Prediction of Crowd Flow in City Complex with Missing Data

Shiyang Qiu, Peng Xu, Wei Zheng, Junjie Wang, Guo Yu, Mingyao Hou, Hengchang Liu
Proceedings of The Eleventh Asian Conference on Machine Learning, PMLR 101:758-773, 2019.

Abstract

Crowd flow forecasting plays an important role in risk assessment and public safety. It is a difficult task due to complex spatial-temporal dependencies as well as missing values in data. A number of models are proposed to predict crowd flow on city-scale, yet the missing pattern in city complex environment is seldomly considered. We propose a crowd flow forecasting model, Imputed Spatial-Temporal Convolution network(ISTC) to accurately predict the crowd flow in large complex buildings. ISTC uses convolution layers, whose structures are configured by graphs, to model the spatial-temporal correlations. Meanwhile ISTC adds imputation layers to handle the missing data. We demonstrate our model on several real data sets collected from sensors in a large six-floor commercial complex building. The results show that ISTC outperforms the baseline methods and is capable of handling data with as much as 40% missing data.

Cite this Paper


BibTeX
@InProceedings{pmlr-v101-qiu19a, title = {Prediction of Crowd Flow in City Complex with Missing Data}, author = {Qiu, Shiyang and Xu, Peng and Zheng, Wei and Wang, Junjie and Yu, Guo and Hou, Mingyao and Liu, Hengchang}, booktitle = {Proceedings of The Eleventh Asian Conference on Machine Learning}, pages = {758--773}, year = {2019}, editor = {Lee, Wee Sun and Suzuki, Taiji}, volume = {101}, series = {Proceedings of Machine Learning Research}, month = {17--19 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v101/qiu19a/qiu19a.pdf}, url = {https://proceedings.mlr.press/v101/qiu19a.html}, abstract = {Crowd flow forecasting plays an important role in risk assessment and public safety. It is a difficult task due to complex spatial-temporal dependencies as well as missing values in data. A number of models are proposed to predict crowd flow on city-scale, yet the missing pattern in city complex environment is seldomly considered. We propose a crowd flow forecasting model, Imputed Spatial-Temporal Convolution network(ISTC) to accurately predict the crowd flow in large complex buildings. ISTC uses convolution layers, whose structures are configured by graphs, to model the spatial-temporal correlations. Meanwhile ISTC adds imputation layers to handle the missing data. We demonstrate our model on several real data sets collected from sensors in a large six-floor commercial complex building. The results show that ISTC outperforms the baseline methods and is capable of handling data with as much as 40% missing data.} }
Endnote
%0 Conference Paper %T Prediction of Crowd Flow in City Complex with Missing Data %A Shiyang Qiu %A Peng Xu %A Wei Zheng %A Junjie Wang %A Guo Yu %A Mingyao Hou %A Hengchang Liu %B Proceedings of The Eleventh Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Wee Sun Lee %E Taiji Suzuki %F pmlr-v101-qiu19a %I PMLR %P 758--773 %U https://proceedings.mlr.press/v101/qiu19a.html %V 101 %X Crowd flow forecasting plays an important role in risk assessment and public safety. It is a difficult task due to complex spatial-temporal dependencies as well as missing values in data. A number of models are proposed to predict crowd flow on city-scale, yet the missing pattern in city complex environment is seldomly considered. We propose a crowd flow forecasting model, Imputed Spatial-Temporal Convolution network(ISTC) to accurately predict the crowd flow in large complex buildings. ISTC uses convolution layers, whose structures are configured by graphs, to model the spatial-temporal correlations. Meanwhile ISTC adds imputation layers to handle the missing data. We demonstrate our model on several real data sets collected from sensors in a large six-floor commercial complex building. The results show that ISTC outperforms the baseline methods and is capable of handling data with as much as 40% missing data.
APA
Qiu, S., Xu, P., Zheng, W., Wang, J., Yu, G., Hou, M. & Liu, H.. (2019). Prediction of Crowd Flow in City Complex with Missing Data. Proceedings of The Eleventh Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 101:758-773 Available from https://proceedings.mlr.press/v101/qiu19a.html.

Related Material