Unsupervised feature learning for EEG-based emotion recognition

Zirui Lan, Olga Sourina, Lipo Wang, Reinhold Scherer, Gernot Müller-Putz

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung

Abstract

Spectral band power features are one of the most widely used features in the studies of electroencephalogram (EEG)-based emotion recognition. The power spectral density of EEG signals is partitioned into different bands such as delta, theta, alpha and beta band etc. Though based on neuroscientific findings, the partition of frequency bands is somewhat on an ad-hoc basis, and the definition of frequency ranges of the bands of interest can vary between studies. On the other hand, it is also arguable that one definition of power bands could perform equally well on all subjects. In this paper, we propose to use autoencoder to automatically learn from each subject the salient frequency components from power spectral density estimated as periodogram by Fast Fourier Transform (FFT). We propose a network architecture especially for EEG feature extraction, one that adopts hidden unit clustering with added pooling neuron per cluster. The classification accuracy with features extracted by our proposed method is benchmarked against that with standard power features. Experimental results show that our proposed feature extraction method achieves accuracy ranging from 44% to 59% for three-emotion classification. We also see a 4-20% accuracy improvement over standard band power features.

Originalspracheenglisch
TitelProceedings - 2017 International Conference on Cyberworlds, CW 2017 - in cooperation with
UntertitelEurographics Association International Federation for Information Processing ACM SIGGRAPH
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers
Seiten182-185
Seitenumfang4
Band2017-January
ISBN (elektronisch)9781538620892
DOIs
PublikationsstatusVeröffentlicht - 27 Nov. 2017
Veranstaltung2017 International Conference on Cyberworlds: CW 2017 - Chester, Großbritannien / Vereinigtes Königreich
Dauer: 20 Sept. 201722 Sept. 2017
http://cw2017.org/index.html

Konferenz

Konferenz2017 International Conference on Cyberworlds
KurztitelCYBERWORLDS
Land/GebietGroßbritannien / Vereinigtes Königreich
OrtChester
Zeitraum20/09/1722/09/17
Internetadresse

ASJC Scopus subject areas

  • Artificial intelligence
  • Computernetzwerke und -kommunikation
  • Angewandte Informatik
  • Medientechnik
  • Modellierung und Simulation

Fingerprint

Untersuchen Sie die Forschungsthemen von „Unsupervised feature learning for EEG-based emotion recognition“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren