华东师范大学学报（自然科学版） >

2023 , Vol. 2023 >Issue 2: 106 - 118

DOI: https://doi.org/10.3969/j.issn.1000-5641.2023.02.012

计算机科学

基于神经网络的行驶时长预测

  • 武朝阳 ,
  • 毛嘉莉
展开
  • 华东师范大学 数据科学与工程学院, 上海　200062

收稿日期: 2021-12-03

  网络出版日期: 2023-03-23

基金资助

国家自然科学基金 (62072180)

收起

Research on travel time prediction based on neural network

  • Zhaoyang WU ,
  • Jiali MAO
Expand
  • School of Data Science and Engineering, East China Normal University, Shanghai　200062, China

Received date: 2021-12-03

  Online published: 2023-03-23

Fold

摘要

定位设备的普及产生了海量的车辆行驶数据, 使得利用历史数据预测车辆行驶时长成为可能. 车辆行驶数据由两部分组成: 车辆行驶经过的路段序列信息和出发时段; 路径总长度等外部信息. 如何提取路段序列特征, 以及如何将序列特征与外部特征有效地融合, 成为预测行驶时间的关键问题. 为解决以上问题, 提出了一个基于 Transformer 的行驶时间预测模型, 模型由路段序列处理模块和特征融合模块两部分组成. 首先, 路段序列处理模块使用自注意力机制处理路段序列, 提取路段序列特征. 该模型不但可以充分考虑各条路段与其他路段间道路速度的时空关联性, 同时可保证数据并行输入模型, 避免了使用循环神经网络时数据顺序输入导致的效率低下. 其次, 特征融合模块将路段序列特征与出发时段等外部信息相融合, 最终获得预测的行驶时长. 在此基础上, 统计路口连接的路段数作为路段的上/下游路口特征, 与路段特征结合输入模型, 进一步提升了行驶时长的预测精度. 在真实的数据集上与主流预测模型进行的对比实验表明, 该模型在预测精度以及训练速度上均有提升, 体现了所提模型的有效性.

关键词： 行驶时长预测; 位置服务; 注意力机制; 时空数据

本文引用格式

武朝阳 , 毛嘉莉 . 基于神经网络的行驶时长预测[J]. 华东师范大学学报（自然科学版）, 2023 , 2023(2) : 106 -118 . DOI: 10.3969/j.issn.1000-5641.2023.02.012

Abstract

The popularity of positioning devices has generated a large volume of vehicle driving data, making it possible to use historical data to predict the driving time of vehicles. Vehicle driving data consists of two parts: the sequence of road segments that the vehicle travels through, the departure time, the total length of the path, and other external information. The questions of how to extract sequence features in road segments and how to effectively fuse sequence features with external features become the key issues in predicting the travel time. To solve the aforementioned problems, a transformer-based travel time prediction model is proposed, which consists of two parts: a road segment sequence processing module and a feature fusion module. First, the road segment sequence processing module uses the self-attention mechanism to process the road segment sequence and extract the road segment sequence features. The model can not only fully consider the spatiotemporal correlation of road speeds between each road segment and other road segments, but also ensures the parallel input of data into the model, avoiding the low efficiency problem caused by sequential input of data when using recurrent neural networks. The feature fusion module fuses the road segment sequence features with external information, such as departure time, and obtains the predicted travel time. On this basis, the number of road segments connected by the intersection is determined by the upstream and downstream intersection features of the road segment, and the input model is combined with the road segment characteristics to further improve the prediction accuracy of the driving time. Comparative experiments with mainstream prediction methods on real data sets show that the model improves prediction accuracy and training speed, reflecting the effectiveness of the proposed method.

Key words： travel time predition; location-based services; attention mechanism; spatial-temporal data

参考文献

1 WANG Z, FU K, YE J P. Learning to estimate the travel time [C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2018: 858-866.
2 WANG D, ZHANG J B, CAO W, et al. When will you arrive? Estimating travel time based on deep neural networks [C]// Proceedings of the 32nd AAAI Conference on Artificial Intelligence and 30th Innovative Applications of Artificial Intelligence Conference and 8th AAAI Symposium on Educational Advances in Artificial Intelligence. AAAI, 2018: 2500-2507.
3 VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS 2017). Red Hook, NY, United States: Curran Associates Inc., 2017: 6000-6010.
4 DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16 × 16 words: Transformers for image recognition at scale [EB/OL]. (2020-10-22)[2022-11-26]. https://arxiv.org/abs/2010.11929.
5 YING C X, CAI T, LUO S J, et al. Do transformers really perform bad for graph representation? [EB/OL]. (2021-11-24)[2021-11-26]. https://arxiv.org/abs/2106.05234.
6 DE SOUZA PEREIRA MOREIRA G, RABHI S, LEE J M, et al. Transformers4rec: Bridging the gap between nlp and sequential/session-based recommendation [C]// Proceedings of the 15th ACM Conference on Recommender Systems. ACM, 2021: 143-153.
7 WANG H J, TANG X F, KUO Y H, et al. A simple baseline for travel time estimation using large-scale trip data. ACM Transactions on Intelligent Systems and Technology (TIST), 2019, 10 (2): 19:1- 19:22.
8 JINDAL I, QIN Z W, CHEN X W, et al. A unified neural network approach for estimating travel time and distance for a taxi trip [EB/OL]. (2017-10-12)[2021-11-26]. https://arxiv.org/pdf/1710.04350.pdf.
9 LI Y G, FU K, WANG Z, et al. Multi-task representation learning for travel time estimation [C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2018: 1695-1704.
10 OUNOUGHI C, YEFERNY T, YAHIA S B. ZED-TTE: Zone embedding and deep neural network based travel time estimation approach [C]// 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, 2021. DOI: 10.1109/IJCNN52387.2021.9533456.
11 ASGHARI M, EMRICH T, DEMIRYUREK U, et al. Probabilistic estimation of link travel times in dynamic road networks [C]// Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems. ACM, 2015: Article number 47. DOI: http://dx.doi.org/10.1145/2820783.2820836.
12 JIA Z F, CHEN C, COIFMAN B, et al. The PeMS algorithms for accurate, real-time estimates of g-factors and speeds from single-loop detectors [C]// 2001 IEEE Intelligent Transportation Systems Proceedings. IEEE, 2001: 536-541. DOI: 10.1109/ITSC.2001.948715.
13 PETTY K F, BICKEL P, OSTLAND M, et al. Accurate estimation of travel times from single-loop detectors. Transportation Research Part A, 1998, 32 (1): 1- 17.
14 TANG J J, ZOU Y J, ASH J, et al. Travel time estimation using freeway point detector data based on evolving fuzzy neural inference system. PloS One, 2016, 11 (2): e0147263.
15 JENELIUS E, KOUTSOPOULOS H N. Travel time estimation for urban road networks using low frequency probe vehicle data. Transportation Research Part B, 2013, 53 (4): 64- 81.
16 HUNTER T, HERRING R, ABBEEL P, et al. Path and travel time inference from GPS probe vehicle data [EB/OL]. (2009-01-29)[2022-11-25]. https://snap.stanford.edu/nipsgraphs2009/papers/hunter-paper.pdf.
17 WANG Y L, ZHENG Y, XUE Y X. Travel time estimation of a path using sparse trajectories [C]// Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2014: 25-34.
18 ALEXANDER-RAKHLIN. CNN-for-sentence-classification-in-Keras [EB/OL]. (2017-07-17)[2022-11-26]. https://github.com/alexander-rakhlin/CNN-for-Sentence-Classification-in-Keras.
19 HENG-TZE C, LEVENT K, JEREMIAH H, et al. Wide & deep learning for recommender systems [C]// Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. ACM, 2016: 7-10.
20 FU K, MENG F L, YE J P, et al. CompactETA: A fast inference system for travel time prediction [C]// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2020: 3337-3345.
21 FANG X M, HUANG J Z, WANG F, et al. ConSTGAT: Contextual spatial-temporal graph attention network for travel time estimation at Baidu maps [C]// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2020: 2697-2705.
22 SUN Y, WANG Y, FU K, et al. FMA-ETA: Estimating travel time entirely based on FFN with attention [C]// ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2021: 3355-3359.
23 FANG X M, HUANG J Z, WANG F, et al. SSML: Self-supervised meta-learner for en route travel time estimation at Baidu maps [C]// Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. ACM, 2021: 2840-2848.
24 HONG H T, LIN Y C, YANG X Q, et al. HetETA: Heterogeneous information network embedding for estimating time of arrival [C]// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2020: 2444-2454.
25 FU T Y, LEE W C. DeepIST: Deep image-based spatio-temporal network for travel time estimation [C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management. ACM, 2019: 69-78.
26 XU J, ZHANG Y, CHAO L, et al. STDR: A deep learning method for travel time estimation [C]// International Conference on Database Systems for Advanced Applications, DASFAA 2019, Lecture Notes in Computer Science, vol 11447. Cham: Springer, 2019: 156-172.
27 XIONG R B, YANG Y C, HE D, et al. On layer normalization in the transformer architecture [EB/OL]. (2020-06-29)[2021-11-26]. https://arxiv.org/abs/2002.04745.
28 HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition [C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2016: 770-778.
29 LOSHCHILOV I, HUTTER F. Decoupled weight decay regularization [EB/OL]. (2019-01-04)[2021-11-26]. https://arxiv.org/abs/1711.05101v3.
30 KE G L, MENG Q, FINLEY T, et al. LightGBM: A highly efficient gradient boosting decision tree [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS 2017). Red Hook, NY, USA: Curran Associates Inc., 2017: 3149-3157.
31 GUO H F, TANG R M, YE Y M, et al. DeepFM: A factorization-machine based neural network for CTR prediction[C]// Proceedings of the 26th International Joint Conference on Artificial Intelligence. AAAI, 2017: 1725-1731.
Options
文章导航

/

〈 〉