Towards situation-awareness and ubiquitous data mining for road safety: rationale and architecture for a compelling application

Road crashes cost Australia $15 billion a year and 95% of these are attributed to drivers' errors. Risk assessment is at the core of the road safety problem. This paper presents an Advanced Driving Assistance System (ADAS), called SAWUR, that analyses situational driver behaviour and proposes real-time countermeasures to minimise fatalities/casualties. The system is based on Ubiquitous Data Mining (UDM) concepts. It fuses and analyses different types of information from crash data and physiological sensors to diagnose driving risks in realtime. The novelty of our approach consists of augmenting the diagnosis through UDM with associated countermeasures based on a context awareness mechanism. In other words, our system diagnoses and chooses a countermeasure by taking into account the contextual situation of the driver and the road conditions. The types of context we exploit include vehicle dynamics, drivers’ physiological condition, driver’s profile and environmental conditions. The rationale for exploiting contextual information is to increase the accuracy of the diagnosis (90%) and to reduce false alarm rates (below 1%). The ultimate goal is to decrease driver’s exposure to risks.