Heading for new shores! Overcoming pitfalls in BCI design

• Published in: Brain computer interfaces (Abingdon, England) Vol. 4; no. 1-2; pp. 60 - 73
• Main Authors: Chavarriaga, Ricardo, Fried-Oken, Melanie, Kleih, Sonja, Lotte, Fabien, Scherer, Reinhold
• Format: Journal Article
• Language: English
• Published: England Taylor & Francis 03.04.2017
• Subjects: Artificial Intelligence; BCI; Biotechnology; Cognitive science; Computer Science; Computer Vision and Pattern Recognition; EEG; Human-Computer Interaction; limitations; Machine Learning; Neuroscience; Psychology; publication bias; Signal and Image Processing; signal processing; user training; user-centered design; publication bias; user training; signal processing; EEG; BCI; user centered design; artifacts; limitations; pitfalls; brain-computer interfaces; artefacts; reporting
• ISSN: 2326-263X; 2326-2621
• DOI: 10.1080/2326263X.2016.1263916

Research in brain-computer interfaces has achieved impressive progress towards implementing assistive technologies for restoration or substitution of lost motor capabilities, as well as supporting technologies for able-bodied subjects. Notwithstanding this progress, effective translation of these interfaces from proof-of-concept prototypes into reliable applications remains elusive. As a matter of fact, most of the current BCI systems cannot be used independently for long periods of time by their intended end-users. Multiple factors that inhibit the achievement of this goal have already been identified. However, it is not clear how they affect the overall BCI performance or how they should be tackled. This is worsened by publication bias, where only positive results are disseminated, preventing the research community from learning from its errors. This paper is the result of a workshop held at the 6th International BCI meeting in Asilomar. We summarize here the discussion on concrete research avenues and guidelines that may help overcome common pitfalls and make BCIs a useful alternative communication device.