A deep learning model based on vision transformer architecture classified lower limb movement intention from EEG signals with 97.33% accuracy (p < 0.0001).
Vision transformer architecture applied to EEG time-frequency maps provides highly accurate decoding of lower limb movement intention, showing potential for brain-machine interface development in neurorehabilitation.
p-value: p=< 0.0001
Electroencephalography (EEG) signals have a major impact on how well assistive rehabilitation devices work. These signals have become a common technique in recent studies to investigate human motion functions and behaviors. However, incorporating EEG signals to investigate motor planning or movement intention could benefit all patients who can plan motion but are unable to execute it. In this paper, the movement planning of the lower limb was investigated using EEG signal and bilateral movements were employed including dorsiflexion and plantar flexion of the right and left ankle joint movements. The proposed system uses Continuous Wavelet Transform (CWT) to generate a time–frequency (TF) map of each EEG signal in the motor cortex, and then uses the extracted images as input to a deep learning model for classification. Deep Learning (DL) models are created based on vision transformer architecture (ViT) which is the state-of-the-art of image classification and also the proposed models were compared with residual neural network (ResNet). The proposed technique reveals a significant classification performance for the multiclass problem ( p < 0.0001) where the classification accuracy was 97.33 ± 1.86 % and the F score, recall and precision were 97.32 ± 1.88 %, 97.30 ± 1.90 % and 97.36 ± 1.81 % respectively. These results shows that DL is a promising technique that can applied to investigate the user’s movements intention from EEG signals and highlight the potential of the proposed model for the development of future brain machine interface (BMI) for neurorehabilitation purposes.
Al-Quraishi et al. (2022) studied Motor planning or movement intention. Vision transformer architecture (ViT) deep learning model vs. Residual neural network (ResNet) was evaluated on Classification accuracy for multiclass lower limb movement planning (p=< 0.0001). A deep learning model based on vision transformer architecture classified lower limb movement intention from EEG signals with 97.33% accuracy (p < 0.0001).