A Haemodynamic Brain–Computer Interface Based on Real-Time Classification of near Infrared Spectroscopy Signals during Motor Imagery and Mental Arithmetic. Issue 3 (June 2013)

• Record Type: Journal Article
• Authors: Stangl, Matthias; Bauernfeind, Günther; Kurzmann, Jürgen; Scherer, Reinhold; Neuper, Christa
• Is Part Of: Journal of near infrared spectroscopy. Volume 21:Issue 3(2013)
• Page Start: 157
• Page End: 171
• Publication Date: 2013-06
• Subjects: brain–computer interface (BCI) -- near infrared (NIR) spectroscopy -- motor imagery -- mental arithmetic -- real-time classification; Near infrared spectroscopy -- Periodicals; 543.5
• DOI: 10.1255/jnirs.1048
• Languages: English
• ISSNs: 0967-0335

Abstract

Over the past decade, an increasing number of studies have investigated near infrared (NIR) spectroscopy for signal acquisition in brain–computer interface (BCI) systems. However, although a BCI relies on classifying brain signals in real-time, the majority of previous studies did not perform real-time NIR spectroscopy signal classification but derived knowledge about the feasibility of NIR spectroscopy for BCI purposes from offline analyses. The present study investigates whether NIR spectroscopy signals evoked by two different mental tasks (i.e. motor imagery and mental arithmetic) can be classified in real-time in order to control a NIR-BCI application. Furthermore, since this is the first study that attempts to distinguish between the haemodynamic responses to these two tasks, we aimed to investigate whether this task-combination is feasible for controlling a NIR-BCI. Twelve healthy participants were asked to control a moving ball on a computer screen by performing motor imagery and mental arithmetic tasks. The real-time classification of their task-specific NIR spectroscopy signals yielded accuracy rates ranging from 45% up to 93%. Offline analyses across all participants showed that both tasks evoked different haemodynamic responses in prefrontal and sensorimotor cortex areas. On the one hand, these results demonstrate the considerable potential of NIR spectroscopy for BCI signal acquisition and the feasibility of the applied mental tasks for NIR-BCI control. On the other hand, since the classification accuracy showed an unsatisfactory stability across measurement sessions, we conclude that further investigations and progress in methodological issues are needed and we discuss further steps that have to be taken until it is conceivable to implement a real-time capable NIR-BCI that works with sufficient accuracy across a large group of individuals.