Domain adaptation techniques for EEG-based emotion recognition : a comparative study on two public datasets

Affective brain-computer interface (aBCI) introduces personal affective factors to human-computer interaction. The state-of-the-art aBCI tailors its classifier to each individual user to achieve accurate emotion classification. A subject-independent classifier that is trained on pooled data from mul...

Full description

Saved in:
Bibliographic Details
Main Authors: Lan, Zirui, Sourina, Olga, Wang, Lipo, Scherer, Reinhold, Muller-Putz, Gernot R.
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/144553
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-144553
record_format dspace
spelling sg-ntu-dr.10356-1445532020-11-12T02:50:25Z Domain adaptation techniques for EEG-based emotion recognition : a comparative study on two public datasets Lan, Zirui Sourina, Olga Wang, Lipo Scherer, Reinhold Muller-Putz, Gernot R. School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Affective Brain–computer Interface Cross Dataset Affective brain-computer interface (aBCI) introduces personal affective factors to human-computer interaction. The state-of-the-art aBCI tailors its classifier to each individual user to achieve accurate emotion classification. A subject-independent classifier that is trained on pooled data from multiple subjects generally leads to inferior accuracy, due to the fact that electroencephalography patterns vary from subject to subject. Transfer learning or domain adaptation techniques have been leveraged to tackle this problem. Existing studies have reported successful applications of domain adaptation techniques on SEED dataset. However, little is known about the effectiveness of the domain adaptation techniques on other affective datasets or in a cross-dataset application. In this paper, we focus on a comparative study on several state-of-the-art domain adaptation techniques on two datasets: 1) DEAP and 2) SEED. We demonstrate that domain adaptation techniques can improve the classification accuracy on both datasets, but not so effective on DEAP as on SEED. Then, we explore the efficacy of domain adaptation in a cross-dataset setting when the data are collected under different environments using different devices and experimental protocols. Here, we propose to apply domain adaptation to reduce the intersubject variance as well as technical discrepancies between datasets, and then train a subject-independent classifier on one dataset and test on the other. Experiment results show that using domain adaptation technique in a transductive adaptation setting can improve the accuracy significantly by 7.25%-13.40% compared to the baseline accuracy where no domain adaptation technique is used. National Research Foundation (NRF) Accepted version This work was supported by the National Research Foundation, Prime Minister’s Office, Singapore, through Its International Research Centers in Singapore Funding Initiative. 2020-11-12T02:50:25Z 2020-11-12T02:50:25Z 2019 Journal Article Lan, Z., Sourina, O., Wang, L., Scherer, R., & Muller-Putz, G. R. (2019). Domain Adaptation Techniques for EEG-Based Emotion Recognition : A Comparative Study on Two Public Datasets. IEEE Transactions on Cognitive and Developmental Systems, 11(1), 85–94. doi:10.1109/tcds.2018.2826840 2379-8920 https://hdl.handle.net/10356/144553 10.1109/TCDS.2018.2826840 1 11 85 94 en IEEE Transactions on Cognitive and Developmental Systems © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TCDS.2018.2826840. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
Affective Brain–computer Interface
Cross Dataset
spellingShingle Engineering::Electrical and electronic engineering
Affective Brain–computer Interface
Cross Dataset
Lan, Zirui
Sourina, Olga
Wang, Lipo
Scherer, Reinhold
Muller-Putz, Gernot R.
Domain adaptation techniques for EEG-based emotion recognition : a comparative study on two public datasets
description Affective brain-computer interface (aBCI) introduces personal affective factors to human-computer interaction. The state-of-the-art aBCI tailors its classifier to each individual user to achieve accurate emotion classification. A subject-independent classifier that is trained on pooled data from multiple subjects generally leads to inferior accuracy, due to the fact that electroencephalography patterns vary from subject to subject. Transfer learning or domain adaptation techniques have been leveraged to tackle this problem. Existing studies have reported successful applications of domain adaptation techniques on SEED dataset. However, little is known about the effectiveness of the domain adaptation techniques on other affective datasets or in a cross-dataset application. In this paper, we focus on a comparative study on several state-of-the-art domain adaptation techniques on two datasets: 1) DEAP and 2) SEED. We demonstrate that domain adaptation techniques can improve the classification accuracy on both datasets, but not so effective on DEAP as on SEED. Then, we explore the efficacy of domain adaptation in a cross-dataset setting when the data are collected under different environments using different devices and experimental protocols. Here, we propose to apply domain adaptation to reduce the intersubject variance as well as technical discrepancies between datasets, and then train a subject-independent classifier on one dataset and test on the other. Experiment results show that using domain adaptation technique in a transductive adaptation setting can improve the accuracy significantly by 7.25%-13.40% compared to the baseline accuracy where no domain adaptation technique is used.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Lan, Zirui
Sourina, Olga
Wang, Lipo
Scherer, Reinhold
Muller-Putz, Gernot R.
format Article
author Lan, Zirui
Sourina, Olga
Wang, Lipo
Scherer, Reinhold
Muller-Putz, Gernot R.
author_sort Lan, Zirui
title Domain adaptation techniques for EEG-based emotion recognition : a comparative study on two public datasets
title_short Domain adaptation techniques for EEG-based emotion recognition : a comparative study on two public datasets
title_full Domain adaptation techniques for EEG-based emotion recognition : a comparative study on two public datasets
title_fullStr Domain adaptation techniques for EEG-based emotion recognition : a comparative study on two public datasets
title_full_unstemmed Domain adaptation techniques for EEG-based emotion recognition : a comparative study on two public datasets
title_sort domain adaptation techniques for eeg-based emotion recognition : a comparative study on two public datasets
publishDate 2020
url https://hdl.handle.net/10356/144553
_version_ 1686109392461627392