01334553

Component

Accurate short-term prediction of traffic condition on freeways and major arterials has become increasingly important because of its vital role in traffic management functions and various trip-making decisions. Given the dynamic nature of freeway traffic, this study proposed a stochastic approach, Hidden Markov Model (HMM), for short-term freeway traffic prediction during peak periods. The data used in the study was real world traffic monitoring data gathered over 6 years on the 38-mile segment of I-4 in Orlando, Florida. The HMM defines traffic states in a two-dimensional space using both first-order statistics (mean) and second-order statistics (contrast) of speed, and addresses the dynamic aspect of freeway traffic with state transition probabilities. For a sequence of traffic speed observations, the HMMs estimated the most likely corresponding traffic states sequence. Relatively small prediction errors were obtained, and the model performance was slightly affected by location, travel direction, and peak period time. The study concluded that the HMM approach is able to account for the stochastic nature of traffic conditions, and therefore, is appropriate for short-term traffic condition prediction during peak periods.

01329018

11-1439

English

19p

2011

Transportation Research Board 90th Annual Meeting

DVD

Figures (5) ; References (26) ; Tables (2)

Data collection; Freeway operations; Peak hour traffic; Stochastic processes; Traffic forecasting; Traffic speed; Trip purpose

Hidden Markov models; Real world traffic; Traffic state estimation; Transition probabilities

Orlando (Florida)

Highways; Operations and Traffic Management; Planning and Forecasting; I72: Traffic and Transport Planning

Transportation Research Board Annual Meeting 2011 Paper #11-1439

TRIS, TRB

Feb 17 2011 5:48PM