The highly non-linear characteristics of the freeway travel time prediction problem require a modeling approach that is capable of dealing with complex non-linear spatio-temporal relationships between the observable traffic quantities. Based on a state-space formulation of the travel time prediction problem, we derived a recurrent state-space neural network (SSNN) topology. The SSNN model is capable of accurately predicting experienced travel times - outperforming current practice by far - producing approximately zero mean normally distributed residuals, generally not outside a range of 10% of the real expected travel times. Furthermore, analyses of the internal states and the weight configurations revealed that the SSNN developed an internal models closely related to the underlying traffic processes. This allowed us to rationally eliminate the insignificant parameters, resulting in a Reduced SSNN topology, with just 63 adjustable weights, yielding a 72% reduction in model-size, without loss of predictive performance.
[1]
Serge P. Hoogendoorn,et al.
State-of-the-art of vehicular traffic flow modelling
,
2001
.
[2]
Jeffrey L. Elman,et al.
Finding Structure in Time
,
1990,
Cogn. Sci..
[3]
Ruey Long Cheu,et al.
FREEWAY TRAFFIC PREDICTION USING NEURAL NETWORKS
,
1998
.
[4]
Dongjoo Park,et al.
Forecasting Freeway Link Travel Times with a Multilayer Feedforward Neural Network
,
1999
.
[5]
R G Vermijs,et al.
EVALUATING CAPACITY OF FREEWAY WEAVING SECTIONS AND ON-RAMPS USIN THE MICROSCOPIC SIMULATION MODEL FOSIM
,
1994
.
[6]
Baher Abdulhai,et al.
Short Term Freeway Traffic Flow Prediction Using Genetically-Optimized Time-Delay-Based Neural Networks
,
1999
.