Short Term Traffic Flow Forecasting Using Bayesian Combined Neural Network Model
N.T. Makanjuola, O.O. Shoewu, Alao, W.A, Akinyemi, L.A, Akinyan A. R
Corresponding Author : O.O. Shoewu,
Department of Electronic and Computer Engineering, Lagos State University, Nigeria.
Email ID : firstname.lastname@example.org
Received : 2015-03-25 Accepted : 2015-03-27 Published : 2015-03-27
Abstract : In this Work, an artificial neural network model is introduced that combines the prediction from single neural network predictors according to an adaptive and heuristic credit assignment algorithm based on the theory of conditional probability and Bayesâ€™ rule. Two single predictors are applied and combined linearly into a Bayesian combined neural network model. The credit value for each predictor in the combined model is calculated according to the proposed credit assignment algorithm and largely depends on the accumulative prediction performance of these predictors during the previous prediction intervals. Three indices, i.e., the mean absolute percentage error (MAPE), the variance of absolute percentage error (VAPE), and the probability of percentage error (PPE), are employed to compare the forecasting performance. It is found that most of the time, the combined model outperforms the singular predictors.
Keywords : Back propagation neural network, Radial Basis Function Neural network, Bayesian Combined neural network model, credit value, MAPE, VAPE, PPE
Citation : O.O. Shoewu, et al. (2017). Short Term Traffic Flow Forecasting Using Bayesian Combined Neural Network Model. J. of Computation in Biosciences and Engineering. V3I3. DOI : 10.5281/zenodo.893481
Copyright : Â© 2017 O.O. Shoewu. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Journal of Computation in Biosciences and Engineering
ISSN : 2348-7321
Volume 3 / Issue 3
ScienceQ Publishing GroupDownload Article