Detecting behavioral microsleeps using EEG and LSTM recurrent neural networks

Lapses in visuomotor performance are often associated with behavioral microsleep events. Experiencing a lapse of this type while performing an important task can have catastrophic consequences. A warning system capable of reliably detecting patterns in EEG occurring before or during a lapse has the potential to save many lives. We are developing a behavioral microsleep detection system which employs Long Short'Term Memory (LSTM) recurrent neural networks. To train and validate the system, EEG, facial video and tracking data were collected from 15 subjects performing a visuomotor tracking task for 2 1-hour sessions. This provided behavioral information on lapse events with good temporal resolution. We developed an automated behavior rating system and trained it to estimate the mean opinion of 3 human raters on the likelihood of a lapse. We then trained an LSTM neural network to estimate the output of the lapse rating system given only EEG spectral data. The detection system was designed to operate in real-time without calibration for individual subjects. Preliminary results show the system is not reliable enough for general use, but results from some tracking sessions encourage further investigation of the reported approach.