Hansen, S. T. | bioRxiv Science

bioRxiv2019

A framework for closed-loop neurofeedback for real-time EEG decoding

Neurofeedback based on real-time brain imaging allows for targeted training of brain activity with demonstrated clinical applications. A rapid technical development of electroen-cephalography (EEG)-based systems and an increasing interest in cognitive training has lead to a call for accessible and adaptable software frameworks. Here, we present and outline the core components of a novel open-source neurofeedback framework based on scalp EEG signals for real-time neuroimaging, state classification and closed-loop feedback.\n\nThe software framework includes real-time signal preprocessing, adaptive artifact rejection, and cognitive state classification from scalp EEG. The framework is implemented using exclusively Python source code to allow for diverse functionality, high modularity, and easy extendibility of software development depending on the experimenters needs.\n\nAs a proof of concept, we demonstrate the functionality of our new software framework by implementing an attention training paradigm using a consumer-grade, dry-electrode EEG system. Twenty-two participants were trained on a single neurofeedback session with behavioral pre- and post-training sessions within three consecutive days. We demonstrate a mean decoding error rate of 34.3% (chance=50%) of subjective attentional states. Hence, cognitive states were decoded in real-time by continuously updating classification models on recently recorded EEG data without the need for any EEG recordings prior to the neurofeedback session.\n\nThe proposed software framework allows a wide range of users to actively engage in the development of novel neurofeedback tools to accelerate improvements in neurofeedback as a translational and therapeutic tool.

neuroscience↗

bioRxiv2018

Single Trial Decoding of Scalp EEG Under Naturalistic Stimuli

There is significant current interest in decoding mental states from electro-encephalography (EEG) recordings. EEG signals are subject-specific, sensitive to disturbances, and have a low signal-to-noise ratio, which has been mitigated by the use of laboratory-grade EEG acquisition equipment under highly controlled conditions. In the present study, we investigate single-trial decoding of natural, complex stimuli based on scalp EEG acquired with a portable, 32 dry-electrode sensor system in a typical office setting. We probe generalizability by a leave-one-subject-out cross-validation approach. We demonstrate that Support Vector Machine (SVM) classifiers trained on a relatively small set of de-noised (averaged) pseudo-trials perform on par with classifiers trained on a large set of noisy single-trial samples. For visualization of EEG signatures exploited by SVM classifiers, we propose a novel method for computing sensitivity maps of EEG-based SVM classifiers. Moreover, we apply the NPAIRS resampling framework for estimation of map uncertainty and show that effect sizes of sensitivity maps for classifiers trained on small samples of de-noised data and large samples of noisy data are similar. Finally, we demonstrate that the average pseudo-trial classifier can successfully predict the class of single trials from withheld subjects, which allows for fast classifier training, parameter optimization and unbiased performance evaluation in machine learning approaches for brain decoding.

neuroscience↗