PREDICTING INTERSECTION QUEUE WITH NEURAL NETWORK MODELS

Abstract To capture the complex nature of intersection queue dynamics, this study has explored the use of neural network models with data from extensive simulation experiments. The proposed models, although lacking in mathematical elegance, are capable of providing the acceptable prediction accuracy (more than 90%) at 3 time-steps ahead. As each time-step is as short as 3 s, the resulting information on queue evolution is sufficiently detailed for both responsive signal control and intersection operations. To accommodate the differences in available surveillance systems, this study has also investigated the most suitable neural network structure for each proposed queue model with extensive exploratory analyses.

[1]  D. Smith.  Adaptive Response for Exponential Smoothing: Comparative System Analysis , 1974 .

[2]  P J Wong,et al.  IMPROVED CONTROL LOGIC FOR USE WITH COMPUTER-CONTROLLED TRAFFIC , 1977 .

[3]  John S. Baras,et al.  Discrete time point processes in urban traffic queue estimation , 1978 .

[4]  William S. Levine,et al.  ESTIMATION OF TRAFFIC FLOW PARAMETERS IN URBAN TRAFFIC NETWORKS , 1977 .

[5]  Denos C. Gazis,et al.  On-Line Estimation of Traffic Densities from Time-Series of Flow and Speed Data , 1971 .

[6]  Neil W. Polhemus.  Time series analysis of local fluctuations in traffic parameters , 1976 .

[7]  R. D. Bretherton,et al.  Recent enhancements to SCOOT-SCOOT Version 2.4 , 1990 .

[8]  Patrick K. Simpson,et al.  Artificial Neural Systems: Foundations, Paradigms, Applications, and Implementations , 1990 .

[9]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[10]  H. Nicholson,et al.  The prediction of traffic flow volumes based on spectral analysis , 1974 .

[11]  John B. Kreer.  FACTORS AFFECTING THE RELATIVE PERFORMANCE OF TRAFFIC RESPONSIVE AND TIME-OF-DAY TRAFFIC SIGNAL CONTROL , 1976 .

[12]  George Stephanopoulos,et al.  Modelling and analysis of traffic queue dynamics at signalized intersections , 1979 .

[13]  I Okutani,et al.  Dynamic prediction of traffic volume through Kalman Filtering , 1984 .

[14]  Jean-Loup Farges,et al.  THE PRODYN REAL TIME TRAFFIC ALGORITHM , 1983 .

[15]  R D Bretherton,et al.  SCOOT-a Traffic Responsive Method of Coordinating Signals , 1981 .

[16]  Gregory Stephanopoulos,et al.  Modeling of Traffic Flow at Signalized Links , 1980 .