Abstract
Accurate travel time prediction between two locations is one of the most substantial services in transport. In travel time prediction, origin–destination (OD) method is more challenging since it has no intermediate trajectory points. This paper puts forward a deep learning-based model, called Gated Spatial–Temporal Attention (GSTA), to optimize the OD travel time prediction. While many trip features are available, their relations and particular contributions to the output are usually unknown. To give our model the flexibility to select the most relevant features, we develop a feature selection module with an integration unit and a gating mechanism to pass or suppress the trip feature based on its contribution. To capture spatial–temporal dependencies and correlations in the short and long term, we propose a new pair-wise attention mechanism with spatial inference and temporal reasoning. In addition, we adapt and integrate multi-head attention to improve model performance in case of sophisticated dependencies in long term. Extensive experiments on two large taxi datasets in New York City, USA, and Chengdu, China demonstrate the superiority of our model in comparison with other models.
Similar content being viewed by others
References
Abbar S, Stanojevic R, Mokbel MSTAD (2020) Spatio-temporal adjustment of traffic-oblivious travel-time estimation. In: Proceedings—IEEE international conference on mobile data management 2020–June, 79–88 https://doi.org/10.1109/MDM48529.2020.00029
Abdollahi M, Khaleghi T, Yang K (2020) An integrated feature learning approach using deep learning for travel time prediction. Exp Syst Appl. https://doi.org/10.1016/j.eswa.2019.112864
Aceto G, Ciuonzo D, Montieri A, Pescapè A (2019) Mimetic: mobile encrypted traffic classification using multimodal deep learning. Comput Netw 165:106944. https://doi.org/10.1016/j.comnet.2019.106944. https://www.sciencedirect.com/science/article/pii/S1389128619304669
Ahmed MS, Cook AR (1979) Analysis of freeway traffic time-series data by using box-Jenkins techniques. Transp Res Rec 722:1–9
Ba JL, Kiros JR, Hinton GE (2016) Layer normalization. http://arxiv.org/abs/1607.06450
Clevert DA, Unterthiner T, Hochreiter S (2016) Fast and accurate deep network learning by exponential linear units (ELUs). In: Proceedings of the 4th international conference on learning representations, ICLR 2016: conference track proceedings. pp 1–14
Commission NTL (2021) TLC trip record data: TLC. Accessed on 2 May 2021. https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page
Dataset DCT (2021) DiDi Chengdu taxi dataset. Accessed on 2 May 2021. https://outreach.didichuxing.com/app-vue/dataList
Dauphin YN, Fan A, Auli M, Grangier D (2016) Language modeling with gated convolutional networks. CoRR abs/1612.0. http://arxiv.org/abs/1612.08083
Delling D (2018) Route planning in transportation networks: from research to practice. In: Proceedings of the 26th ACM SIGSPATIAL international conference on advances in geographic information systems, SIGSPATIAL ’18, p. 2. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3274895.3282802
Drucker H, Burges CJC, Kaufman L, Smola A, Vapnik V (1996). Support vector regression machines. In: Proceedings of the 9th international conference on neural information processing systems, NIPS’96, p. 155–161. MIT Press, Cambridge, MA, USA
Du W, Sun B, Kuai J, Xie J, Yu J, Sun T (2021) Highway travel time prediction of segments based on ANPR data considering traffic diversion. J Adv Transp 2021:1–16. https://doi.org/10.1155/2021/9512501
Fang X, Huang J, Wang F, Zeng L, Liang H, Wang H (2020) ConSTGAT: contextual spatial-temporal graph attention network for travel time estimation at Baidu Maps. In: Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining. pp 2697–2705. https://doi.org/10.1145/3394486.3403320
Fei X, Lu CC, Liu K (2011) A bayesian dynamic linear model approach for real-time short-term freeway travel time prediction. Transp Res C Emerg Technol 19(6):1306–1318. https://doi.org/10.1016/j.trc.2010.10.005
Guo G, Zhang T (2020) A residual spatio-temporal architecture for travel demand forecasting. Transp Res C Emerg Technol 115:102639. https://doi.org/10.1016/j.trc.2020.102639
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition 2016-Decem, 770–778. https://doi.org/10.1109/CVPR.2016.90
Ishak S, Kotha P, Alecsandru C (2003) Optimization of dynamic neural network performance for short-term traffic prediction. Transp Res Rec 1836:45–56
Jindal I, Tony Q, Chen X, Nokleby M, Ye J (2017) A unified neural network approach for estimating travel time and distance for a taxi trip. http://arxiv.org/abs/1710.04350
Kankanamge KD, Witharanage YR, Withanage CS, Hansini M, Lakmal D, Thayasivam U (2019) Taxi trip travel time prediction with isolated xgboost regression. In: MERCon 2019: Proceedings, 5th international multidisciplinary moratuwa engineering research conference (April 2020), 54–59 . https://doi.org/10.1109/MERCon.2019.8818915
Ke G, Meng Q, Finely T, Wang T, Chen W, Ma W, Ye Q, Liu, T.Y (2017). Lightgbm: a highly efficient gradient boosting decision tree. In: Advances in Neural Information Processing Systems 30 (NIP 2017)
Khodaverdian Z, Sadr H, Edalatpanah SA (2021) A shallow deep neural network for selection of migration candidate virtual machines to reduce energy consumption. In: Proceedings of the 2021 7th international conference on web research (ICWR), pp 191–196. https://doi.org/10.1109/ICWR51868.2021.9443133
Khodaverdian Z, Sadr H, Edalatpanah SA, Solimandarabi MN (2021) Combination of convolutional neural network and gated recurrent unit for energy aware resource allocation. CoRR abs/210612178. https://arxiv.org/abs/2106.12178
Li Y, Fu K, Wang Z, Shahabi C, Ye J, Liu Y (2018) Multi-task representation learning for travel time estimation. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining
Myung J, Kim D, Kho S, Park C (2011) Travel time prediction using k nearest neighbor method with combined data from vehicle detector system and automatic toll collection system. Transp Res Rec 2256:51–59
Ngiam J, Khosla A, Kim M, Nam J, Lee H, Ng AY (2011) Multimodal deep learning. In: Proceedings of the 28th international conference on international conference on machine learning, ICML’11, p. 689–696. Omni press, Madison, WI, USA
Prokhorchuk A, Dauwels J, Jaillet P (2020) Estimating travel time distributions by bayesian network inference. IEEE Trans Intell Transp Syst 21(5):1867–1876. https://doi.org/10.1109/TITS.2019.2899906
Savarese P, Figueiredo D (2017) Residual gates: a simple mechanism for improved network optimization
Service N.W (2021) NWS New York significant weather events archive. Accessed on 2 May 2021. https://www.weather.gov/okx/stormevents
Sun Y, Wang Y, Fu K, Wang Z, Yan Z, Zhang C, Ye J (2020) FMA-ETA: estimating travel time entirely based on FFN with attention pp 1–10 . http://arxiv.org/abs/2006.04077
Tan K, Chen J, Wang D (2018) Gated residual networks with dilated convolutions for supervised speech separation department of computer science and engineering, the Ohio state university, USA center for cognitive and brain sciences, the Ohio state university, USA. Icassp 1:21–25
Ting P, Wada T, Chiu Y, Sun M, Sakai K, Ku W, Jeng AA, Hwu J (2020) Freeway travel time prediction using deep hybrid model: taking sun Yat-Sen freeway as an example. IEEE Trans Veh Technol 69(8):8257–8266
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. Adv Neural Inform Process Syst 2017:5999–6009
Wang D, Zhang J, Cao W, Li J, Zheng Y When will you arrive? Estimating travel time based on deep neural networks
Wang H, Tang X, Kuo YH, Kifer D, Li Z (2019) A simple baseline for travel time estimation using large-scale trip data. ACM Trans Intel Syst Technol 10(2):1–22. https://doi.org/10.1145/3293317
Wang Z, Fu K, Ye J, Labs DAI, Chuxing D (2018) Learning to estimate the travel. Time 1:858–866
Wu Z, Rilett LR, Ren W (2021) New methodologies for predicting corridor travel time mean and reliability. Int J Urban Sci. https://doi.org/10.1080/12265934.2021.1899844
Xu S, Zhang R, Cheng W, Xu J (2020) MTLM: a multi-task learning model for travel time estimation. GeoInformatica. https://doi.org/10.1007/s10707-020-00422-x
Yuan H, Li G, Bao Z, Feng L (2020) Effective travel time estimation: when historical trajectories over road networks matter. In: Proceedings of the ACM SIGMOD international conference on management of data. pp 2135–2149. https://doi.org/10.1145/3318464.3389771
Zhang H, Wu H, Sun W, Zheng B (2018) DEEPTRAVEL: a neural network based travel time estimation model with auxiliary supervision. IJCAI Int Joint Conf Artif Intel 2018:3655–3661. https://doi.org/10.24963/ijcai.2018/508
Zou Z, Yang H, Zhu AX (2020) Estimation of travel time based on ensemble method with multi-modality perspective urban big data. IEEE Access 8(2):24819–24828. https://doi.org/10.1109/ACCESS.2020.2971008
Acknowledgements
This work is supported in part by the National Natural Science Foundation of China under Grant U1811463, and also in part by the Innovation Foundation of Science and Technology of Dalian under Grant 2018J11CY010.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Khaled, A., Elsir, A.M.T. & Shen, Y. GSTA: gated spatial–temporal attention approach for travel time prediction. Neural Comput & Applic 34, 2307–2322 (2022). https://doi.org/10.1007/s00521-021-06560-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06560-z