Component-mixing strategy: A decomposition-based data augmentation algorithm for motor imagery signals

Deep learning has achieved a remarkable success in areas such as brain-computer interface systems (BCI). However, electroencephalography (EEG) signals evoked by motor imagery (MI) are sometimes limited in their amount due to invalid data caused by the subjects’ fatigue, leading to a performance degr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neurocomputing (Amsterdam) Jg. 465; S. 325 - 335
Hauptverfasser: Li, Binghua, Zhang, Zhiwen, Duan, Feng, Yang, Zhenglu, Zhao, Qibin, Sun, Zhe, Solé-Casals, Jordi
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 20.11.2021
Schlagworte:
Brain-computer interface
Data augmentation
Motor imagery
Signal decomposition
Brain-computer interface
Data augmentation
Motor imagery
Signal decomposition
ISSN:0925-2312, 1872-8286
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Deep learning has achieved a remarkable success in areas such as brain-computer interface systems (BCI). However, electroencephalography (EEG) signals evoked by motor imagery (MI) are sometimes limited in their amount due to invalid data caused by the subjects’ fatigue, leading to a performance degradation. To this end, in this work we extend empirical mode decomposition into multivariate empirical mode decomposition and intrinsic time-scale decomposition, proposing a component-mixing strategy (CMS) for MI data augmentation. Compared to commonly used data augmentation methods such as generative adversarial networks, CMS can generate artificial trials from a few training samples without any required training. We claim that raw and artificial data generated by CMS are consistent with respect to the distribution and power spectral density. Experiments done on the BCI Competition IV dataset 2b show that CMS can achieve a considerable improvement on the binary classification accuracy and the area under the curve score using EEGNet, wavelet neural networks and a support vector machine.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2021.08.119