UCTB：时空人群流动预测工具箱

doi:10.3778/j.issn.1673-9418.2012072

计算机科学与探索 ›› 2022, Vol. 16 ›› Issue (4): 835-843.DOI: 10.3778/j.issn.1673-9418.2012072

UCTB：时空人群流动预测工具箱

陈李越¹^,², 柴迪³, 王乐业¹^,²^,⁺()

1.高可信软件技术教育部重点实验室（北京大学）,北京 100871
2.北京大学信息科学技术学院计算机科学技术系,北京 100871
3.香港科技大学计算机科学与工程系,香港 999077

收稿日期:2020-12-04 修回日期:2021-02-01 出版日期:2022-04-01 发布日期:2021-02-04
通讯作者: + E-mail: leyewang@pku.edu.cn
作者简介:陈李越（1998—）,男,湖北黄冈人,博士研究生,主要研究方向为普适计算、城市计算。
柴迪（1995—）,男,河北保定人,博士研究生,主要研究方向为联邦学习、隐私保护学习。
王乐业（1987—）,男,上海人,博士,助理教授,博士生导师,主要研究方向为普适计算、群智感知、城市计算。
基金资助:
国家自然科学基金(61972008)

UCTB: Spatiotemporal Crowd Flow Prediction Toolbox

CHEN Liyue¹^,², CHAI Di³, WANG Leye¹^,²^,⁺()

1. Key Lab of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing 100871, China
2. Department of Computer Science and Technology, School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China
3. Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong 999077, China

Received:2020-12-04 Revised:2021-02-01 Online:2022-04-01 Published:2021-02-04
About author:CHEN Liyue, born in 1998, Ph.D. candidate. His research interests include ubiquitous computing and urban computing.
CHAI Di, born in 1995, Ph.D. candidate. His research interests include federated learning and privacy-preserving.
WANG Leye, born in 1987, Ph.D., assistant professor, Ph.D. supervisor. His research interests include ubiquitous computing, mobile crowdsensing and urban computing.
Supported by:
National Natural Science Foundation of China(61972008)

摘要/Abstract

摘要：

时空人群流动预测是智慧城市中的关键技术之一。目前主要有两大痛点困扰着相关研究、从业人员：第一,人群流动与多种因素相关,先前的研究总结出了多种时空先验知识,但由于人群流动预测应用场景的多样性,后续工作很难合理而全面地利用这些先验知识;第二,随着深度学习技术的发展,相关技术的实现越来越复杂,复现先进的模型是一件费时且愈发繁琐的事情。针对上述痛点,设计了时间序列采样接口和图构建接口,时间序列采样接口能够基于不同的先验知识产生不同类型的时间序列,图构建接口能够产生不同类型的空间图,上述两个接口还可通过继承接口实现自定义,以利用新的时空先验知识;基于TensorFlow框架实现了多种先进的时空图模型并封装了其中常用的时空建模单元,使用者不仅能够直接使用先进的时空模型,还能够基于这些高级模型层进行二次开发。综上,时空人群流动预测工具箱UCTB内同时集成了多种时空先验知识和多种先进的模型,对开发时空人群流动预测相关应用有着促进作用。相关的代码和配套文档均已开源,工具箱的网址是https://github.com/uctb/UCTB。

关键词: 城市计算, 人群流动, 时空预测, 开源工具箱

Abstract:

Spatiotemporal crowd flow prediction is one of the key technologies in smart cities. There are mainly two major shortcomings that plague researchers and developers. Firstly, crowd flow is affected by complex factors and previous studies have summarized a variety of spatiotemporal prior knowledge. However, it is difficult for follow-up work to comprehensively incorporate this prior knowledge as its application scenarios are diverse. Secondly, with the development of deep learning technology, implementing state-of-the-art models is cumbersome work and becomes more and more complicated. To fill in the above gaps, this paper designs time-series sampling interfaces and graph construction interfaces. The time series sampling interfaces can generate different types of time series based on diverse prior knowledge, and the graph construction interfaces can build different types of spatial graphs. Moreover, users can extend the above two interfaces to utilize new spatiotemporal prior knowledge. Based on the TensorFlow framework, this paper implements a variety of advanced spatiotemporal graph models and encapsulates the frequently-used spatiotemporal modeling units. Users can leverage state-of-the-art spatiotemporal models and perform customized development based on these advanced layers. In summary, the spatiotemporal crowd flow prediction tool box UCTB integrates diverse spatiotemporal prior knowledge and a variety of advanced models, which may promote the development of spatiotemporal crowd flow prediction applications. The codes and detailed documents are open-source. The URL of UCTB is https://github.com/uctb/UCTB.

Key words: urban computing, crowd flow, spatiotemporal prediction, open-source toolbox

中图分类号:

TP311

陈李越, 柴迪, 王乐业. UCTB：时空人群流动预测工具箱[J]. 计算机科学与探索, 2022, 16(4): 835-843.

CHEN Liyue, CHAI Di, WANG Leye. UCTB: Spatiotemporal Crowd Flow Prediction Toolbox[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(4): 835-843.

图/表 9

参考文献 26

[1]	郑宇. 城市计算概述[J]. 武汉大学学报(信息科学版), 2015, 40(1):1-13.
	ZHENG Y. Introduction to urban computing[J]. Geomatics and Information Science of Wuhan University, 2015, 40(1):1-13.
[2]	HAMED M M, AL-MASAEID H R, SAID Z M B. Short-term prediction of traffic volume in urban arterials[J]. Journal of Transportation Engineering, 1995, 121(3):249-254. DOI URL
[3]	HOANG M X, ZHENG Y, SINGH A K. FCCF: forecasting citywide crowd flows based on big data[C]// Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Burlingame, Oct 31 - Nov 3, 2016. New York: ACM, 2016: 1-10.
[4]	LI Y X, ZHENG Y, ZHANG H C, et al. Traffic prediction in a bike-sharing system[C]// Proceedings of the 23rd SIG-SPATIAL International Conference on Advances in Geographic Information Systems, Bellevue, Nov 3-6, 2015. New York: ACM, 2015: 1-10.
[5]	LV Y S, DUAN Y J, KANG W W, et al. Traffic flow prediction with big data: a deep learning approach[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(2):865-873.
[6]	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780. DOI URL
[7]	CHO K, MERRIËNBOER B V, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[J]. arXiv: 1406. 1078, 2014.
[8]	YU R, LI Y G, SHAHABI C, et al. Deep learning: a generic approach for extreme condition traffic forecasting[C]// Proceedings of the 2017 SIAM International Conference on Data Mining, Houston, Apr 27-29, 2017. Philadelphia: SIAM, 2017: 777-785.
[9]	YUAN N J, ZHENG Y, XIE X, et al. Discovering urban functional zones using latent activity trajectories[J]. IEEE Transactions on Knowledge and Data Engineering, 2014, 27(3):712-725. DOI URL
[10]	ZHANG J B, ZHENG Y, QI D K, et al. DNN-based prediction model for spatio-temporal data[C]// Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Burlingame, Oct 31-Nov 3, 2016. New York: ACM, 2016: 1-4.
[11]	KE J T, ZHENG H Y, YANG H, et al. Short-term forecasting of passenger demand under on-demand ride services: a spatio-temporal deep learning approach[J]. Transportation Research Part C: Emerging Technologies, 2017, 85:591-608. DOI URL
[12]	ZHANG J B, ZHENG Y, QI D K. Deep spatio-temporal residual networks for citywide crowd flows prediction[C]// Proceedings of the 31st AAAI Conference on Artificial Intelligence, San Francisco, Feb 4-9, 2017. Menlo Park: AAAI, 2017: 1655-1661.
[13]	ZHANG J B, ZHENG Y, SUN J K, et al. Flow prediction in spatio-temporal networks based on multitask deep learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 32(3):468-478. DOI URL
[14]	LI Y G, YU R, SHAHABI C, et al. Diffusion convolutional recurrent neural network: data-driven traffic forecasting[J]. arXiv: 1707. 01926, 2017.
[15]	CHAI D, WANG L Y, YANG Q. Bike flow prediction with multi-graph convolutional networks[C]// Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Seattle, Nov 6-9, 2018. New York: ACM, 2018: 397-400.
[16]	GENG X, LI Y G, WANG L Y, et al. Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting[C]// Proceedings of the 33rd AAAI Conference on Artificial Intelligence, the 31st Innovative Applications of Artificial Intelligence Conference, the 9th AAAI Symposium on Educa-tional Advances in Artificial Intelligence, Honolulu, Jan 27-Feb 1, 2019. Menlo Park: AAAI, 2019: 3656-3663.
[17]	冯宁, 郭晟楠, 宋超, 等. 面向交通流量预测的多组件时空图卷积网络[J]. 软件学报, 2019, 30(3):759-769.
	FENG N, GUO S N, SONG C, et al. Multi-component spatial-temporal graph convolution networks for traffic flow forecasting[J]. Journal of Software, 2019, 30(3):759-769.
[18]	LIANG Y X, KE S Y, ZHANG J B, et al. GeoMAN: multi-level attention networks for geo-sensory time series prediction[C]// Proceedings of the 27th International Joint Conference on Artificial Intelligence, Stockholm, Jul 13-19, 2018: 3428-3434.
[19]	ZHANG J N, SHI X J, XIE J Y, et al. GaAN: gated attention networks for learning on large and spatiotemporal graphs[J]. arXiv: 1803. 07294, 2018.
[20]	WANG X Y, MA Y, WANG Y Q, et al. Traffic flow prediction via spatial temporal graph neural network[C]// Proceedings of the Web Conference 2020, Taiwan, China, Apr 20-24, 2020. New York: ACM, 2020: 1082-1092.
[21]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]// Proceedings of the Annual Conference on Neural Information Processing Systems, Long Beach, Dec 4-9, 2017. Red Hook: Curran Associates, 2017: 5998-6008.
[22]	ABADI M, BARHAM P, CHEN J M, et al. TensorFlow: a system for large-scale machine learning[C]// Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, Savannah, Nov 2-4, 2016. Berkeley: USENIX Association, 2016: 265-283.
[23]	DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[C]// Proceedings of the Annual Conference on Neural Information Processing Systems, Barcelona, Dec 5-10, 2016. Red Hook: Curran Associates, 2016: 3837-3845.
[24]	CHEN T Q, GUESTRIN C. XGBoost: a scalable tree Boosting system[C]// Proceedings of the 22nd ACM SIGKDD Interna-tional Conference on Knowledge Discovery and Data Mining, San Francisco, Aug 13-17, 2016. New York: ACM, 2016: 785-794.
[25]	WANG L Y, CHAI D, LIU X Z, et al. Exploring the generalizability of spatio-temporal crowd flow prediction: meta-modeling and an analytic framework[J]. arXiv: 2009. 09379, 2020.
[26]	VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph attention networks[J]. arXiv: 1710. 10903, 2017.

键	值（含义）
TimeRange	数据的时间范围
TimeFitness	数据的时间粒度
Node	存储节点型数据
Grid	存储网格型数据
ExternalFeature	存储外部特征

键	值（含义）
TimeRange	数据的时间范围
TimeFitness	数据的时间粒度
Node	存储节点型数据
Grid	存储网格型数据
ExternalFeature	存储外部特征

接口名称	接口功能
GridTrafficLoader	读取并预处理网格型数据
NodeTrafficLoader	读取并预处理节点型数据
ST_MoveSample	以不同间隔采样时序数据
GraphGenerator	产生不同类型的图

接口名称	接口功能
GridTrafficLoader	读取并预处理网格型数据
NodeTrafficLoader	读取并预处理节点型数据
ST_MoveSample	以不同间隔采样时序数据
GraphGenerator	产生不同类型的图

模型	时间知识	空间知识
ARIMA^[2]	√	—
HM	√	—
XGBoost^[24]	√	—
ST-ResNet^[12]	√	√
DCRNN^[14]	√	√
ST-MGCN^[16]	√	√
STMeta^[25]	√	√

UCTB：时空人群流动预测工具箱

UCTB: Spatiotemporal Crowd Flow Prediction Toolbox

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 26

相关文章 15

编辑推荐

Metrics

高级模型层	模型层描述
DCGRU^[14]	同时建模时空关联
GCLSTM^[15]	同时建模时空关联
GCL^[23]	基于ChebNet谱域图卷积
GAL^[26]	图注意层

模块	接口	接口功能
训练	MiniBatchFeedDict	分批训练
训练	EarlyStopping	早停机制
评估	RMSE/MAPE	评估模型

[1]	赵学武, 王红梅, 刘超慧, 李玲玲, 薄树奎, 冀俊忠. 面向人脑功能划分的人工水母搜索优化算法[J]. 计算机科学与探索, 2022, 16(8): 1829-1841.
[2]	郭金鑫, 张广婷, 张云泉, 陈泽华, 贾海鹏. Cooley-Tukey FFT算法高性能实现与优化研究[J]. 计算机科学与探索, 2022, 16(6): 1304-1315.
[3]	魏光, 钱德沛, 杨海龙, 栾钟治. 程序能耗测量分析工具FPowerTool及其能耗优化实践[J]. 计算机科学与探索, 2022, 16(6): 1291-1303.
[4]	毛伊敏, 耿俊豪. 结合信息论和范数的并行随机森林算法[J]. 计算机科学与探索, 2022, 16(5): 1064-1075.
[5]	李金红, 王丽珍, 周丽华. 模糊特征的top-k平均效用co-location模式挖掘[J]. 计算机科学与探索, 2022, 16(5): 1053-1063.
[6]	张少伟, 王鑫, 陈子睿, 王林, 徐大为, 贾勇哲. 有监督实体关系联合抽取方法研究综述[J]. 计算机科学与探索, 2022, 16(4): 713-733.
[7]	蒋祎莹, 张丽平, 金飞虎, 郝晓红. 空间数据库中混合数据组最近邻查询[J]. 计算机科学与探索, 2022, 16(2): 348-358.
[8]	李朝阳, 李琳, 陶晓辉. 面向动态交通流预测的双流图卷积网络[J]. 计算机科学与探索, 2022, 16(2): 384-394.
[9]	赵恒泰, 赵宇海, 袁野, 季航旭, 乔百友, 王国仁. 分布式环境下大规模维表关联技术优化[J]. 计算机科学与探索, 2022, 16(2): 337-347.
[10]	刘卫明, 张弛, 毛伊敏. 采用N-list结构的混合并行频繁项集挖掘算法[J]. 计算机科学与探索, 2022, 16(1): 120-136.
[11]	宗枫博, 赵宇海, 王国仁, 季航旭. 面向多表数据连接投影和连接顺序的优化方法[J]. 计算机科学与探索, 2022, 16(1): 106-119.
[12]	林洪武 1,2 , 尤朝 1,2 , 周明辉1,2+ , 梅宏 1,2 . 以代理为中心的 OSGi 构件资源监控方法[J]. 计算机科学与探索, 2011, 5(1): 23-31.
[13]	朱小虎1,2 , 宋文军1,2 , 王崇骏1,2+ , 谢俊元1,2 . 用于社团发现的Girvan-Newman改进算法[J]. 计算机科学与探索, 2010, 4(12): 1101-1108.
[14]	曾红卫+, 缪淮扣 . 模型检验在构件数据流测试中的应用[J]. 计算机科学与探索, 2010, 4(12): 1121-1130.
[15]	袁崇义1,2 , 黄雨1,2,3+ , 赵文1,2,3 , 黄舒志2 . 操作表达式的Petri网表示*[J]. 计算机科学与探索, 2010, 4(11): 961-976.