Graph based embedding learning of trajectory data for transportation mode recognition by fusing sequence and dependency relations

Abstract

AbstractAs an important task in spatial data mining, trajectory transportation mode recognition can reflect various individual behaviors and traveling patterns in urban space. As trajectory is essentially a sequence, many scholars use the sequence inference models to mine the information in trajectory data. However, such methods often ignored the spatial correlation between trajectory points and implemented the evaluation based only on representative feature statistics selected in the trajectory data preprocessing stage, thus have difficulties in acquiring high-order traveling pattern features. In this study, we propose a novel ensemble recognition method for representing trajectory data with the graph structure based on sequence and dependency relations. This method integrates the sequence of trajectory points and the correlation between characteristic points of a travel path into a fused graph convolutional network to obtain semantic feature information at multiple levels. We validate our proposed method with experiments on the trajectory benchmark dataset from the Microsoft GeoLife project. The results demonstrated that our proposed graph network outperforms other baseline methods in the transportation mode recognition task of trajectories. This method can help to discover the movement patterns of urban residents, and further provide effective assistance for the management of cities.Keywords: Trajectory datagraph convolution networktransportation mode recognitionfeature extractionfeature fusion AcknowledgmentsThe authors are grateful to the associate editor, Urska Demsar, and the anonymous referees for their valuable comments and suggestions. The project was supported by the National Natural Science Foundation of China (42371446 and 42071442) and by the Fundamental Research Funds for the Central Universities, China University of Geosciences (Wuhan) (No.CUG170640). This research was also supported by Meituan.Author contributionsWenhao Yu: Conceptualization, methodology, formal analysis, validation, writing—original draft preparation, writing—review and editing, supervision, project administration, funding acquisition; Guanwen Wang: Methodology, validation, formal analysis, investigation, writing—original draft preparation, writing—review and editing, visualization. All authors have read and agreed to the published version of the manuscript.Disclosure statementNo potential conflict of interest was reported by the author(s).Data and codes availability statementThe data and codes that support the findings of this study are available with a DOI at (https://doi.org/10.6084/m9.figshare.21608310).Additional informationNotes on contributorsWenhao YuWenhao Yu received the B.S. and Ph.D. degrees in Geoinformatics from the Wuhan University, Wuhan, China, in 2010 and 2015, respectively. He is a professor at China University of Geosciences, Wuhan, China (CUG). His research interests include spatial data mining, map generalization, and deep learning.Guanwen WangGuanwen Wang is a master student in the School of Geography and Information Engineering, China University of Geosciences, Wuhan, China (CUG). Her research interests include deep learning and spatial data mining.