基于相空间重构的GQPSO-WNN短时交通流预测
|
摘要
交通流预测有助于减少交通拥堵和交通事故发生。在定量分析交通流变化过程的混沌特性以及可预测性基础上,提出一种基于相空间的GQPSO-WNN的混合预测模型。引入遗传算法,使用混合优化后的量子粒子群算法初始化小波神经网络的各项参数,克服网络因初始值设置不当造成无法收敛或陷入多个局部极小值的问题。由于神经网络输入的随机性,采用重新构建交通流时间序列的相空间技术,用重构后的数据作为输入样本。实验结果表明,与WNN、PSO-WNN预测模型相比,该模型可以更加准确预测交通流,算法收敛性也有明显提高。
Traffic flow prediction plays an important role in traffic congestion and accident control. The paper quantitatively analyzed the chaotic characteristics and predictability of traffic flow changes, and proposed a hybrid prediction model based on phase space GQPSO-WNN. We introduced genetic algorithm to initialize the parameters of the wavelet neural network by using the hybrid optimized quantum particle swarm algorithm, and it could overcome the problem that the network could not converge or fall into multiple local minimum values due to inappropriate initial settings. Due to the randomness of the neural network input, we used the phase space technique of reconstructing the traffic flow time series, and the reconstructed data was used as the input samples. The experimental results show that, compared with the WNN and PSO-WNN prediction models, the model can predict traffic flow more accurately, and the convergence of the algorithm is also significantly improved.
Traffic flow prediction plays an important role in traffic congestion and accident control. The paper quantitatively analyzed the chaotic characteristics and predictability of traffic flow changes, and proposed a hybrid prediction model based on phase space GQPSO-WNN. We introduced genetic algorithm to initialize the parameters of the wavelet neural network by using the hybrid optimized quantum particle swarm algorithm, and it could overcome the problem that the network could not converge or fall into multiple local minimum values due to inappropriate initial settings. Due to the randomness of the neural network input, we used the phase space technique of reconstructing the traffic flow time series, and the reconstructed data was used as the input samples. The experimental results show that, compared with the WNN and PSO-WNN prediction models, the model can predict traffic flow more accurately, and the convergence of the algorithm is also significantly improved.
引文
[1] Smith B L,Demetsky M J.Traffic Flow Forecasting:Comparison of Modeling Approaches[J].Journal of Transportation Engineering,1997,123(4):262-266.
[2] 尚宁,覃明贵,王亚琴,等.基于BP神经网络的路口短时交通流量预测方法[J].计算机应用与软件,2006,23(2):32-33,57.
[3] 罗向龙,焦琴琴,牛力瑶,等.基于深度学习的短时交通流预测 [J].计算机应用研究,2017,34(1):91-93,97.
[4] 李松,刘力军,翟曼.改进粒子群算法优化 BP 神经网络的短时交通流预测[J].系统工程理论与实践,2012,32(9):2045-2049.
[5] 王小川.MATLAB神经网络43个案例分析[M].北京航空航天大学出版社,2013.
[6] 黄晓慧,张翠芳.布谷鸟算法优化小波神经网络的短时交通流预测[J].计算机应用与软件,2017,34(3):238-242.
[7] 金玉婷,余立建.基于小波神经网络的短时交通流预测[J].交通科技与经济,2014,16(1):82-86.
[8] Packard N H,Crutchfield J P,Farmer J D,et al.Geometry from a Time Series[J].Physical Review Letters,1980,45(9):712-716.
[9] Takens F.Determing strange attractors in turbulence[J].Lecture Notes in Mathematics,1980,898:366-381.
[10] 臧利林,贾磊,杨立才,等.交通流实时预测的混沌时间序列模型[J].中国公路学报,2007,20(6):95-99.
[11] 吕金虎,陆君安,陈士华.混沌时间序列预测与应用[M].武汉:武汉大学出版,2002.
[12] Brock W A,Hsieh D A,LeBaron B.Nonlinear Dynamic,Chaos,and Instability:Statistical Theory and Economic Evidence[J].Journal of Economic Literature,1993,31(1)232-234.
[13] Casdagli M.Nonlinear prediction of chaotic time series[J].Physica D:Nonlinear Phenomena,1989,35(3):335-356.
[14] Rosenstein M T,Collins J J,De Luca C J.Rosenstein M T.A practical method for calculating largest Lyapunov exponents from small data sets[J].Physica D:Nonlinear Phenomena,1993,65(1/2):117-134.
[15] 董虎胜,陆萍,龚声蓉.具有学习行为的协同量子粒子群算法[J].计算机应用研究,2014,31(9):2588-2591.
[16] Kennedy J,Eberhart R C.Particle swarm optimiza-tion[C]// Proceedings of IEEE International Conference on Neural Networks,1995.
[17] 朱建锋,陈汉武.基于交叉的量子粒子群算法[C]//东南大学学术论坛,2014.
[2] 尚宁,覃明贵,王亚琴,等.基于BP神经网络的路口短时交通流量预测方法[J].计算机应用与软件,2006,23(2):32-33,57.
[3] 罗向龙,焦琴琴,牛力瑶,等.基于深度学习的短时交通流预测 [J].计算机应用研究,2017,34(1):91-93,97.
[4] 李松,刘力军,翟曼.改进粒子群算法优化 BP 神经网络的短时交通流预测[J].系统工程理论与实践,2012,32(9):2045-2049.
[5] 王小川.MATLAB神经网络43个案例分析[M].北京航空航天大学出版社,2013.
[6] 黄晓慧,张翠芳.布谷鸟算法优化小波神经网络的短时交通流预测[J].计算机应用与软件,2017,34(3):238-242.
[7] 金玉婷,余立建.基于小波神经网络的短时交通流预测[J].交通科技与经济,2014,16(1):82-86.
[8] Packard N H,Crutchfield J P,Farmer J D,et al.Geometry from a Time Series[J].Physical Review Letters,1980,45(9):712-716.
[9] Takens F.Determing strange attractors in turbulence[J].Lecture Notes in Mathematics,1980,898:366-381.
[10] 臧利林,贾磊,杨立才,等.交通流实时预测的混沌时间序列模型[J].中国公路学报,2007,20(6):95-99.
[11] 吕金虎,陆君安,陈士华.混沌时间序列预测与应用[M].武汉:武汉大学出版,2002.
[12] Brock W A,Hsieh D A,LeBaron B.Nonlinear Dynamic,Chaos,and Instability:Statistical Theory and Economic Evidence[J].Journal of Economic Literature,1993,31(1)232-234.
[13] Casdagli M.Nonlinear prediction of chaotic time series[J].Physica D:Nonlinear Phenomena,1989,35(3):335-356.
[14] Rosenstein M T,Collins J J,De Luca C J.Rosenstein M T.A practical method for calculating largest Lyapunov exponents from small data sets[J].Physica D:Nonlinear Phenomena,1993,65(1/2):117-134.
[15] 董虎胜,陆萍,龚声蓉.具有学习行为的协同量子粒子群算法[J].计算机应用研究,2014,31(9):2588-2591.
[16] Kennedy J,Eberhart R C.Particle swarm optimiza-tion[C]// Proceedings of IEEE International Conference on Neural Networks,1995.
[17] 朱建锋,陈汉武.基于交叉的量子粒子群算法[C]//东南大学学术论坛,2014.