A multiple sources and multiple measures based traffic flow prediction algorithm using the chaos theory and support vector regression method is proposed.

The chaotic characteristics of traffic flow associated with the speed, occupancy, and flow are identified using the maximum Lyapunov exponent.

The phase space of multiple measures chaotic time series are reconstructed based on the phase space reconstruction theory.

The support vector regression (SVR) model is designed to predict the traffic flow.

Results show that the proposed method has better performance in terms of the accuracy and timeliness.