Accepted Paper: Prediction of Crowd Flow in City Complex with Missing Data
Back to list of accepted papers
- Session 3: Supervised and General Machine Learning -- Day 3 (Nov.19), talks: 10:50-11:30 (5th floor Hall 1), poster session: 11:30-14:00
- Poster number: Tue12
- Download paper
Authors
Shiyang Qiu (University of Science and Technology of China); Peng Xu (University of Science and Technology of China); Wei Zheng (Kehang Technology and Information); Wang Junjie (University of Science and Technology of China); Guo Yu (China People's Police University); Mingyao Hou (Kehang Technology and Information); Hengchang Liu (USTC)
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 and missing values in data. There have been some models that can predict crowd flow in 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.