Real-time Stage 1 Sleep Detection and Warning System Using a Low-Cost EEG Headset

3 Acknowledgements I would like to thank my committee chair Dr. Samhita Rhodes for her assistance and direction in my research and thesis. I would also like to thank Dr. Dr. Paul Fishback for being willing to participate in my thesis committee. All of their input helped improve the depth of my research and quality this thesis. I would also like to thank my wife, Jen Van Hal, for giving me the time to devote to this thesis and for helping and supporting me every step of the way. Abstract The goal of this thesis is to design and test a real-time Stage 1 sleep detection and warning system using a low-cost single dry-sensor EEG headset. Such a system would allow aircraft pilots or truck drivers to receive an auditory warning when they are beginning to fall asleep. The device designed in this study records a single EEG signal and filters it into low Alpha (7. frequency bands. When the EEG transitions to match that of Stage 1 sleep for a short period of time, the device produces an audible alarm. The system proved 81% effective at detecting sleep in a small sample group. All failures were due to false alarms. Compared to tradition sleep scoring, this device predicted and responded to the onset of drowsiness preceding stage 1 sleep.