Page 101 - 《软件学报》2020年第12期

柏梦婷 等:行程时间预测方法研究 3767

保证一定的准确率.数据驱动方法适用于高速公路上的行程时间预测,在城区道路上的行程时间预测的相关研
究较少.数据驱动方法的共同优势在于直接从数据中挖掘模式,不需要交通流建模方面的知识.大多数的数据驱
动方法能够对非线性、高维的数据进行时间和空间特征处理,具有一定的泛化能力、自适应能力和容错能力.
然而,数据驱动方法大都具有较多参数,计算量大,需要花费较长时间训练模型,且需要在准确率和模型复杂度
之间寻求折中.缺乏可解释性也是大多数数据驱动方法的缺点.只有少数的数据驱动方法如 k-NN 和 SSNN 以及
集成学习方法具有一定的可解释性.
本文指出了行程时间的未来研究方向以及现存的行程时间预测方法中存在的问题的一些可能的解决方
案.此外,本文提出了一种新的数据处理框架和行程时间预测模型.虽然针对行程时间预测问题已经存在大量的
研究,但高效准确的预测方法的研究仍具有重要意义.

References:
[1] Mahmassani, HS, Peeta S. System optimal dynamic assignment for electronic route guidance in a congested traffic network. In:
Proc. of the Urban Traffic Networks: Dynamic Flow Modeling and Control. Berlin, Heidelberg: Springer-Verlag, 1995. 3−37.
[2] Ho FS, Ioannou P. Traffic flow modeling and control using artificial neural networks. IEEE Control Systems Magazine, 1996,16(5):
16−26.
[3] Chabini, Ismail. Discrete dynamic shortest path problems in transportation applications: Complexity and algorithms with optimal
run time. Transportation Research Record: Journal of the Transportation Research Board, 1998,1645:170−175.
[4] Stephanedes YJ, Chassiakos AP. Freeway incident detection through filtering. Transportation Research Part C (Emerging
Technologies), 1993,1(3):219−233.
[5] Figueiredo L, Jesus I, Machado JAT, Ferreira JR, Carvalho JLMD. Towards the development of intelligent transportation systems.
In: Proc. of the Intelligent Transportation Systems. IEEE, 2001. 1206−1211.
[6] Zhang J, Wang FY, Wang K, Lin WH, Xu X, Chen C. Data-Driven intelligent transportation systems: A survey. IEEE Trans. on
Intelligent Transportation Systems, 2011,12(4):1624−1639.
[7] Khattak AJ, Targa F, Yim Y. Advanced Traveler Information Systems. 2004.
[8] Heathington KW. On the development of a freeway driver information system. In: Proc. of the Real Time Information. 1969.
[9] Zhang Y, Haghani A. A gradient boosting method to improve travel time prediction. Transportation Research Part C: Emerging
Technologies, 2015,58:308−324.
[10] Wisitpongphan N, Jitsakul W, Jieamumporn D. Travel time prediction using multi-layer feed forward artificial neural network. In:
Proc. of the 4th Int’l Conf. on Computational Intelligence. IEEE, 2012. 326−330.
[11] Chen H, Rakha HA. Multi-Step prediction of experienced travel times using agent-based modeling. Transportation Research Part C:
Emerging Technologies, 2016,71:108−121.
[12] Wei CH, Lee Y. Development of freeway travel time forecasting models by integrating different sources of traffic data. IEEE Trans.
on Vehicular Technology, 2007,56(6):3682−3694.
[13] Yeon J, Elefteriadou L, Lawphongpanich S. Travel time estimation on a freeway using discrete time Markov chains. Transportation
Research Part B: Methodological, 2008,42(4):325−338.
[14] Chrobok R, Hafstein SF, Pottmeier A. OLSIM: A new generation of traffic information systems. Journal of Information Science &
Technology, 2013,3(2):883−886.
[15] Messmer A, Papageorgiou M. METANET: A macroscopic simulation program for motorway networks. Traffic Engineering and
Control, 1990,31(8):466−470.
[16] Oh S, Byon YJ, Jang K, Yeo H. Short-Term travel-time prediction on highway: A review on model-based approach. KSCE Journal
of Civil Engineering, 2018,22(1):298−310.
[17] Takaba S, Morita T, Hada T, Usami T. Estimation and measurement of travel time by vehicle detectors and license plate readers. In:
Proc. of the Vehicle Navigation and Information Systems Conf. 1991. 257−267.
[18] Daganzo C. The Cell Transmission Model. Part I: A Simple Dynamic Representation of Highway Traffic. 1992. 288.
[19] Chrobok R. Theory and Application of Advanced Traffic Forecast Methods. 2005.