Sensor selection for maneuver classification
K. Torkkola, Subbarayan Venkatesan, Huan Liu · 2005
To determine when to present information from various devices or services to the driver of an automobile, it is necessary to determine whether a driver is engaged in a difficult driving situation that requires extensive attention. We present simulator experiments in determining which sensors make the classification of driving states into such maneuvers possible, using various machine learning techniques. Our findings indicate that a small number of derived sensor signals can accomplish the task.