TY - GEN
T1 - CNN-based Subject-Transfer Approach for Training Minimized Lower-Limb MI-BCIs
AU - Jeong, Ji Hyeok
AU - Kim, Keun Tae
AU - Lee, Song Joo
AU - Kim, Dong Joo
AU - Kim, Hyungmin
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - The subject-transfer approach has recently been proposed to overcome the limitation of requiring a long training time in the motor imagery (MI)-based brain-computer interfaces (BCIs). However, the applicability for reducing the training time for lower-limb MI-BCI has not been investigated yet. In this study, we proposed a dual-domain convolutional neural network (CNN)-based subject-transfer method. We investigated how the classification accuracy changes according to the reduced number of training trials. Two lower-limb MIs (gait and sit-down) and rest electroencephalography (EEG) data were collected from five healthy subjects. The CNN model was pre-trained using other subjects' data and fine-tuned with the target subject's training data. There was a significant increase in classification accuracy (7% with 15 and 10 trials) compared to the self-training approach using the same CNN model trained only with the target subject's training data. Based on these results, the subject-transfer approach can contribute to minimizing the training time of lower-limb MI-BCIs while preserving the classification accuracy.
AB - The subject-transfer approach has recently been proposed to overcome the limitation of requiring a long training time in the motor imagery (MI)-based brain-computer interfaces (BCIs). However, the applicability for reducing the training time for lower-limb MI-BCI has not been investigated yet. In this study, we proposed a dual-domain convolutional neural network (CNN)-based subject-transfer method. We investigated how the classification accuracy changes according to the reduced number of training trials. Two lower-limb MIs (gait and sit-down) and rest electroencephalography (EEG) data were collected from five healthy subjects. The CNN model was pre-trained using other subjects' data and fine-tuned with the target subject's training data. There was a significant increase in classification accuracy (7% with 15 and 10 trials) compared to the self-training approach using the same CNN model trained only with the target subject's training data. Based on these results, the subject-transfer approach can contribute to minimizing the training time of lower-limb MI-BCIs while preserving the classification accuracy.
KW - Brain-Computer interface
KW - Convolutional Neural Network
KW - Lower-Limb Motor Imagery
KW - Subject-Transfer
UR - http://www.scopus.com/inward/record.url?scp=85146199737&partnerID=8YFLogxK
U2 - 10.1109/BCI53720.2022.9734910
DO - 10.1109/BCI53720.2022.9734910
M3 - Conference contribution
AN - SCOPUS:85146199737
T3 - International Winter Conference on Brain-Computer Interface, BCI
BT - 10th International Winter Conference on Brain-Computer Interface, BCI 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Winter Conference on Brain-Computer Interface, BCI 2022
Y2 - 21 February 2022 through 23 February 2022
ER -