ZHAO Shu-xu, WU Hong-wei, LIU Chang-rong
（School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China）
Abstract： In order to alleviate urban traffic congestion and provide fast vehicle paths, a hidden Markov model (HMM) based on multi-feature data of urban regional roads is constructed to solve the problems of low recognition rate and poor instability of traditional model algorithms. At first, the HHM is obtained by training. Then according to dynamic planning principle, the traffic states of intersections are obtained by the Viterbi algorithm. Finally, the optimal path is selected based on the obtained traffic states of intersections. The experiment results show that the proposed method is superior to other algorithms in road unobstruction rate and recognition rate under complex road conditions.
Key words： hidden Markov model (HMM) ； Viterbi algorithm； traffic congestion； optimal path
CLD number： TP391.4 doi： 10.3969/j.issn.1674-8042.2020.04.006
References
［1］Hennon T D, Riser S C, Alford M H. Observations of internal gravity waves by argo floats. Journal of Physical Oceanography, 2014, 44(9)： 2370-2386.
［2］Kubryakov A A, Bagaev A V, Stanichny S V, et al. Thermohaline structure, transport and evolution of the Black Sea eddies from hydrological and satellite data, Progress in Oceanography, 2018, 167 (6)： 44-63.
［3］Xu L, Li P, Xie S P, et al. Observing mesoscale eddy effects on mode-water subduction and transport in the North Pacific. Nature Communications, 2016, 7(10)： 105-115.
［4］D’Asaro E, Farmer D M, Osse J T. A Lagrangian float. Journal of Atmospheric and Oceanic Technology, 1996, 13(6)： 1230-1246.
［5］Le Reste S, Dutreuil V, André X, et al. “Deep-arvor”： A new profiling float to extend the argo observations down to 4000-m depth. Journal of Atmospheric and Oceanic Technology, 2016, 33(5)： 1039-1055.
［6］Barker L. Closed-loop buoyancy control for a coastal profiling float. MBARI International Reports, 2014, (8)： 1-15.
［7］McGilvray B, Roman C. Control system performance and efficiency for a mid-depth Lagrangian profiling float. In： Proceedings of Oceans 2010 IEEE, Sydney, 2010, 978(4)： 1-10.
［8］Smith R N, Huynh V T. Controlling buoyancy-driven profiling floats for applications in ocean observation. IEEE Journal of Oceanic Engineering, 2013, 39(3)： 571-586.
［9］Zhang H L, Li X F, Yang S B, er al. Dual closed-loop fuzzy PID depth control for deep-sea self-holding intelligent buoy. Information and Control, 2018, 48(2)： 202-208.
［10］Zhou Z H. Machine learning, Beijing： Tsinghua University Press, 2016： 319- 321.
［11］Li H. Statistical learning method. Beijing： Tsinghua University Press, 2012： 171-184.
基于隐马尔可夫模型的最优交通路径模式识别
赵庶旭， 伍宏伟， 刘昌荣
（兰州交通大学电子与信息工程学院，甘肃兰州 730070）
摘 要： 为了缓解当前城市交通拥堵压力、 提供最优车辆行驶路线， 针对传统模型算法稳定性不足以及识别率低等问题， 构建了基于城市区域道路多特征数据的隐马尔可夫模型。 首先， 通过训练得到隐马尔可夫模型； 然后， 根据动态规划原理， 采用维特比算法， 得到某个交叉口交通状态情形； 最后， 根据这些交叉路口的交通状况选出最优出行路径。 实验结果表明， 在复杂的道路交通环境下， 相比其他的求解最优路径的算法， 本文所提出的算法求解得到的路径在道路畅通率和识别率等方面性能更忧。
关键词： 隐马尔可夫模型； 维特比算法； 交通拥堵； 最优路径
引用格式： ZHAO Shu-xu, WU Hong-wei, LIU Chang-rong. Pattern recognition of optimal traffic path based on HMM. Journal of Measurement Science and Instrumentation, 2020, 11（4）： 351-357. ［doi： 10.3969／j.issn.1674-8042.2020.04.006］
[full text view]
