基于深度学习的网约车供需缺口短时预测研究
|
摘要
城市不同区域网约车供需缺口预测可为车辆调度策略提供支持,从而提高车辆运行效率和乘客服务水平.为实现网约车供需缺口短时预测,提出一种基于时空数据挖掘的深度学习预测模型(Spatio-Temporal Deep Learning Model, S-TDL).该模型由时空变量模型、空间属性变量模型和环境变量模型3个子模型融合而成,可捕捉时空关联性、区域差异性和环境变化对供需缺口的影响.同时,提出特征聚类—最大信息系数两阶段特征选择方法,筛选与供需缺口相关性强的特征变量,提高训练效率,减少过拟合.滴滴出行实例分析证明,特征选择后的STDL模型预测精度显著优于BP神经网络、长短期记忆网络和卷积神经网络.
The results of supply-demand gap prediction for online car-hailing services in different areas can provide support for online car-hailing scheduling system, thereby improving efficiency and service levels. In order to realize the short-term forecast of supply-demand gap for online car-hailing services, this paper proposes a novel spatio-temporal deep learning model(S-TDL). The model is composed of three sub-models: spatiotemporal variable model, spatial attribute variable model and environment variable model. It can capture the impact of spatio-temporal correlation, regional difference and environmental change on supply-demand gap. Moreover, a feature selection method named feature clustering-maximum information coefficient two-stage feature selection is proposed to screen out the important features which are strongly correlated with the supply-demand gap, improve training efficiency. The experimental results show that the S-TDL model after feature selection achieves the better performance than the existing methods.
The results of supply-demand gap prediction for online car-hailing services in different areas can provide support for online car-hailing scheduling system, thereby improving efficiency and service levels. In order to realize the short-term forecast of supply-demand gap for online car-hailing services, this paper proposes a novel spatio-temporal deep learning model(S-TDL). The model is composed of three sub-models: spatiotemporal variable model, spatial attribute variable model and environment variable model. It can capture the impact of spatio-temporal correlation, regional difference and environmental change on supply-demand gap. Moreover, a feature selection method named feature clustering-maximum information coefficient two-stage feature selection is proposed to screen out the important features which are strongly correlated with the supply-demand gap, improve training efficiency. The experimental results show that the S-TDL model after feature selection achieves the better performance than the existing methods.
引文
[1] KE J, ZHENG H, YANG H, et al. Short-term forecasting of passenger demand under on-demand ride services:A spatio-temporal deep learning approach[J].Transportation Research Part C:Emerging Technologies, 2017(85):591-608.
[2] JAMIL M S, AKBAR S. Taxi passenger hotspot prediction using automatic ARIMA model[C]//Science in Information Technology(ICSITech), 2017 3rd International Conference on. IEEE, 2017.
[3] MOREIRA-MATIAS L, GAMA J, FERREIRA M, et al.Predicting taxi-passenger demand using streaming data[J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 14(3):1393-1402.
[4] LIU J, CUI E, HU H, et al. Short-term forecasting of emerging on-demand ride services[C]//Transportation Information and Safety(ICTIS), 2017 4th International Conference on. IEEE, 2017.
[5] LI Y, LU J, ZHANG L, et al. Taxi booking mobile app order demand prediction based on short-term traffic forecasting[J]. Transportation Research Record:Journal of the Transportation Research Board, 2017(2634):57-68.
[6] XU J, RAHMATIZADEH R, B?L?NI L, et al. A sequence learning model with recurrent neural networks for taxi demand prediction[C]//Local Computer Networks(LCN), 2017 IEEE 42nd Conference on.IEEE, 2017.
[7]段宗涛,张凯,杨云,等.基于深度CNN-LSTM-ResNet组合模型的出租车需求预测[J].交通运输系统工程与信息, 2018, 18(4):215-223.[DUAN Z T, ZHANG K,YANG Y, et al. Taxi demand prediction based on CNNLSTM-ResNet hybrid depth learning model[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(4):215-223.]
[8] ZHANG X, WANG X, CHEN W, et al. A Taxi gap prediction method via double ensemble gradient boosting decision tree[C]//IEEE, International Conference on Big Data Security on Cloud. IEEE, 2017.
[9] LI J, WANG Z. Online car-hailing dispatch:Deep supply-demand gap forecast on spark[C]//IEEE,International Conference on Big Data Analysis. IEEE,2017.
[10] WANG D, CAO W, LI J, et al. DeepSD:supply-demand prediction for online car-hailing services using deep neural networks[C]//2017 IEEE 33rd International Conference on Data Engineering(ICDE). IEEE, 2017.
[11] SHI X, CHEN Z, WANG H, et al. Convolutional LSTM network:A machine learning approach for precipitation nowcasting[C]//Advances in Neural Information Processing Systems, 2015.
[12]国家质量监督检验检疫总局. GB3095-2012环境空气质量标准[S].北京:中国环境科学出版社,2012.[General Administration of Quality Supervision,Inspection and Quarantine of the People's Republic of China. GB3095-2012 Ambient Air Quality Standard[S]. Beijing:China Environmental Science Press, 2012.]
[2] JAMIL M S, AKBAR S. Taxi passenger hotspot prediction using automatic ARIMA model[C]//Science in Information Technology(ICSITech), 2017 3rd International Conference on. IEEE, 2017.
[3] MOREIRA-MATIAS L, GAMA J, FERREIRA M, et al.Predicting taxi-passenger demand using streaming data[J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 14(3):1393-1402.
[4] LIU J, CUI E, HU H, et al. Short-term forecasting of emerging on-demand ride services[C]//Transportation Information and Safety(ICTIS), 2017 4th International Conference on. IEEE, 2017.
[5] LI Y, LU J, ZHANG L, et al. Taxi booking mobile app order demand prediction based on short-term traffic forecasting[J]. Transportation Research Record:Journal of the Transportation Research Board, 2017(2634):57-68.
[6] XU J, RAHMATIZADEH R, B?L?NI L, et al. A sequence learning model with recurrent neural networks for taxi demand prediction[C]//Local Computer Networks(LCN), 2017 IEEE 42nd Conference on.IEEE, 2017.
[7]段宗涛,张凯,杨云,等.基于深度CNN-LSTM-ResNet组合模型的出租车需求预测[J].交通运输系统工程与信息, 2018, 18(4):215-223.[DUAN Z T, ZHANG K,YANG Y, et al. Taxi demand prediction based on CNNLSTM-ResNet hybrid depth learning model[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(4):215-223.]
[8] ZHANG X, WANG X, CHEN W, et al. A Taxi gap prediction method via double ensemble gradient boosting decision tree[C]//IEEE, International Conference on Big Data Security on Cloud. IEEE, 2017.
[9] LI J, WANG Z. Online car-hailing dispatch:Deep supply-demand gap forecast on spark[C]//IEEE,International Conference on Big Data Analysis. IEEE,2017.
[10] WANG D, CAO W, LI J, et al. DeepSD:supply-demand prediction for online car-hailing services using deep neural networks[C]//2017 IEEE 33rd International Conference on Data Engineering(ICDE). IEEE, 2017.
[11] SHI X, CHEN Z, WANG H, et al. Convolutional LSTM network:A machine learning approach for precipitation nowcasting[C]//Advances in Neural Information Processing Systems, 2015.
[12]国家质量监督检验检疫总局. GB3095-2012环境空气质量标准[S].北京:中国环境科学出版社,2012.[General Administration of Quality Supervision,Inspection and Quarantine of the People's Republic of China. GB3095-2012 Ambient Air Quality Standard[S]. Beijing:China Environmental Science Press, 2012.]