Predict Short Term Bus Passenger Flow via Multi-Task Learning

doi:10.3778/j.issn.1002-8331.2210-0046

Abstract

Abstract: Most of the existing methods for short-term bus passenger flow prediction only rely on the information of a single bus line, which may ignore the impact of the correlation of multiple lines on the improvement of prediction accuracy. Thus, a prediction method based on correlation analysis and multi-task learning is proposed. Firstly, the correlation coefficient of multiple bus lines is obtained by using grey correlation analysis and Pearson correlation coefficient. Then, taking the passenger flow prediction of relevant bus lines as the auxiliary task of the passenger flow prediction of the current line, a multi-task deep learning model based on gate recurrent unit（GRU） neural network is established to predict the passenger flow. Experimental results show that the multi-task deep learning model performs better on the prediction accuracy compared against the traditional time series prediction model and the neural network model that considers a single bus line only.

Key words: short-term bus passenger flow forecasting, gate recurrent unit（GRU） neural network, multi-task learning, grey correlation analysis

摘要： 现有公交线路短时客流预测方法主要依赖于单条线路的信息，忽略了多条线路之间的相关关系对客流预测的提升效果。针对这一问题，提出一种基于相关度分析和多任务学习的公交客流预测方法。利用灰色关联分析和皮尔逊相关系数获取公交线路之间的关联度系数，计算当前线路的相关线路集合；将相关线路的客流预测作为当前线路客流预测的辅助任务，建立基于门控循环单元（GRU）神经网络的多任务深度学习模型来预测客流。实验结果表明，该多任务学习模型在预测精度方面优于传统的时间序列预测模型以及仅考虑单条线路信息的神经网络预测模型。

关键词: 公交短时客流预测, 门控循环单元（GRU）神经网络, 多任务学习, 灰色关联分析

ZHANG Pengzhen, ZUO Xingquan, HUANG Hai. Predict Short Term Bus Passenger Flow via Multi-Task Learning[J]. Computer Engineering and Applications, 2023, 59(24): 360-366.

张鹏祯, 左兴权, 黄海. 采用多任务学习预测短时公交客流[J]. 计算机工程与应用, 2023, 59(24): 360-366.

References

[1] BAI Y，SUN Z，ZENG B，et al.A multi-pattern deep fusion model for short-term bus passenger flow forecasting[J].Applied Soft Computing，2017，58：669-680.
[2] XUE R，SUN D J，CHEN S.Short-term bus passenger demand prediction based on time series model and interactive multiple model approach[J].Discrete Dynamics in Nature and Society，2015，66（1）：61-78.
[3] ZHANG J，SHEN D，TU L，et al.A real-time passenger flow estimation and prediction method for urban bus transit systems[J].IEEE Transactions on Intelligent Transportation Systems，2017，18（11）：3168-3178.
[4] TANG L，ZHAO Y，CABRERA J，et al.Forecasting short-term passenger flow：an empirical study on shenzhen metro[J].IEEE Transactions on Intelligent Transportation Systems，2018，20（10）：3613-3622.
[5] CHEN Q，LI W，ZHAO J.The use of LS-SVM for short-term passenger flow prediction[J].Transport，2011，26（1）：5-10.
[6] BAI Y，SUN Z，ZENG B，et al.A multi-pattern deep fusion model for short-term bus passenger flow forecasting[J].Applied Soft Computing，2017，58：669-680.
[7] LI X，CHEN Z，ZHU F，et al.Short-term bus passenger flow forecast based on deep learning[C]//2018 International Conference on Security，Pattern Analysis，and Cybernetics（SPAC），2018：372-376.
[8] CHEN D，ZHANG J，JIANG S.Forecasting the short-term metro ridership with seasonal and trend decomposition using loess and LSTM neural networks[J].IEEE Access，2020，8：91181-91187.
[9] ZHANG Y，YANG Q.A survey on multi-task learning[J].arXiv：1707.08114v2，2021.
[10] MAHMOUD R A，HAJJ H，KARAMEH F N.A systematic approach to multi-task learning from time-series data[J].Applied Soft Computing，2020，96：106586.
[11] WARRIER S，RUTTER E M，FLORES K B.Multitask neural networks for predicting bladder pressure with time series data[J].Biomedical Signal Processing and Control，2022，72：103298.
[12] XU X，YONEDA M.Multitask air-quality prediction based on LSTM-autoencoder model[J].IEEE Transactions on Cybernetics，2019，51（5）：2577-2586.
[13] ZHONG R，LV W，DU B，et al.Spatiotemporal multi-task learning for citywide passenger flow prediction[C]//2017 IEEE SmartWorld，Ubiquitous Intelligence & Computing，Advanced & Trusted Computed，Scalable Computing & Communications，Cloud & Big Data Computing，Internet of People and Smart City Innovation（SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI），2017：1-8.
[14] BAI L，YAO L，KANHERE S S，et al.Passenger demand forecasting with multi-task convolutional recurrent neural networks[C]//Pacific-Asia Conference on Knowledge Discovery and Data Mining.Cham：Springer，2019：29-42.
[15] CHIDLOVSKII B.Multi-task learning of time series and its application to the travel demand[J].arXiv：1712.08164，2017.
[16] LUO D，ZHAO D，KE Q，et al.Fine-grained service-level passenger flow prediction for bus transit systems based on multitask deep learning[J].IEEE Transactions on Intelligent Transportation Systems，2020，22（11）：7184-7199.
[17] CARUANA R.Multitask learning[J].Machine Learning，1997，28（1）：41-75.
[18] DEND J Y.Introduction to grey system theory[J].The Journal of Grey System，1989，1（1）：1-24.
[19] 张宇镭，党琰，贺平安.利用Pearson相关系数定量分析生物亲缘关系[J].计算机工程与应用，2005，41（33）：79-82.
ZHANG Y L，DANG Y，HE P A.Quantitative analysis of the relationship of biology species using Pearson correlation coefficient[J].Computer Engineering and Applications，2005，41（33）：79-82.
[20] WEI G.Grey relational analysis model for dynamic hybrid multiple attribute decision making[J].Knowledge-Based Systems，2011，24（5）：672-679.
[21] MA J，ZHAO Z，YI X，et al.Modeling task relationships in multi-task learning with multi-gate mixture-of-experts[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining，2018：1930-1939.
[22] CHO K，VAN MERRI?NBOER B，GULCEHRE C，et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[J].arXiv：1406.1078，2014.
[23] JOZEFOWICZ R，ZAREMBA W，SUTSKEVER I.An empirical exploration of recurrent network architectures[C]//International Conference on Machine Learning，2015：2342-2350.
[24] MINH D L，SADEGHI-NIARAKI A，HUY H D，et al.Deep learning approach for short-term stock trends prediction based on two-stream gated recurrent unit network[J].IEEE Access，2018，6：55392-55404.
[25] SHEN G，TAN Q，ZHANG H，et al.Deep learning with gated recurrent unit networks for financial sequence predictions[J].Procedia Computer Science，2018，131：895-903.
[26] UNGUREAN L，MICEA M V，CARSTOIU G.Online state of health prediction method for lithium‐ion batteries，based on gated recurrent unit neural networks[J].International Journal of Energy Research，2020，44（8）：6767-6777.
[27] GILES C L，KUHN G M，WILLIAMS R J.Dynamic recurrent neural networks：theory and applications[J].IEEE Transactions on Neural Networks，1994，5（2）：153-156.