… on BCI classification models using CNN-Transformer … the combination of CNNs and
Transformer in the field of speech … perform fNIRS classification based on CNN-Transformer and …

… vision, we propose an fNIRS classification network based on Transformer, named fNIRS-T.
We … The CNN model [39] consists of three 1D convolutional layers, two fully connected layers, …

… By using the fNIRS system to monitor changes in cerebral … This paper proposes a CNN-Transformer
network, which … innovative use of the CNN-Transformer network to classify the three-…

… To achieve a higher level of classification of fNIRS signals, we propose a method that fuses
CNN and … In this study, we propose a hybrid CNN and Transformer model, which extracts …

… Attempts have been made to classify the states of awake, drowsy, … As a follow-up study, a
study using the LSTM-CNN model … This research uses CNN to learn spatial information but fails …

… To this goal, we propose a transformer-based method for cross-subject mental workload …
We only use a pure transformer encoder and we further discuss the effect of CNN parts and …

… fNIRS neuroimaging was used to collect highresolution … model, a CNN-LSTM hybrid, and
a transformer model. Results: … features from fNIRS data and classified workload confidence …

… CNN and LSTM techniques for fNIRS … the transformer-based neural network model, which
excels in identifying and excluding OOD data in fNIRS, within both detection and classification …

… This study applied CNNs to classify overt and imagined … fNIRS-guided attention feature in a
CNN along with EEG and … -the-art model architectures such as transformer-based models for …

… -term memory (CNN-LSTM) algorithm for the integrated classification of fNIRS EEG for hybrid
… dimension with RPs and fed into the CNN to extract essential features without performing …