developed to analyze the data vector corresponding to the entire EOG waveform, instead of just one characteristic value of the signal, thus avoiding the system recalibration process. A convolutional neural network (CNN) was implemented to classify six targets corresponding to different eye movements. The proposed model was compared with a feedforward neural network (FNN) to evaluate its performance. The results were implemented in an HMI for interaction with a manipulator robot.

AB - Electrooculography (EOG) has been widely applied in human–machine interfaces (HMI) because it provides a reliable communication channel to assist people with disabilities. However, signal behavior under different conditions hinders eye movement classification when algorithms based on voltage threshold detection are used. Therefore, recalibration of the system is required for the classification algorithm to work correctly. Based on the above, a classification algorithm was developed to analyze the data vector corresponding to the entire EOG waveform, instead of just one characteristic value of the signal, thus avoiding the system recalibration process. A convolutional neural network (CNN) was implemented to classify six targets corresponding to different eye movements. The proposed model was compared with a feedforward neural network (FNN) to evaluate its performance. The results were implemented in an HMI for interaction with a manipulator robot.

KW - Convolutional neural networks

KW - Deep learning

KW - Electrooculography

KW - Human machine interface

UR - http://www.scopus.com/inward/record.url?scp=85144224888&partnerID=8YFLogxK

U2 - 10.1007/978-981-19-6347-6_2

DO - 10.1007/978-981-19-6347-6_2

M3 - Contribución a la conferencia

AN - SCOPUS:85144224888

SN - 9789811963469

T3 - Smart Innovation, Systems and Technologies

SP - 13

EP - 23

BT - Communication and Applied Technologies - Proceedings of ICOMTA 2022

A2 - López-López, Paulo Carlos

A2 - Torres-Toukoumidis, Ángel

A2 - De-Santis, Andrea

A2 - Avilés, Óscar

A2 - Barredo, Daniel

PB - Springer Science and Business Media Deutschland GmbH

T2 - International Conference on Communication and Applied Technologies, ICOMTA 2022

Y2 - 7 September 2022 through 9 September 2022

ER -

Pellico-Sánchez OI, Niño-Suárez PA, Hernández-Beleño RD, Avilés-Sánchez OF, Pérez-Bahena MH. Classification of Electrooculography Signals Using Convolutional Neural Networks for Interaction with a Manipulator Robot. In López-López PC, Torres-Toukoumidis Á, De-Santis A, Avilés Ó, Barredo D, editors, Communication and Applied Technologies - Proceedings of ICOMTA 2022. Springer Science and Business Media Deutschland GmbH. 2023. p. 13-23. (Smart Innovation, Systems and Technologies). doi: 10.1007/978-981-19-6347-6_2

Classification of Electrooculography Signals Using Convolutional Neural Networks for Interaction with a Manipulator Robot

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this