© The Institution of Engineering and Technology
Urban travel time prediction has received much less attention than predictions on freeways, perhaps because urban travel times show much larger variations and are therefore much harder to predict. However, urban travel time can form a substantial part of the total travel time of a road user and therefore effort should be taken to predict urban travel times. In this study, neural networks are used for urban travel time prediction because these have shown to be able to deal with noisy data. Bayesian techniques are used for training of the networks, resulting in committees with lower error and in confidence bounds. It is shown that the neural network committees are capable of predicting the ‘low-frequency trend’, which can be seen when the high-frequency component of travel time is removed using de-noising. The errors of the predictions on the low-frequency trend are in the same order as when predicting freeway travel times, and it is shown that the predicted confidence bounds are accurate.
References
-
-
1)
-
van Hinsbergen, C.P.I., van Lint, J.W.C., Sanders, F.M.: `Short term traffic prediction models', Proc. 14th ITS World Congress, 2007, Beijing, China.
-
2)
-
S. Sardy ,
P. Tseng ,
A. Bruce
.
Robust wavelet denoising.
IEEE Trans. Signal Process.
,
6 ,
1146 -
1152
-
3)
-
J. Sietsma ,
R.J.F. Dow
.
Creating artificial neural networks that generalize.
Neural Netw.
,
1 ,
67 -
79
-
4)
-
M. Zhong ,
S. Sharma ,
P. Lingras
.
Refining genetically designed models for improved traffic prediction on rural roads.
Transp. Plan. Technol.
,
3 ,
213 -
236
-
5)
-
B.S. Kerner
.
(2004)
The physics of traffic.
-
6)
-
Neal, R.M.: `Bayesian learning for neural networks', 1994, PhD, , Toronto, Canada.
-
7)
-
van Zuylen, H.J., Zheng, F., Chen, Y.: `Using Probe vehicle data for traffic state estimation in signalized urban networks', Proc. Int. Workshop on Traffic Data Collection and its Standardisation, 2008, Barcelona, Spain.
-
8)
-
Zheng, F., van Zuylen, H.J.: `Uncertainty and predictability of urban link travel time: a delay distribution based analysis', Eighty-Ninth Annual Meeting of the Transportation Research Board, 2010, Washington, DC, USA.
-
9)
-
B.L. Smith ,
M.J. Demetsky
.
Multiple-interval freeway traffic flow forecasting.
Transp. Res. Rec.
,
136 -
141
-
10)
-
C.M. Bishop
.
(1995)
Neural networks for pattern recognition.
-
11)
-
S. Lee ,
D.B. Fambro
.
Application of subset autoregressive integrated moving average model for short-term freeway traffic volume forecasting.
Transp. Res. Rec.
,
179 -
188
-
12)
-
S. Innamaa
.
Short-term prediction of travel time using neural networks on an interurban highway.
Transportation
,
649 -
669
-
13)
-
C.P.I. van Hinsbergen ,
J.W.C. van Lint ,
H.J. van Zuylen
.
Bayesian committee of neural networks to predict travel times with confidence intervals.
Transp. Res. C, Emerg. Technol.
,
498 -
509
-
14)
-
I. Okutani ,
Y.J. Stephanedes
.
Dynamic prediction of traffic volume through Kalman filtering theory.
Transp. Res. B
,
1 ,
1 -
11
-
15)
-
Ben-Akiva, M., Cantarella, G., Cascetta, E., de Ruiter, J., Whittaker, J., Kroes, E.: `Real-time prediction of traffic congestion', The Third Int. Conf. on Vehicle Navigation and Information Systems, 1992, Oslo, Norway.
-
16)
-
C.P.I. van Hinsbergen ,
J.W.C. van Lint ,
H.J. van Zuylen
.
Bayesian training and committees of State-Space Neural Networks for online travel time prediction.
Transp. Res. Rec.
,
118 -
126
-
17)
-
Mark, C.D., Sadek, A.W., Rizzo, D.: `Predicting experienced travel time with neural networks: a PARAMICS simulation study', The Seventh Int. IEEE Conf. on Intelligent Transportation Systems, 2004, Washington, DC, USA.
-
18)
-
A. Procházka ,
M. Mudrová ,
M. Štorek ,
A. Procházka
.
(1998)
Wavelet use for noise rejection and signal modelling, Signal analysis and prediction.
-
19)
-
Viti, F.: `The dynamics and the uncertainy of delays at signals', 2006, PhD, , Delft, The Netherlands.
-
20)
-
D.J.C. MacKay
.
Probable networks and plausible predictions – a review of practical Bayesian methods for supervised neural networks.
Network, Comput. Neural Syst.
,
469 -
505
-
21)
-
A. Dharia ,
H. Adeli
.
Neural network model for rapid forecasting of freeway link travel time.
Eng. Appl. Artif. Intell.
,
607 -
613
-
22)
-
N.L. Nihan
.
Use of the Box and Jenkins time series technique in traffic forecasting.
Transportation
,
125 -
143
-
23)
-
H.H. Thodberg
.
(1993)
Ace of Bayes: application of neural networks with pruning.
-
24)
-
van Hinsbergen, C.P.I., van Lint, J.W.C., van Zuylen, H.J.: `Neural network committee to predict travel times: comparison of Bayesian evidence approach to the use of a validation set', Eleventh Int. IEEE Conf. on Intelligent Transportation Systems, 2008, Beijing, China.
-
25)
-
Yang, J.-S.: `Travel time prediction using the GPS test vehicle and Kalman filtering techniques', American Control Conf., 2005, Portland, Oregon, USA.
-
26)
-
H.M. Zhang
.
Recursive prediction of traffic conditions with neural network models.
J. Transp. Eng.
,
6 ,
472 -
481
-
27)
-
H. Xiong ,
G.A. Davis
.
Field evaluation of model-based estimation of arterial link travel times.
Transp. Res. Rec.: J. Transp. Res. Board
,
149 -
157
-
28)
-
D.L. Donoho ,
I.M. Johnstone
.
Ideal spatial adaptation via wavelet shrinkage.
Biometrica
,
435 -
455
-
29)
-
http://www.dsp.rice.edu/software/rice-wavelet-toolbox, accessed November 2009.
-
30)
-
Liu, H.: `Travel time prediction for urban networks', 2008, PhD, , Delft, The Netherlands.
-
31)
-
V. Petridis ,
A. Kehagias ,
L. Petrou
.
A Bayesian multiple models combination method for time series prediction.
J. Intell. Robot. Syst.
,
69 -
89
-
32)
-
C.P.I. van Hinsbergen ,
J.W.C. van Lint
.
Bayesian combination of travel time prediction models.
Transp. Res. Rec.
,
73 -
80
-
33)
-
S. Clark
.
Traffic prediction using multivariate nonparametric regression.
J. Transp. Eng.
,
2 ,
161 -
168
-
34)
-
C.M. Kuchipudi ,
S.I.J. Chien
.
Development of a hybrid model for dynamic travel-time prediction.
Transp. Res. Rec.
,
22 -
31
-
35)
-
J.W.C. van Lint ,
S.P. Hoogendoorn ,
H.J. van Zuylen
.
Accurate travel time prediction with state-space neural networks under missing data.
Transp. Res. C, Emerg. Technol.
,
347 -
369
-
36)
-
M.S. Dougherty ,
M.R. Cobbett
.
Short-term inter-urban traffic forecasts using neural networks.
Int. J. Forecast.
,
21 -
31
-
37)
-
C.G. Chua ,
A.T.C. Goh
.
A hybrid Bayesian back-propagation neural network approach to multivariate modelling.
Int. J. Numer. Anal. Methods Geomech.
,
8 ,
651 -
667
-
38)
-
Nikovski, D., Nishiuma, N., Goto, Y., Kumazawa, H.: `Univariate short-term prediction of road travel times', Eighth Int. IEEE Conf. on Intelligent Transportation Systems, 2005, Vienna, Austria.
-
39)
-
W. Zheng ,
D. Lee ,
Q. Shi
.
Short-term freeway traffic flow prediction: Bayesian combined neural network approach.
J. Transp. Eng.
,
2 ,
114 -
121
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2009.0114
Related content
content/journals/10.1049/iet-its.2009.0114
pub_keyword,iet_inspecKeyword,pub_concept
6
6