EUVIMEDEUVIMED entdecken
Open Access

Feature Extraction With Stacked Autoencoders for EEG Channel Reduction in Emotion Recognition

Elnaz Vafaei iD, Fereidoun Nowshiravan Rahatabad iD, Seyed Kamaledin Setarehdan iD, Parviz Azadfallah iD

Basic and Clinical Neuroscience Journal · 01.05.2024 · 15 (3) · 393-402

DOI: 10.32598/bcn.2023.5138.2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Basic and Clinical Neuroscience Journal, online erschienen am 01.05.2024. Verfasst von Elnaz Vafaei und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Faculty of Medical Sciences and Technologies, Science and Research Branch, Islamic Azad University, Tehran, Ira…. Die Arbeit wurde bisher 4-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Emotion recognition by electroencephalogram (EEG) signals is one of the complex methods because the extraction and recognition of the features hidden in the signal are sophisticated and require a significant number of EEG channels. Presenting a method for feature analysis and an algorithm for reducing the number of EEG channels fulfills the need for research in this field.

Methods

Accordingly, this study investigates the possibility of utilizing deep learning to reduce the number of channels while maintaining the quality of the EEG signal. A stacked autoencoder network extracts optimal features for emotion classification in valence and arousal dimensions. Autoencoder networks can extract complex features to provide linear and non- linear features which are a good representative of the signal.

Results

The accuracy of a conventional emotion recognition classifier (support vector machine) using features extracted from SAEs was obtained at 75.7% for valence and 74.4% for arousal dimensions, respectively.

Conclusion

Further analysis also illustrates that valence dimension detection with reduced EEG channels has a different composition of EEG channels compared to the arousal dimension. In addition, the number of channels is reduced from 32 to 12, which is an excellent development for designing a small-size EEG device by applying these optimal features.

Schlagwörter

Stichwörter der Autor:innen

Channel reductionDeep learningElectroencephalogram (EEG)EmotionStacked auto-encoderanalysis

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Faculty of Medical Sciences and Technologies, Science and Research Branch, Islamic Azad University, Tehran, Iran.
  • School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran.
  • Faculty of Humanities, Tarbiat Modares University, Tehran, Iran.

ORCID-Profile: Elnaz Vafaei, Fereidoun Nowshiravan Rahatabad, Seyed Kamaledin Setarehdan, Parviz Azadfallah

Zitieren

APA

Vafaei, E., Nowshiravan Rahatabad, F., Setarehdan, S. K., & Azadfallah, P. (2024). Feature Extraction With Stacked Autoencoders for EEG Channel Reduction in Emotion Recognition. Basic and Clinical Neuroscience Journal, 15(3), 393-402. https://doi.org/10.32598/bcn.2023.5138.2

Vancouver

Vafaei E, Nowshiravan Rahatabad F, Setarehdan SK, Azadfallah P. Feature Extraction With Stacked Autoencoders for EEG Channel Reduction in Emotion Recognition. Basic and Clinical Neuroscience Journal. 2024;15(3):393-402. doi:10.32598/bcn.2023.5138.2

BibTeX
@article{Vafaei2024,
  author = {Vafaei, Elnaz and Nowshiravan Rahatabad, Fereidoun and Setarehdan, Seyed Kamaledin and Azadfallah, Parviz},
  title = {Feature Extraction With Stacked Autoencoders for EEG Channel Reduction in Emotion Recognition},
  journal = {Basic and Clinical Neuroscience Journal},
  year = {2024},
  volume = {15},
  number = {3},
  pages = {393--402},
  doi = {10.32598/bcn.2023.5138.2}
}
Kostenlos starten →