Rxivist logo

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

By Greta Tuckute, Sofie Therese Hansen, Troels Wesenberg Kjaer, Lars Kai Hansen

Posted 11 Nov 2019
bioRxiv DOI: 10.1101/834713

Neurofeedback based on real-time brain imaging allows for targeted training of brain activity with demonstrated clinical applications. A rapid technical development of electroencephalography (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. The 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 experimenter's needs. As 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. The 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.

Download data

  • Downloaded 747 times
  • Download rankings, all-time:
    • Site-wide: 18,708 out of 92,185
    • In neuroscience: 3,071 out of 16,393
  • Year to date:
    • Site-wide: 4,611 out of 92,185
  • Since beginning of last month:
    • Site-wide: 4,585 out of 92,185

Altmetric data


Downloads over time

Distribution of downloads per paper, site-wide


PanLingua

Sign up for the Rxivist weekly newsletter! (Click here for more details.)


News