版主 (文坛精英)
有尾巴的青蛙 ![]()
|
★
Flexing(金币+2, 博学EPI+1):谢谢 2010-04-30 11:19
YUE-jf(金币+1):你是怎么查到的呢？ 2010-04-30 11:40
Predicting urban arterial travel time with state-space neural networks and Kalman filters
SCI检索号为： ISI:000245460800012
FN ISI Export Format
VR 1.0
PT S
AU Liu, H
van Zuylen, H
van Lint, H
Salomons, M
AF Liu, Hao
van Zuylen, Henk
van Lint, Hans
Salomons, Maria
GP Natl Acad, TRB
TI Predicting urban arterial travel time with state-space neural networks and Kalman filters
SO ARTIFICIAL INTELLIGENCE AND ADVANCED COMPUTING APPLICATIONS
SE TRANSPORTATION RESEARCH RECORD
LA English
DT Proceedings Paper
CT 85th Annual Meeting of the Transportation-Research-Board
CY JAN 22-26, 2006
CL Washington, DC
SP Transportat Res Board
ID REAL-TIME; PERFORMANCE
AB A hybrid model for predicting urban arterial travel time on the basis of so-called state-space neural networks (SSNNs) and the extended Kalman filter (EKF) is presented. Previous research demonstrated that SSNNs can address complex nonlinear spatiotemporal problems. However, SSNN models require off-line training with large sets of input-output data, presenting three main drawbacks: (a) great amounts of time and effort are involved in collecting, preparing, and executing these training sessions; (b) as the input-output mapping changes over time, the model requires complete retraining; and (c) if a different input set becomes available (e.g., from inductive loops) and the input-output mapping has to be changed, then retraining the model is impossible until enough time has passed to compose a representative training data set. To improve SSNN effectiveness, the EKF is proposed to train the SSNN instead of conventional approaches. Moreover, this network topology is derived from the urban travel time prediction problem. Instead of treating the neural network as a "black-box" model, the design explicitly reflects the relationships that exist in physical traffic systems. It allows the interpretation of neuron weights and structure in terms of the inherent mechanism of the network process with clear physical meaning. Model performance was tested on a densely used urban arterial in the Netherlands. Performance of this proposed model is compared with that of two existing models. Results of the comparisons indicate that the proposed model predicts complex nonlinear urban arterial travel times with satisfying effectiveness, robustness, and reliability.
C1 Delft Univ Technol, Fac Civil Engn & Geosci, NL-2600 GA Delft, Netherlands.
Natl ITS Ctr Engn & Technol, Beijing 100088, Peoples R China.
RP Liu, H, Delft Univ Technol, Fac Civil Engn & Geosci, POB 5048, NL-2600 GA Delft, Netherlands.
NR 22
TC 1
PU NATL ACAD SCI
PI WASHINGTON
PA 2101 CONSTITUTION AVE, WASHINGTON, DC 20418 USA
SN 0361-1981
BN 978-0-309-09977-6
J9 TRANSP RES REC
PY 2006
IS 1968
BP 99
EP 108
PG 10
SC Engineering, Civil; Transportation; Transportation Science & Technology
GA BFY64
UT ISI:000245460800012
ER
[ Last edited by qfw_68 on 2010-4-30 at 11:03 ] |
|
回复此楼