Research Article
Contrastive Learning Consistent and Identifiable Latent Embeddings for EEG
@INPROCEEDINGS{10.1007/978-3-031-65126-7_22, author={Feng Liang and Zhen Zhang and Jiawei Mo and Wenxin Hu}, title={Contrastive Learning Consistent and Identifiable Latent Embeddings for EEG}, proceedings={Quality, Reliability, Security and Robustness in Heterogeneous Systems. 19th EAI International Conference, QShine 2023, Shenzhen, China, October 8 -- 9, 2023, Proceedings, Part I}, proceedings_a={QSHINE}, year={2024}, month={8}, keywords={EEG Contrastive learning Latent embedding Neural representation Identity recognition}, doi={10.1007/978-3-031-65126-7_22} }- Feng Liang
Zhen Zhang
Jiawei Mo
Wenxin Hu
Year: 2024
Contrastive Learning Consistent and Identifiable Latent Embeddings for EEG
QSHINE
Springer
DOI: 10.1007/978-3-031-65126-7_22
Abstract
Extracting informative EEG data into low-dimension latent embeddings is important for storing and analyzing these neuron signals and applying them to various applications, such as modern human-computer interaction (HCI) techniques. We use the contrastive learning algorithm on time-domain features of EEG in both discovery-driven (self-supervised) and hypothesis (supervised) manners to encode the EEG data into latent embeddings that are proven consistent and identifiable. The self-supervised embeddings have the potential to be used for a range of downstream tasks, while the supervised embeddings have very high decoding accuracy for specific tasks. With embeddings encoded from EEG features collected within every 0.5-s window, the accuracy of recognizing the identities of persons by decoding the self-supervised and supervised embeddings is as high as 96.2% and 99.6%, respectively. Our method and results can promote new HCI techniques, e.g., automatically connecting users to their roles in AR games once they wear EEG-capable devices. The source code is available at:https://www.github.com/liangfengsid/timeEegContrastive.
