Passenger flow forecasting of airport express based on time and feature cooperative attention
-
摘要:
机场快轨客流的准确预测是实现机场轨道交通系统智能化、精细化、高效化管控的基础,对提升机场服务水平和运行效率有着重要意义。由于影响因素众多、相互耦合,且因素对客流时序影响机理复杂,机场快轨客流的准确预测极具挑战。提出了一种基于“时间-特征”协同注意力机制的机场快轨客流预测模型,实现了精准捕捉多维因素在不同时序上对机场快轨客流的影响。基于北京首都国际机场快轨实际客流数据进行实验,结果表明了所提方法的有效性。
-
关键词:
- 机场快轨 /
- 时间序列 /
- 客流预测 /
- “时间-特征”协同注意力 /
- 长短时记忆网络
Abstract:Accurate prediction of passenger flow of airport express rail is the basis for realizing intelligent, refined and efficient control of airport rail transit system. And it is of great significance to improve airport service levels and operational efficiency. The correct prediction of airport express rail passenger flow is particularly difficult due to the complex interplay of multiple factors that influence passenger flow in complicated ways. In this paper, an airport express passenger flow prediction model based on time and feature cooperative attention mechanism is proposed to accurately capture the influence degree of multi-dimensional factors on express passenger flow in different time series. Based on the actual passenger flow data of Beijing Capital International Airport, the experiment results show that the proposed method is effective.
-
表 1 机场快轨客流预测性能
Table 1. Forecasting performance of airport express rail passenger flow
客流方向 预测模型 MSE MAE 机场→市区 BPNN 112.245 8.81 SVR 107.72 8.90 ARIMA 101.89 7.89 LSTM 105.35 8.11 TFATT 96.94 7.67 市区→机场 BPNN 129.95 8.16 SVR 128.06 8.22 ARIMA 127.89 8.49 LSTM 132.22 8.70 TFATT 123.52 8.12 -
[1] LI Y. Passenger flow forecast of Harbin the Line 1 subway[C]// 2010 International Conference On Computer Design and Applications. Piscataway: IEEE Press, 2010: 11524216. [2] DING C, DUAN J, ZHANG Y, et al. Using an ARIMA-GARCH modeling approach to improve subway short-term ridership forecasting accounting for dynamic volatility[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(4): 1054-1064. doi: 10.1109/TITS.2017.2711046 [3] ZHANG Z, LIANG T. Short-term forecasting of passenger flow on the metro platform using an improved Kalman filtering method[C]//19th COTA International Conference of Transportation Professionals, 2019. [4] ROOS J, BONNEVAY S, GAVIN G. Short-term urban rail passenger flow forecasting: A dynamic bayesian network approach[C]//2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA). Piscataway: IEEE Press, 2016: 16640539. [5] 惠阳, 王永岗, 彭辉, 等. 基于优化PSO-BP算法的耦合时空特征下地铁客流预测[J]. 交通运输工程学报, 2021, 21(4): 210-222. https://www.cnki.com.cn/Article/CJFDTOTAL-JYGC202104019.htmHUI Y, WANG Y G, PENG H, et al. Prediction of subway passenger flow based on optimized PSO-BP algorithm[J]. Journal of Traffic and Transportation Engineering, 2021, 21(4): 210-222(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JYGC202104019.htm [6] SUN Y, LENG B, GUAN W. A novel wavelet-SVM short-time passenger flow prediction in Beijing subway system[J]. Neurocomputing, 2015, 166: 109-121. doi: 10.1016/j.neucom.2015.03.085 [7] YANG B, SUN S, LI J, et al. Traffic flow prediction using LSTM with feature enhancement[J]. Neurocomputing, 2019, 332: 320-327. doi: 10.1016/j.neucom.2018.12.016 [8] MA X, ZHANG J, DU B, et al. Parallel architecture of convolutional bi-directional LSTM neural networks for network-wide metro ridership prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(6): 2278-2288. doi: 10.1109/TITS.2018.2867042 [9] LIU Y, LIU Z, JIA R. DeepPF: A deep learning based architecture for metro passenger flow prediction[J]. Transportation Research Part C: Emerging Technologies, 2019, 101: 18-34. doi: 10.1016/j.trc.2019.01.027 [10] GERS F A, SCHMIDHUBER J, CUMMINS F. Learning to forget: Continual prediction with LSTM[J]. Neural Computation, 2000, 12(10): 2451-2471. doi: 10.1162/089976600300015015 [11] TIAN D, LIN C, ZHOU J, et al. SA-YOLOv3: An efficient and accurate object detector using self-attention mechanism for autonomous driving[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(5): 4099-4110. doi: 10.1109/TITS.2020.3041278 [12] SUN J, KIM J. Joint prediction of next location and travel time from urban vehicle trajectories using long short-term memory neural networks[J]. Transportation Research Part C: Emerging Technologies, 2021, 128: 103114. doi: 10.1016/j.trc.2021.103114 [13] MUNKHDALAI L, MUNKHDALAI T, PARK K H, et al. Mixture of activation functions with extended min-max normalization for forex market prediction[J]. IEEE Access, 2019, 7: 183680-183691. doi: 10.1109/ACCESS.2019.2959789 [14] BOGAERTS T, MASEGOSA A D, ANGARITA-ZAPATA J S, et al. A graph CNN-LSTM neural network for short and long-term traffic forecasting based on trajectory data[J]. Transportation Research Part C: Emerging Technologies, 2020, 112: 62-77. doi: 10.1016/j.trc.2020.01.010 [15] ZHANG J, CHE H, CHEN F, et al. Short-term origin-destination demand prediction in urban rail transit systems: A channel-wise attentive split-convolutional neural network method[J]. Transportation Research Part C: Emerging Technologies, 2020, 124: 102928. [16] MA Q, LI S, ZHANG H, et al. Robust optimal predictive control for real-time bus regulation strategy with passenger demand uncertainties in urban rapid transit[J]. Transportation Research Part C: Emerging Technologies, 2021, 127: 103086. doi: 10.1016/j.trc.2021.103086 [17] DU B, PENG H, WANG S, et al. Deep irregular convolutional residual LSTM for urban traffic passenger flows prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(3): 972-985. doi: 10.1109/TITS.2019.2900481 -