Universal brain-computer interface lets people play games with just their thoughts

Science Daily  April 1, 2024
Subject training requires collecting user-specific calibration data due to high inter-subject neural variability that limits the usability of generic decoders. Calibration is cumbersome and may produce inadequate data for building decoders, especially with naïve subjects. Researchers at UT Austin showed that a decoder trained on the data of a single expert is readily transferrable to inexperienced users via domain adaptation techniques allowing calibration-free Brain-computer interface (BCI) training. They introduced two real-time frameworks, (i) Generic Recentering (GR) through unsupervised adaptation and (ii) Personally Assisted Recentering (PAR) and evaluated it on naïve subjects to show that their frameworks promoted subjects’ ability to acquire individual BCI skills. The features were task-specific and were learned in parallel as participants practiced the tasks in every session. They observed that longitudinal training coupled with unsupervised domain matching (GR) achieved similar performance to supervised recalibration (PAR). The researchers concluded that their frameworks facilitate calibration-free BCIs and have immediate implications for broader populations—such as patients with neurological pathologies… read more. Open Access TECHNICAL ARTICLE