ANN-Based Prediction of Turning Rate of Traffic Flows at Intersection
-
摘要: 为了预测路口交通信号控制所需的转向交通流量,提出了基于改进BP(back-propagation)神经网络的路口交通流转向比预测模型,给出了相应参数的计算方法;采用自适应学习率和动量梯度下降法以提高神经网络的学习速度和算法的可靠性,并用调查数据对模型进行了检验.研究结果表明,与传统的平均值法相比,用所提出的模型,平均绝对相对误差减小约1%~3%.Abstract: Based on an improved back-propagation neural network,a predication model for the turning rate of traffic flows at intersections was proposed to predict traffic flows for the signal control of intersections.The corresponding method to determine necessary parameters in this model was given.To improve the learning rate and reliability of neural network algorithms,the self-adaptive learning rate approach and the gradient descent with momentum method were adopted.In addition,a simulation was carried out to prove the correctness of the proposed model.The research result shows that compared with the average value method,the proposed model can decrease the mean absolute relative error by 1%~3%.
-
Key words:
- traffic turning rate /
- prediction model /
- neural network /
- self-adaptive learning rate
-
NIHAN N L,DAVIS G A.Recursive estimation of origin-destination matrices from input/output counts[J].Transportation Research,Part B,1987,21(2):149-163.[2] BELL M G H.The real time estimation of origin-destination flows in the presence of platoon dispersion[J].Transportation Research,Part B,1991,25(2):115-125.[3] 王炜,徐吉谦.城市交通规划理论与方法[M].北京:人民交通出版社,1993:8-23.[4] 史艳华.道路交叉口转向流量浅析[J].有色冶金设计与研究,1997,12:17-19.[5] MIRCHANDANI P B,HEAD K L.A Real-time traffic signal control system:architecture algorithm and analysis[J].Transportation Research Part C,2001,9(6):415-432.[6] YANG H,AKIYAMA T,SASAKI A T.A neural network approach to the identification of real time origin-destination from traffic counts[C] //Proceedings of the International Conference on Artificial Intelligence Application in Transportation Engineering,San Buenaventura,1992:253-269.[7] 何志宏.模糊类神经适应性网路号志控制模式之研究[R].台南市:国立成功大学,1995.[8] 李瑞敏.城市交通信号控制系统相关理论模型研究及软件开发[D].北京:清华大学,2005.[9] 董菁,张毅,张佐,等.基于主成分分析法的城市交通路口相关性分析[J].西南交通大学学报,2003,38(6):619.622.DONG Jing,ZHANG Yi,ZHANG Zuo,et al.Principal component analysis of dependency of urban intersections[J].Journal of Southwest Jiaotong University,2003,38(6):619-622.[10] 闻新,周露,李翔,等.MATLAB神经网络仿真与应用[M].北京:科学出版社,2003:86-106. -
点击查看大图
计量
- 文章访问数: 1676
- HTML全文浏览量: 79
- PDF下载量: 327
- 被引次数: 0
下载: