A CNN-LSTM for Motor Imagery EEG Detection
Why CNN-LSTM?
CNN layers detect better the spatial component of the data selecting the best features for us and RNN detect better the temporal component of the data.
(CNN layer is used to extract the most relevant features from the brain waves and LSTM is used to classify the time series.)
Contributions
1.proposed method of CNN-LSTM.
2.discussed the influence of using raw data over using the data split in frequency bands in the model proposed.
3.discuss the influence of certain frequency bands activity over other frequency bands.
Conclusions
the 5 types of waves (alpha, beta, theta, delta and gamma) are needed for an accurate classification and the raw data is not enough to ensure the accuracy of the results.
Cite This
F. M. Garcia-Moreno, M. Bermudez-Edo, M. J. Rodríguez-Fórtiz and J. L. Garrido, “A CNN-LSTM Deep Learning Classifier for Motor Imagery EEG Detection Using a Low-invasive and Low-Cost BCI Headband,” 2020 16th International Conference on Intelligent Environments (IE), 2020, pp. 84-91, doi: 10.1109/IE49459.2020.9155016.