4.7 Article

Transfer Learning With Optimal Transportation and Frequency Mixup for EEG-Based Motor Imagery Recognition

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNSRE.2022.3211881

Keywords

Electroencephalography; Brain modeling; Transfer learning; Frequency-domain analysis; Transportation; Adaptation models; Feature extraction; Electroencephalogram (EEG); brain-computer interface (BCI); transfer learning; optimal transportation

Funding

  1. National Natural Science Foundation of China [61873181, 61922062, 61903270, 2021ZD0201600]
  2. Natural Science Foundation of Tianjin, China [21JCJQJC00130]

Ask authors/readers for more resources

In this study, a novel domain adaptation method with optimal transport and frequency mixup is proposed for cross-subject transfer learning in motor imagery BCIs. The method maps preprocessed EEG signals from source and target domains into latent space and aligns their distribution using optimal transport. Experimental results show that the proposed method outperforms previous state-of-the-art domain adaptation approaches.
Electroencephalography-based Brain Computer Interfaces (BCIs) invariably have a degenerate performance due to the considerable individual variability. To address this problem, we develop a novel domain adaptation method with optimal transport and frequency mixup for cross-subject transfer learning in motor imagery BCIs. Specifically, the preprocessed EEG signals from source and target domain are mapped into latent space with an embedding module, where the representation distributions and label distributions across domains have a large discrepancy. We assume that there exists a non-linear coupling matrix between both domains, which can be utilized to estimate the distance of joint distributions for different domains. Depending on the optimal transport, the Wasserstein distance between source and target domains is minimized, yielding the alignment of joint distributions. Moreover, a new mixup strategy is also introduced to generalize the model, where the inputs trials are mixed in frequency domain rather than in raw space. The extensive experiments on three evaluation benchmarks are conducted to validate the proposed framework. All the results demonstrate that our method achieves a superior performance than previous state-of-the-art domain adaptation approaches.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available