Variational Autoencoder based Latent Factor Decoding of Multichannel EEG for Emotion Recognition

Xiang Li; Zhigang Zhao; Dawei Song; Yazhou Zhang; Chunyang Niu; Junwei Zhang; Jidong Huo; Jing Li

doi:10.1109/BIBM47256.2019.8983341

Variational Autoencoder based Latent Factor Decoding of Multichannel EEG for Emotion Recognition

Xiang Li
, Zhigang Zhao
, Dawei Song
, Yazhou Zhang
, Chunyang Niu
, Junwei Zhang
, Jidong Huo
, Jing Li

School of Computer Science and Technology

Qilu University of Technology
Zhengzhou University of Light Industry
Beijing Institute of Technology
Jiuquan Satellite Launch Center

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

26 Citations (Scopus)

Abstract

Robust cross-subject emotion recognition based on multichannel EEG has always been a hard work. In this work, we hypothesize there exists default brain variables across subjects in emotional processes. Hence, the states of the latent variables that related to emotional processing must contribute to building robust recognition models. We propose to utilize variational autoencoder (VAE) to determine the latent factors from the multichannel EEG. Through sequence modeling method, we examine the emotion recognition performance based on the learnt latent factors. The performance of the proposed methodology is verified on two public datasets (DEAP and SEED), and compared with traditional matrix factorization based (ICA) and autoencoder based (AE) approaches. Experimental results demonstrate that neural network is suitable for unsupervised EEG modeling and our proposed emotion recognition framework achieves the state-of-the-art performance. As far as we know, it is the first work that introduces VAE into multichannel EEG decoding for emotion recognition.

Original language	English
Title of host publication	Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019
Editors	Illhoi Yoo, Jinbo Bi, Xiaohua Tony Hu
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	684-687
Number of pages	4
ISBN (Electronic)	9781728118673
DOIs	https://doi.org/10.1109/BIBM47256.2019.8983341
Publication status	Published - Nov 2019
Event	2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019 - San Diego, United States Duration: 18 Nov 2019 → 21 Nov 2019

Publication series

Name	Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019

Conference

Conference	2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019
Country/Territory	United States
City	San Diego
Period	18/11/19 → 21/11/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Affective Computing
EEG
Emotion Recognition
Latent Factor Decoding
Variational Autoencoder

Access to Document

10.1109/BIBM47256.2019.8983341

Cite this

Li, X., Zhao, Z., Song, D., Zhang, Y., Niu, C., Zhang, J., Huo, J., & Li, J. (2019). Variational Autoencoder based Latent Factor Decoding of Multichannel EEG for Emotion Recognition. In I. Yoo, J. Bi, & X. T. Hu (Eds.), Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019 (pp. 684-687). Article 8983341 (Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM47256.2019.8983341

Li, Xiang ; Zhao, Zhigang ; Song, Dawei et al. / Variational Autoencoder based Latent Factor Decoding of Multichannel EEG for Emotion Recognition. Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019. editor / Illhoi Yoo ; Jinbo Bi ; Xiaohua Tony Hu. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 684-687 (Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019).

@inproceedings{53779a4182ee43fdbfedcad6a8d4a351,

title = "Variational Autoencoder based Latent Factor Decoding of Multichannel EEG for Emotion Recognition",

abstract = "Robust cross-subject emotion recognition based on multichannel EEG has always been a hard work. In this work, we hypothesize there exists default brain variables across subjects in emotional processes. Hence, the states of the latent variables that related to emotional processing must contribute to building robust recognition models. We propose to utilize variational autoencoder (VAE) to determine the latent factors from the multichannel EEG. Through sequence modeling method, we examine the emotion recognition performance based on the learnt latent factors. The performance of the proposed methodology is verified on two public datasets (DEAP and SEED), and compared with traditional matrix factorization based (ICA) and autoencoder based (AE) approaches. Experimental results demonstrate that neural network is suitable for unsupervised EEG modeling and our proposed emotion recognition framework achieves the state-of-the-art performance. As far as we know, it is the first work that introduces VAE into multichannel EEG decoding for emotion recognition.",

keywords = "Affective Computing, EEG, Emotion Recognition, Latent Factor Decoding, Variational Autoencoder",

author = "Xiang Li and Zhigang Zhao and Dawei Song and Yazhou Zhang and Chunyang Niu and Junwei Zhang and Jidong Huo and Jing Li",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019 ; Conference date: 18-11-2019 Through 21-11-2019",

year = "2019",

month = nov,

doi = "10.1109/BIBM47256.2019.8983341",

language = "English",

series = "Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "684--687",

editor = "Illhoi Yoo and Jinbo Bi and Hu, \{Xiaohua Tony\}",

booktitle = "Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019",

address = "United States",

}

Li, X, Zhao, Z, Song, D, Zhang, Y, Niu, C, Zhang, J, Huo, J & Li, J 2019, Variational Autoencoder based Latent Factor Decoding of Multichannel EEG for Emotion Recognition. in I Yoo, J Bi & XT Hu (eds), Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019., 8983341, Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019, Institute of Electrical and Electronics Engineers Inc., pp. 684-687, 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019, San Diego, United States, 18/11/19. https://doi.org/10.1109/BIBM47256.2019.8983341

Variational Autoencoder based Latent Factor Decoding of Multichannel EEG for Emotion Recognition. / Li, Xiang; Zhao, Zhigang; Song, Dawei et al.
Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019. ed. / Illhoi Yoo; Jinbo Bi; Xiaohua Tony Hu. Institute of Electrical and Electronics Engineers Inc., 2019. p. 684-687 8983341 (Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019).

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

TY - GEN

T1 - Variational Autoencoder based Latent Factor Decoding of Multichannel EEG for Emotion Recognition

AU - Li, Xiang

AU - Zhao, Zhigang

AU - Song, Dawei

AU - Zhang, Yazhou

AU - Niu, Chunyang

AU - Zhang, Junwei

AU - Huo, Jidong

AU - Li, Jing

PY - 2019/11

Y1 - 2019/11

N2 - Robust cross-subject emotion recognition based on multichannel EEG has always been a hard work. In this work, we hypothesize there exists default brain variables across subjects in emotional processes. Hence, the states of the latent variables that related to emotional processing must contribute to building robust recognition models. We propose to utilize variational autoencoder (VAE) to determine the latent factors from the multichannel EEG. Through sequence modeling method, we examine the emotion recognition performance based on the learnt latent factors. The performance of the proposed methodology is verified on two public datasets (DEAP and SEED), and compared with traditional matrix factorization based (ICA) and autoencoder based (AE) approaches. Experimental results demonstrate that neural network is suitable for unsupervised EEG modeling and our proposed emotion recognition framework achieves the state-of-the-art performance. As far as we know, it is the first work that introduces VAE into multichannel EEG decoding for emotion recognition.

AB - Robust cross-subject emotion recognition based on multichannel EEG has always been a hard work. In this work, we hypothesize there exists default brain variables across subjects in emotional processes. Hence, the states of the latent variables that related to emotional processing must contribute to building robust recognition models. We propose to utilize variational autoencoder (VAE) to determine the latent factors from the multichannel EEG. Through sequence modeling method, we examine the emotion recognition performance based on the learnt latent factors. The performance of the proposed methodology is verified on two public datasets (DEAP and SEED), and compared with traditional matrix factorization based (ICA) and autoencoder based (AE) approaches. Experimental results demonstrate that neural network is suitable for unsupervised EEG modeling and our proposed emotion recognition framework achieves the state-of-the-art performance. As far as we know, it is the first work that introduces VAE into multichannel EEG decoding for emotion recognition.

KW - Affective Computing

KW - EEG

KW - Emotion Recognition

KW - Latent Factor Decoding

KW - Variational Autoencoder

UR - https://www.scopus.com/pages/publications/85084339602

U2 - 10.1109/BIBM47256.2019.8983341

DO - 10.1109/BIBM47256.2019.8983341

M3 - Conference contribution

AN - SCOPUS:85084339602

T3 - Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019

SP - 684

EP - 687

BT - Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019

A2 - Yoo, Illhoi

A2 - Bi, Jinbo

A2 - Hu, Xiaohua Tony

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019

Y2 - 18 November 2019 through 21 November 2019

ER -

Li X, Zhao Z, Song D, Zhang Y, Niu C, Zhang J et al. Variational Autoencoder based Latent Factor Decoding of Multichannel EEG for Emotion Recognition. In Yoo I, Bi J, Hu XT, editors, Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 684-687. 8983341. (Proceedings - 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019). doi: 10.1109/BIBM47256.2019.8983341

Variational Autoencoder based Latent Factor Decoding of Multichannel EEG for Emotion Recognition

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this