| Summary: | Brain-computer interfaces (BCIs) provide individuals with a means of interacting with a computer using only neural activity. To date, the majority of near-infrared spectroscopy (NIRS) BCIs have used prescribed tasks to achieve binary control. The goals of this study were to evaluate the possibility of using a personalized approach to establish control of a 2-, 3-, 4-, and 5-class NIRS-BCI, and to explore how various user characteristics correlate to accuracy. Ten able-bodied participants were recruited for five data collection sessions. Participants performed six mental tasks, and a personalized approach was used to select each individual’s best discriminating subset of tasks. The average offline cross-validation accuracies achieved were 78%, 61%, 47%, and 37% for the 2-, 3-, 4-, and 5-class problems, respectively. Most notably, all participants exceeded an accuracy of 70% for the 2-class problem, and two participants exceeded an accuracy of 70% for the 3-class problem. Additionally, accuracy was found to be strongly positively correlated (Pearson’s) with perceived ease of session (p = 0.653), ease of concentration (p = 0.634), and enjoyment (p = 0.550), but strongly negatively correlated with verbal IQ (p = -0.749).
|
|---|
