… -modal EEG+fNIRS recording and deep learning classifiers with synergistic effects. The
higher performances of the multi-modal acquisition with respect to standalone EEG and fNIRS …

… resolution of electroencephalography (EEG) with the … (fNIRS) require novel approaches to
decoding. Methods: We present an EEG-fNIRS Hybrid BCI that employs a new bimodal deep …

… in the classification of the hybrid EEG-fNIRS recordings of motor … recordings when compared
to EEG or fNIRS recordings alone. … performance using multimodal BCI and deep learning. …

… EEG/fNIRS signals. We then employ a deep neural network, as a powerful machine learning
… of applying the proposed method on EEG-only fNIRS-only and EEGfNIRS data is explored. …

… improved the decoding of bimanual force and the deep-learning … cnnatt was better at fusing
EEG and fNIRS. Consequently, the … In particular, we improve the fusion of EEG and fNIRS …

… fNIRS offers the unique advantage to be employed in freely … than electroencephalography
(EEG) or functional magnetic resonance imaging (fMRI). This permits the deployment of fNIRS …

… using the deep learning algorithm. Feature engineering in deep learning algorithms
automatically extracts the appropriate features from the signal. Thanks to deep learning method, we …

… In comparison to fNIRS, EEG has a higher temporal resolution because hemodynamic …
showed how deep learning methods can be successfully used for building BCIs based on fNIRS. …

… Earlier studies have mostly used EEG [22]–[25] for drowsiness … fNIRS were performed
either alone or in conjunction with EEG [10], [26], and a few studies using a combination of EEG/…

… Advancements in deep learning (neural networks) would allow the use of raw data for efficient
… The use of deep learning on a multi-modal system of combining EEG and fNIRS has been …