Real-time head movement tracking through earables in moving vehicles

Abstract

The Internet of Things is enabling innovations in the automotive industry by expanding the capabilities of vehicles by connecting them with the cloud. One important application domain is traffic safety, which can benefit from monitoring the driver’s condition to see if they are capable of safely handling the vehicle. By detecting drowsiness, inattentiveness, and distraction of the driver it is possible to react before accidents happen. This thesis explores how accelerometer and gyroscope data collected using earables can be used to classify the orientation of the driver’s head in a moving vehicle. It is found that machine learning algorithms such as Random Forest and K-Nearest Neighbor can be used to reach fairly accurate classifications even without applying any noise reduction to the signal data. Data cleaning and transformation approaches are studied to see how the models could be improved further. This study paves the way for the development of driver monitoring systems capable of reacting to anomalous driving behavior before traffic accidents can happen.