Intelligent Dynamic Estimation of Traffic Light Time Based on TAN Classifier

doi:10.3969/j.issn.1006-2475.2019.11.016

Abstract

Abstract: Aiming at the problem that traffic lights are weak in intelligence and easy to cause traffic jam, a time intelligent dynamic estimation method for traffic lights based on TAN classifier is proposed. Firstly, this paper analyzes the main factors which affect the traffic light time, and discretizes the collected data by fuzzy classification function. Then, it learns the structure of the TAN classifier by K2 algorithm. Next, it learns the parameters of TAN classifier with maximum likelihood estimation. Finally, the best traffic light time is estimated online by forwards-backwards algorithm based on the sliding window. The experimental simulation shows that the proposed method can dynamically estimate the optimal traffic light time according to real-time traffic information. When the traffic light is free, the traffic light time is short, otherwise, time is long. It is effective to alleviate traffic jam and reduce environment pollution.

Key words: intelligent transportation, dynamic estimation, dynamic Bayesian networks, TAN classifier, sliding window

CLC Number:

TP181

CHEN Hai-yang1, HUAN Xiao-min1, CHEN Xin-zhan2, LIU Xi-qing1. Intelligent Dynamic Estimation of Traffic Light Time Based on TAN Classifier[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2019.11.016.

References

［1］ YANG C H. Research on construction of digital Intelligent city management system［J］. International Journal of Hybrid Information Technology, 2014,7(5):285-294.
［2］ ZHAO D B, DAI Y J, ZHANG Z. Computational intelligence in urban traffic signal control: A survey［J］. IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications and Reviews, 2012,42(4):485-494.
［3］ ZHANG L D, ZHU W X. Delay-feedback control strategy for reducing［J］. Physica A: Statistical Mechanics and Its Applications, 2015,428:481-492.
［4］ HUANG Y S, WENG Y S, ZHOU M C. Design of regulatory traffic light control systems with synchronized timed Petri nets［J］. Asian Journal of Control, 2018,20(5):174-185.
［5］ COLLOTTA M, PAU G. New solutions based on wireless networks for dynamic traffic lights management: A comparison between IEEE 802.15.4 and Bluetooth［J］. Transport and Telecommunication Journal, 2015,16(3):224-236.
［6］ LEAL S S, DE ALMEIDA P E M, CHUNG E. Active control for traffic lights in regions and corridors: An approach based on evolutionary computation［J］. Transportation Research Procedia, 2017,25:1769-1780.
［7］吴黎兵,聂雷,刘冰艺,等. 一种VANET环境下的智能交通信号控制方法［J］. 计算机学报, 2016,39(6):1105-1119.
［8］ COOPER B G F, HERSOVITS E. A Bayesian method for the induction of probabilistic networks from data［J］. Machine Learning， 1992,9(4):309-347．
［9］ ROCCHETTA R, BROGGI M, HUCHET Q, et al. On-line Bayesian model updating for structural health monitoring［J］. Mechanical Systems and Signal Processing, 2018,103(3):174-195.
［10］陈龙,马亚平. 基于分层贝叶斯网络的航母编队对潜威胁评估［J］. 系统仿真学报, 2017,29(9):2206-2212.
［11］邢志伟,蒋骏贤,罗晓,等. 基于贝叶斯网的离港航班滑行时间动态估计［J］. 计算机工程与应用, 2018,54(24):66-71.
［12］惠飞,穆柯楠,赵祥模. 基于动态概率网格和贝叶斯决策网络的车辆变道辅助驾驶决策方法［J］. 交通运输工程学报, 2018,18(2):148-158.
［13］吕学志,胡晓峰,吴琳,等. 基于贝叶斯网络的任务共同体识别［J］. 计算机工程与应用, 2019,55(5):251-257.
［14］KOLLER D, FRIEDMAN N. Probabilistic Graphical Models［M］. Cambridge, MIT Press, 2009:184-201.
［15］FIREDMAN N, GEIGER D, GOLDSZMIDT M. Bayesian network classifiers［J］. Machine Learning, 1997,29(2/3):131-163.
［16］张连文,郭海鹏. 贝叶斯网引论［M］. 北京:科学出版社, 2006:61-62.
［17］齐伟钢,彭凝多,黄慧萍. 基于静态贝叶斯博弈的SCADA系统安防策略选择［J］. 通信技术, 2017,50(9):2037-2044.
［18］仝兆景,张艳杰,赵运星,等. 基于动态贝叶斯网络的装甲车辆前向防撞预警模型［J］. 制造业自动化, 2019,41(2):114-116.
［19］李文广,孙世宇,李建增,等. 无人机航迹规划中动态威胁评估方法［J］. 火力与指挥控制, 2019,44(2):50-53.
［20］戴志辉,谢军,陈曦,等. 基于动态贝叶斯网络的智能变电站监控系统可靠性分析［J］. 电力系统保护与控制, 2018,46(23):68-76.
［21］RUSSELL S J, NORVIG P. Artificial Intelligence: A Modern Approach［M］. Prentice Hall, 1995.
［22］CHEN H Y, NIE H Y, MAO R R. A new inference of dynamic Bayesian networks: Forwards-backwards algorithm based on sliding window［J］. Journal of Computational Information Systems, 2015,11(9):3371-3378.
［23］GAO X G, MEI J F, CHEN H Y, et al. Approximate inference for dynamic Bayesian networks: Sliding window approach［J］. Applied Intelligence, 2014,40(4):575-591.

[1]	WU Jian-bo, ZHU Wen-xia, JU Liang, XU Zhi-fang. Application of Edge Computing in Intelligent Transportation Systems [J]. Computer and Modernization, 2021, 0(12): 103-109.
[2]	WANG Zeng-guang, WANG Hai-qi, CHEN Hai-bo. Short-term Traffic Speed Prediction Based on Graph Convolutional Network [J]. Computer and Modernization, 2021, 0(09): 99-105.
[3]	ZHANG Heng, JU Shi-guang. Network Data Stream Classification Based on Concept Drift Detection [J]. Computer and Modernization, 2021, 0(07): 107-114.
[4]	LI Yan-mei1, YIN Xin-chun1,2,SHAO Meng-li2. Multi-scalar Multiplication Algorithm for Elliptic Curve Based on MBNS and Sliding Window [J]. Computer and Modernization, 2019, 0(01): 11-.
[5]	QU Fu-ping;WANG Kao-jie;L Yu-hua. An Algorithm for Construction of Synopses over Data Stream Based on Sliding Windows [J]. Computer and Modernization, 2013, 1(3): 17-21.
[6]	WAN Ying;LIN Yi;YOU Hong-tao. Optimization of Sliding Window Technology in Continuous Data Protection [J]. Computer and Modernization, 2012, 208(12): 189-192,.
[7]	YANG Guang-nian;YAN Xiao-hong;LIU Yei;YUAN Qi-chuan. Design of Intelligent Traffic Guidance System Based on Virtual Instrument Technology [J]. Computer and Modernization, 2011, 193(9): 116-118,.
[8]	ZHENG Hong-dong;ZHOU Ya-feng;MAO Min. Inter Cell Handover Algorithms Based on Movement Speed of UE in TD-SCDMA System [J]. Computer and Modernization, 2010, 1(6): 126-0129.
[9]	LI Shu;BAI Xing-zhen. Hybrid Petri NetBased Performance Analysis for Urban Transportation Networks [J]. Computer and Modernization, 2009, 169(9): 45-47.