22nd EANN 2021, 25 - 27 June 2021, Greece

fNIRS-Based BCI Using Deep Neural Network with an Application to Deduce the Driving Mode based on the Driver's Mental State

Kazuhiko Takahashi, Reo Yokono, Chang Chu, Gauvain Huve, Masafumi Hashimoto


  Despite the recent advances in the development of autonomous vehicles, it is still important to be able to ascertain if a driver is fit to drive at any given time in case the auto–pilot mode fails. This study evaluates a method for deducing the current driving mode of the vehicle (manual driving versus auto–pilot mode) from the recognised mental state of the driver using a brain–computer interface (BCI) that comprises a functional near–infrared spectroscopy (fNIRS)–based device for measuring the activity in the prefrontal cortex of the driver’s brain and a deep neural network for classifying the fNIRS signals. With an average classification accuracy of over 70%, this study shows the potential of using the fNIRS–based BCI for monitoring the mental states of the driver.  

*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.