Location2vec: A Situation-Aware Representation for Visual Exploration of Urban Locations

• Published in: IEEE transactions on intelligent transportation systems Vol. 20; no. 10; pp. 3981 - 3990
• Main Authors: Zhu, Minfeng, Chen, Wei, Xia, Jiazhi, Ma, Yuxin, Zhang, Yankong, Luo, Yuetong, Huang, Zhaosong, Liu, Liangjun
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.10.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Embedding; Exploration; Human mobility; Mobile handsets; Natural language processing; Representations; Situational awareness; Sociology; spatio-temporal data; Statistics; Trajectory; Transportation management; urban computing; Urban planning; Vehicle dynamics; visual exploration; Visualization; word embedding
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2019.2901117

Understanding the relationship between urban locations is an essential task in urban planning and transportation management. Although prior works have focused on studying urban locations by aggregating location-based properties, our scheme preserves the mutual influence between urban locations and mobility behavior, and thereby enables situation-aware exploration of urban regions. By leveraging word embedding techniques, we encode urban locations with a vectorized representation while retaining situational awareness. Specifically, we design a spatial embedding algorithm that is precomputed by incorporating the interactions between urban locations and moving objects. To explore our proposed technique, we have designed and implemented a web-based visual exploration system that supports the comprehensive analysis of human mobility, location functionality, and traffic assessment by leveraging the proposed visual representation. The case studies demonstrate the effectiveness of our approach.