| 296 | 0 | 63 |
| 下载次数 | 被引频次 | 阅读次数 |
针对智能交通系统中行程时间估计的不确定性量化的难题，提出一种全局-局部不确定性感知行程时间估计方法(global and local uncertainty-aware travel time estimation, GLUTTE)。首先，通过多任务学习策略建模整体路线与各局部路段的行程时间关系及其不确定性。其次，采用多粒度分位数回归方法，综合考虑全局和局部特征，提供准确的置信区间估计。实验结果表明，所提方法能够有效量化不确定性，同时保证准确性并提供可靠的置信区间，从而提升结果的可用性和可信度。
Abstract：In response to the difficulty of uncertainty quantification for travel time estimation in intelligent transportation systems, a global and local uncertainty-aware travel time estimation(GLUTTE) method was proposed. Firstly, a multi-task learning strategy was employed to model the travel time relationship between overall routes and each local segment, as well as their uncertainties. Secondly, a multi-granularity quantile regression approach was adopted, considering both global and local features to provide accurate confidence interval estimation. The experimental results demonstrated that the proposed method could effectively quantify uncertainties while ensuring accuracy and offering reliable confidence intervals, thereby enhancing the usability and credibility of the results.
[1] HU X Y,BINAYKIYA T,FRANK E,et al.DeeprETA:an ETA post-processing system at scale[EB/OL].(2022-06-05)[2024-03-21].https://doi.org/10.48550/arXiv.2206.02127.
[2] 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.New York:ACM Press,2018:858-866.
[3] CHEN Z B,XIAO X L,GONG Y J,et al.Interpreting trajectories from multiple views:a hierarchical self-attention network for estimating the time of arrival[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.New York:ACM Press,2022:2771-2779.
[4] 陈俊彦，黄雪锋，韦俊宇，等.基于多图时空注意力的轨道交通客流预测模型[J].郑州大学学报(理学版),2023,55(4):39-45.CHEN J Y,HUANG X F,WEI J Y,et al.A prediction method of rail transit passenger flow based on multi-graph spatial and temporal attention[J].Journal of Zhengzhou university (natural science edition),2023,55(4):39-45.
[5] 刘玉强，顾晶晶，孙明，等.基于城市区域多模态融合的人群流量预测[J].郑州大学学报(理学版),2022,54(1):25-31.LIU Y Q,GU J J,SUN M,et al.Exploring the multimodal fusion of urban regions for crowd flow prediction[J].Journal of Zhengzhou university (natural science edition),2022,54(1):25-31.
[6] DERROW-PINION A,SHE J,WONG D,et al.ETA prediction with graph neural networks in google maps[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management.New York:ACM Press,2021:3767-3776.
[7] WANG B,LU J,YAN Z,et al.Deep uncertainty quantification:a machine learning approach for weather forecasting[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.New York:ACM Press,2019:2087-2095.
[8] PEARCE T,ZAKI M,BRINTRUP A,et al.High-quality prediction intervals for deep learning:a distribution-free,ensembled approach[EB/OL].(2018-06-15)[2024-03-21].https://doi.org/10.48550/arXiv.1802.07167.
[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.New York:ACM Press,2018:1695-1704.
[10] LIN Y,WAN H Y,HU J L,et al.Origin-destination travel time oracle for map-based services[J].Proceedings of the ACM on management of data,2023,1(3):1-27.
[11] ABDAR M,POURPANAH F,HUSSAIN S,et al.A review of uncertainty quantification in deep learning:techniques,applications and challenges[J].Information fusion,2021,76:243-297.
[12] GAL Y,GHAHRAMANI Z.Dropout as a Bayesian approximation:representing model uncertainty in deep learning[C]//Proceedings of the 33rd International Conference on Machine Learning.New York:ACM Press,2016:1651-1660.
[13] HAO L X,NAIMAN D Q.Quantile regression[M].Los Angeles:Sage Publications,2007.
[14] WU D X,GAO L Y,CHINAZZI M,et al.Quantifying uncertainty in deep spatiotemporal forecasting[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.New York:ACM Press,2021:1841-1851.
[15] SHAFER G,VOVK V.A tutorial on conformal prediction[J].Journal of machine learning research,2008,9:371-421.
[16] HE X N,CHUA T S.Neural factorization machines for sparse predictive analytics[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval.New York:ACM Press,2017:355-364.
[17] MAO X W,CAI T Y,PENG W C,et al.Estimated time of arrival prediction via modeling the spatial-temporal interactions between links and crosses[C]//Proceedings of the 29th International Conference on Advances in Geographic Information Systems.New York:ACM Press,2021:658-661.
基本信息:
DOI：10.13705/j.issn.1671-6841.2024099
中图分类号:U495;TP18
引用信息:
[1]申泽楷,郭晟楠,毛潇苇等.融合不确定性建模的行程时间与置信区间估计[J].郑州大学学报(理学版),2025,57(06):8-15.DOI:10.13705/j.issn.1671-6841.2024099.
基金信息:
国家自然科学基金青年基金项目(62202043)