Abstract
Urban areas of interest (AOIs) represent areas within the urban environment featuring high levels of public interaction, with their understanding holding utility for a wide range of urban planning applications.Within this context, our study proposes a novel space-time analytical framework and implements it to the taxi GPS data for the extent of Manhattan, NYC to identify and describe 31 road-constrained AOIs in terms of their spatiotemporal distribution and contextual characteristics. Our analysis captures many important locations, including but not limited to primary transit hubs, famous cultural venues, open spaces, and some other tourist attractions, prominent landmarks, and commercial centres. Moreover, we respectively analyse these AOIs in terms of their dynamics and contexts by performing further clustering analysis, formulating five temporal clusters delineating the dynamic evolution of the AOIs and four contextual clusters representing their salient contextual characteristics.
Highlights
Urban areas of interest (AOIs) can be broadly defined as areas within an urban environment that attract people’s attention, and which are often related to the generalisation of different types of urban economic activity (Hu et al, 2015; Yuan, Zheng, & Xie, 2012a)
The second phase is boundary-defining, which is responsible for con verting the detected taxi hotspots into road-constrained AOIs through the K-Nearest Neighbour (KNN) algorithm that aggerates point clusters to their nearest road segments
Because of the uncertainties caused by inevitable measurement error of GPS, offset between the observed location and the actual location may be a feature of the data inputs: vehicle GPS location should align with the road network (Yang & Gidofalvi, 2018). Taking such concerns into account, we argue that the road network is a more organic carrier of the detected point clusters, which can be employed to define the boundary of urban AOIs, for an application utilising taxi data since they bound these patterns of mobility (Ma et al, 2019; Yuan, Zheng, & Xie, 2012b)
Summary
Urban areas of interest (AOIs) can be broadly defined as areas within an urban environment that attract people’s attention, and which are often related to the generalisation of different types of urban economic activity (Hu et al, 2015; Yuan, Zheng, & Xie, 2012a). Due to the wide range of applications of AOIs, successfully identifying and understanding the characteristics of such urban areas could provide a useful reference basis that benefits multiple stakeholders, including but not limited to tourism management (van der Zee, Bertocchi, & Vanneste, 2020), the identifi cation of social functions (Zhou, Liu, Qian, Chen, & Tao, 2019), urban environmental study (Chen, Arribas-Bel, & Singleton, 2020), urban vi tality analysis (Kim, 2018), traffic planning (Alfeo, Cimino, Egidi, Lepri, & Vaglini, 2018), and public transit management (Ni, Huang, Meng, Zhou, & Su, 2019). A traditional approach to investigate AOIs is primarily dependent on data derived from questionnaire-based methods such as field surveys or travel diaries These approaches are labour-intensive, timeconsuming, and error-prone, limiting their usefulness and appli cability for large geographic areas (Yuan & Raubal, 2012). Numerous previous studies have implemented data mining techniques on heterogeneous data sources to identify urban AOIs, for instance, check-in data from social media (Chen et al, 2019; Hu et al, 2015; Kuo, Chan, Fan, & Zipf, 2018; Üsküplü, Terzi, & Kartal, 2020), location data from mobile phones (Yang, Zhao, & Lu, 2016), and point of interest (POI) data from commercial location search engines (Xu, Cui, Zhong, & Wang, 2019)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
