A novel explainable machine learning approach for EEG-based brain-computer interface systems

• Published in: Neural computing & applications Vol. 34; no. 14; pp. 11347 - 11360
• Main Authors: Ieracitano, Cosimo, Mammone, Nadia, Hussain, Amir, Morabito, Francesco Carlo
• Format: Journal Article
• Language: English
• Published: London Springer London 01.07.2022; Springer Nature B.V
• Subjects: Accuracy; Artificial Intelligence; Artificial neural networks; Beamforming; Brain research; Classification; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Deep learning; Electroencephalography; Hands; Human-computer interface; Image Processing and Computer Vision; Inverse problems; Investigations; Machine learning; Neural networks; Occlusion; Probability and Statistics in Computer Science; S.I. : Healthcare Analytics; Sensitivity analysis; Deep learning; Beamforming; Brain–computer interface; Explainable machine learning
• DOI: 10.1007/s00521-020-05624-w
• ISSN: 0941-0643

Electroencephalographic (EEG) recordings can be of great help in decoding the open/close hand’s motion preparation. To this end, cortical EEG source signals in the motor cortex (evaluated in the 1-s window preceding movement onset) are extracted by solving inverse problem through beamforming. EEG sources epochs are used as source-time maps input to a custom deep convolutional neural network (CNN) that is trained to perform 2-ways classification tasks: pre-hand close (HC) versus resting state (RE) and pre-hand open (HO) versus RE. The developed deep CNN works well (accuracy rates up to 89.65 ± 5.29 % for HC versus RE and 90.50 ± 5.35 % for HO versus RE), but the core of the present study was to explore the interpretability of the deep CNN to provide further insights into the activation mechanism of cortical sources during the preparation of hands’ sub-movements. Specifically, occlusion sensitivity analysis was carried out to investigate which cortical areas are more relevant in the classification procedure. Experimental results show a recurrent trend of spatial cortical activation across subjects. In particular, the central region (close to the longitudinal fissure) and the right temporal zone of the premotor together with the primary motor cortex appear to be primarily involved. Such findings encourage an in-depth study of cortical areas that seem to play a key role in hand’s open/close preparation.