Sangwoo Park Frank C. Park Choi Junhyuk KIM HYUNG MIN 2024-01-12T06:12:26Z 2024-01-12T06:12:26Z 2021-09-29 2018-02 2572-7672 https://pubs.kist.re.kr/handle/201004/79447 EEG-based BCI was recently applied to lower limb exoskeleton robots. Various machine learning decoders have shown high accuracy performance on classifying the gait state whether the subject is walking or standing. However, there is a trade-off between the accuracy and the responsiveness due to the delay time. The delay time is critical when controlling the exoskeleton robots with EEG decoders online (real-time). In this research, we propose spatio-spectral convolutional neural networks with relatively short segment of EEG data (0.2s) having 83.4% accuracy on gait state recognition. The gait intention recognition that detects the subject’s gait intention prior to the actual gait had 77.3% accuracy. We were able to classify EEG data of both healthy subjects and stroke patients at subacute and chronic phases. English IEEE EEG-based Gait State and Gait Intention Recognition Using Spatio-Spectral Convolutional Neural Network Conference 1 7th International Winter Conference on Brain-Computer Interface (BCI), pp.138 - 140 7th International Winter Conference on Brain-Computer Interface (BCI) 138 140 KO 정선 2018-02-18 2019 7TH INTERNATIONAL WINTER CONFERENCE ON BRAIN-COMPUTER INTERFACE (BCI) 000492868700028 2-s2.0-85068346161