Using Web Mining to Support Low Cost Historical Vehicle Traffic Analytics

Analyzing historical vehicle traffic data has many applications including urban planning and intelligent in-vehicle route prediction. A common practice to acquire this data is through roadside sensors. This approach is expensive because of infrastructure and planning costs and cannot be easily applied to new routes. In this paper, a low-cost Web mining approach is proposed to address these limitations. Our system gathers information about vehicle commute times, accidents, and weather reports from heterogeneous Web sources. Information from these sources can be combined to support road traffic analytics. We illustrate the utility of our system through a clustering analysis that investigates the traffic patterns of the busiest highway in Calgary along with factors having the most impact on commute time. The analysis shows that most of the accidents are localized around a small section of the highway near the city center and that the commute time in this segment is significantly more than that in other segments. Bad weather increases the typical evening rush hour commute time by 60% for days with moderate accidents and by a factor of 100% for days with large number of accidents. Overall, commute times can vary by a factor of 4 depending on accidents and weather. Keywords-road traffic; clustering; data analysis; Web mining; traffic management