Identifying Critical Urban Intersections from a Fine-grained Spatio-Temporal Perspective.
Recommended citation: Zilong Zhao, Luliang Tang, Mengyuan Fang, Xue Yang, Chaokui Li, Qingquan Li (2023). Toward urban traffic scenarios and more: a spatio-temporal analysis empowered low-rank tensor completion method for data imputation. International Journal of Geographical Information Science, 1-34. http://zilzhao.github.io/files/Traffic_data_imputation.pdf
Funded by the National Key R&D Program of China (No. 2017YFB0503604)
• Adopt a manifold embedding approach to depict the local geometric structure of spatio-temporal domains, and propose a novel Spatio-Temporal constrained Low-Rank Tensor Completion (ST-LRTC) method.
• The proposed method achieves stable and accurate imputation results even in extreme scenarios with large missing rates or non-random missing patterns.
• This study won the Grand Prize of the 12th National College Students’ Science and Technology Thesis Competition on Surveying and Mapping; Excellent Bachelor’s Thesis of Wuhan University (2021).
Recommended citation: Zilong Zhao**, Luliang Tang, Mengyuan Fang, Xue Yang, Chaokui Li, Qingquan Li (2023). Toward urban traffic scenarios and more: A spatio-temporal analysis empowered low-rank tensor completion method for data imputation. International Journal of Geographical Information Science. DOI: 10.1080/136588 16.2023.2234434. (SCI, JCR Q1, IF=5.7, **TOP Journal in GIS))