Neurophysiological predictors of deep learning based unilateral upper limb motor imagery classification

Justin Sonntag^1*Lin Yu¹Xilu Wang²Thomas Schack¹

• ¹Department of Psychology and Sport Science, Bielefeld University, Bielefeld, Germany
• ²Computer Science Research Centre, University of Surrey, Guildford, South East England, United Kingdom

Motor imagery-based brain-computer interfaces (BCIs) are a technique for decoding and classifying the intention of motor execution, solely based on imagined (rather than executed) movements. Although deep learning techniques have increased the potential of BCIs, the complexity of decoding unilateral upper limb motor imagery remains challenging. To understand whether neurophysiological features, which are directly related to neural mechanisms of motor imagery, might influence classification accuracy, most studies have largely leveraged traditional machine learning frameworks, leaving deep learning-based techniques underexplored. In this work, three different deep learning models from the literature (EEGNet, FBCNet, NFEEG) and two common spatial pattern-based machine learning classifiers (SVM, LDA) were used to classify the imagery of right elbow flexion and extension from participants using electroencephalography data. From two recorded resting states (eyes-open, eyes-closed), absolute and relative alpha and beta power of the frontal, fronto-central and central electrodes were used to predict the accuracy of the different classifiers. Specifically, the prediction of classifier accuracies by neurophysiological features revealed negative correlations between the relative alpha band and classifier accuracies and positive correlations between the absolute and relative beta band and classifiers accuracies. Most ipsilateral EEG channels yielded significant correlations with classifier accuracies,especially for the machine learning classifier. The findings might be interpreted as significant correlations between the mentioned frequency bands of a visuospatial attention state and classifier accuracies. While this needs further research, it might reveal more insights into the underlying neural mechanism of (unilateral upper limb) motor imagery and differences between deep learning and machine learning classifiers. the potential to restore autonomy for individuals with motor impairments, such as those affected by paralysis or limb loss. By enabling users to control external devices through imagined movements, motor imagery-based BCIs offer a non-invasive, intuitive alternative for interactions with the environment, ranging from robotic limbs to wheelchairs, enhancing the quality of life and increasing independence