A Gaussian Based Dynamic Freeway Segmentation Algorithm

In this paper, we propose a Gaussian distribution dynamic freeway segmentation algorithm according to the traffic speed on the freeways. The proposed algorithm adopts a two-stage policy, in the first stage, we divide the freeway into equal length segments via some fixed static standard, e.g. 1000 meters per segment, and we calculate the average speed on each of them. In the second stage, we partition the segment obtained from first stage into two equal parts if the variance of its speeds is larger than predefine max-variance. And then we merge the approximate segments through a variance-based method. Finally, we do some experiments by using the real traffic flow data, the results show our algorithm promise.