PA mathematical prediction model of a large random, complex investigation fundamental data, which based on the traditional land-use patterns, population, income and other variables establish, has many deficiencies. Propose to establish a PA prediction model based on fuzzy optimization grey prediction theory. Adopt the algorithm which is a recursive estimation process time-series. It requires less priori data. And the process of the application software, data query, model calibration and testing of prediction accuracy was built. Based on the statistics of the toll station over the years, combine the result of model predictions to estimate the future for dynamic OD matrix. For a 10 OD pairs of the provincial freeway network, build the experimental platform which makes use of Trans CAD to establish in order to simulate and analyze. A large number of simulation results show that: compared with traditional models, both the relative error and absolute error of this method results are reduced.
Published in:
Intelligent Systems and Applications (ISA), 2010 2nd International Workshop on
Date of Conference: 22-23 May 2010