Motor Imagery Decoding with Residual Dense Network

Permana Deny, Sae Won Cheon, Kae Won Choi

http://doi.org/10.5626/JOK.2022.49.5.380

This article proposes a Residual Dense Network (RDN) framework for brain signals during motor imagery (MI) decoding. We designed a decoding framework including feature extraction and a decoding algorithm built on a deep neural network to perform feature learning and decision making. We analyzed the capability of the RDN to decode a public BCI dataset from BCI Competition IV Dataset 2A. Experiments were conducted to evaluate the capability in terms of the performance accuracy for a given dataset and showed that the RDN framework achieved a result of 0.8290, outperforming the previous study using the same dataset benchmark. In conclusion, the RDN provided a decoding framework in a practical brain-computer interface.