by Xu, Y, Kong, Q-J, Klette, R and Liu, Y
Abstract:
Current research on traffic flow prediction mainly concentrates on generating accurate prediction results based on intelligent or combined algorithms but ignores the interpretability of the prediction model. In practice, however, the interpretability of the model is equally important for traffic managers to realize which road segment in the road network will affect the future traffic state of the target segment in a specific time interval and when such an influence is expected to happen. In this paper, an interpretable and adaptable spatiotemporal Bayesian multivariate adaptive-regression splines (ST-BMARS) model is developed to predict short-term freeway traffic flow accurately. The parameters in the model are estimated in the way of Bayesian inference, and the optimal models are obtained using a Markov chain Monte Carlo (MCMC) simulation. In order to investigate the spatial relationship of the freeway traffic flow, all of the road segments on the freeway are taken into account for the traffic prediction of the target road segment. In our experiments, actual traffic data collected from a series of observation stations along freeway Interstate 205 in Portland, OR, USA, are used to evaluate the performance of the model. Experimental results indicate that the proposed interpretable ST-BMARS model is robust and can generate superior prediction accuracy in contrast with the temporal MARS model, the parametric model autoregressive integrated moving averaging (ARIMA), the state-of-The-Art seasonal ARIMA model, and the kernel method support vector regression.
Reference:
Accurate and interpretable Bayesian MARS for traffic flow prediction (Xu, Y, Kong, Q-J, Klette, R and Liu, Y), In IEEE Transactions on Intelligent Transportation Systems, Institute of Electrical and Electronics Engineers Inc., volume 15, 2014.
Bibtex Entry:
@article{xu2014accurateprediction,
author = "Xu, Y and Kong, Q-J and Klette, R and Liu, Y",
journal = "IEEE Transactions on Intelligent Transportation Systems",
month = "Dec",
pages = "2457--2469",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
title = "Accurate and interpretable Bayesian MARS for traffic flow prediction",
volume = "15",
year = "2014",
abstract = "Current research on traffic flow prediction mainly concentrates on generating accurate prediction results based on intelligent or combined algorithms but ignores the interpretability of the prediction model. In practice, however, the interpretability of the model is equally important for traffic managers to realize which road segment in the road network will affect the future traffic state of the target segment in a specific time interval and when such an influence is expected to happen. In this paper, an interpretable and adaptable spatiotemporal Bayesian multivariate adaptive-regression splines (ST-BMARS) model is developed to predict short-term freeway traffic flow accurately. The parameters in the model are estimated in the way of Bayesian inference, and the optimal models are obtained using a Markov chain Monte Carlo (MCMC) simulation. In order to investigate the spatial relationship of the freeway traffic flow, all of the road segments on the freeway are taken into account for the traffic prediction of the target road segment. In our experiments, actual traffic data collected from a series of observation stations along freeway Interstate 205 in Portland, OR, USA, are used to evaluate the performance of the model. Experimental results indicate that the proposed interpretable ST-BMARS model is robust and can generate superior prediction accuracy in contrast with the temporal MARS model, the parametric model autoregressive integrated moving averaging (ARIMA), the state-of-The-Art seasonal ARIMA model, and the kernel method support vector regression.",
doi = "10.1109/TITS.2014.2315794",
issn = "1524-9050",
issue = "6",
keyword = "Bayesian inference",
keyword = "interpretable model",
keyword = "Markov chain Monte Carlo (MCMC)",
keyword = "multivariate adaptive-regression splines (MARS)",
keyword = "spatiotemporal relationship analysis",
keyword = "traffic flow prediction",
language = "eng",
day = "1",
}