Wasserstein-Distance-Based Multi-Source Adversarial Domain Adaptation for Emotion Recognition and Vigilance Estimation

To build a subject-independent affective model based on electroencephalography (EEG) is a challenging task due to the domain shift problem caused by individual differences in EEG data. In this paper, we prove a new generalization bound based on Wasserstein distance for multi-source classification an...

Full description

Saved in:
Bibliographic Details
Published in2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) pp. 1424 - 1428
Main Authors Luo, Yun, Lu, Bao-Liang
Format Conference Proceeding
LanguageEnglish
Published IEEE 09.12.2021
Subjects
Affective brain-computer interface
Brain modeling
Buildings
Conferences
Data models
EEG-based emotion recognition
EEG-based vigilance estimation
Electroencephalography
Emotion recognition
Estimation
multisource domain adaptation
Online AccessGet full text

Cover

More Information
Summary:To build a subject-independent affective model based on electroencephalography (EEG) is a challenging task due to the domain shift problem caused by individual differences in EEG data. In this paper, we prove a new generalization bound based on Wasserstein distance for multi-source classification and regression problems. Based on our bound, we propose two novel Wasserstein-distance-based multi-source adversarial domain adaptation methods (wMADA) for learning domain invariant and task discriminative domain mappings by dynamically aligning different domain mappings. We evaluate our methods on two typical EEG datasets. The experimental results demonstrate that our wMADA methods successfully handle the multi-source domain shift problem in creating subject-independent affective models and outperform the state-of-the-art domain adaptation methods.
DOI:10.1109/BIBM52615.2021.9669383