Probe vehicle sample sizes for real-time information: the Houston experience

Abstract

Probe vehicle travel time data is an important source of real-time travel information for a variety of intelligent transportation system applications. This paper investigates the required minimum number of probe vehicles that are necessary to report real-time travel speeds and times for a desired statistical accuracy. Empirical travel time data from the Houston traffic monitoring system were analyzed to calculate travel time variation and the corresponding minimum required probe vehicle sample sizes. A regression equation was developed to estimate travel time variation, which can then be used to calculate sample sizes. It was concluded that the current number of probe vehicles in Houston provide reliable peak period travel speed information (i.e., 95% confidence that displayed real-time speeds are /spl plusmn/10%).