The integrated strategy for detecting driver
drowsiness described in this work makes use of the
driver's physical, physiological, and optical cues. A
machine learning image processing algorithm that
contributes to the visual behaviour analysis is used to
combine facial and eye analysis to assess the driver's
level of exhaustion. As part of the physical behaviour
method, the steering grip of the driver is measured using
a human antenna effect-based touch sensing technology.
Driver heart rate data is collected using a sensor and
evaluated to detect tiredness based on the threshold
Internet of Things, drowsiness, image processing, heart rate, touch sensing, buzzer.