Analytics of movement through checkpoints

A Data Science Framework for Movement

“…Data science and big data analytics provide promising tools for understanding and prediction of dynamic processes in human and natural systems using large arrays of Eulerian‐type data sets (Tao et al. 2018; Sowmya and Suneetha 2017; Miller 2010). Computational movement studies have yet to fully embrace and extend the potential of data science approaches for movement data analytics based on the Lagrangian approach.…”

“…While our ability to observe movement with the Lagrangian perspective have improved through modern trackers, the access to these types of trajectories remains limited due to the higher cost of data collection and concerns over the privacy of observed individuals. Data science and big data analytics provide promising tools for understanding and prediction of dynamic processes in human and natural systems using large arrays of Euleriantype data sets (Tao et al, 2018;Sowmya and Suneetha, 2017;Miller, 2010). Computational movement studies have yet to fully embrace and extend the potential of data science approaches for movement data analytics based on the Lagrangian approach.…”

“…2013), camera‐traps (Karanth and Nichols 1998) and surveillance cameras (Choi, Pantofaru and Savarese 2013), checkpoint data (Tao et al. 2018), observations through IoT and Information Communications Technology (ICT) (Batty et al. 2012) and geosensor networks (Laube, Duckham, and Palaniswami 2011; Both et al.…”

“…While GIScience has significantly advanced computational movement analytics (Long et al, 2018), with the emergence of new forms of movement data, new interdisciplinary approaches are needed to revolutionize the way we analyze and model movement. Examples of these new forms of movement data include trajectory data streams (Coelho et al, 2016), or data obtained from wearable motion sensors equipped with magnetometers and accelerometers (Akhavian and Behzadan, 2015;Shoaib et al, 2014;Nathan et al, 2012), social network activities (Mckenzie et al, 2013;Azmandian et al, 2013), contextual data from remote sensing (Dodge et al, 2013), camera-traps (Karanth and Nichols, 1998) and surveillance cameras (Choi et al, 2013), checkpoint data (Tao et al, 2018), observations through IoT and Information Communications Technology (ICT) (Batty et al, 2012) and geosensor networks (Laube et al, 2011;Both et al, 2013). As movement data become increasingly available at large volumes, high dimensions, and multiple granularities, development of new computational data analytics and modeling approaches have gained momentum to advance movement research (Thums et al, 2018;Kays et al, 2015;Demšar et al, 2015;Dodge et al, 2013).…”

Contextual Awareness in Human-Advanced-Vehicle Systems: A Survey

“…As the amount of data by context-aware movement analytics make the activity analysis more complex, Tao et al [172] proposed a framework to use checkpoint data (e.g., credit card swipes, electronic toll collection points). The framework was used to identify vehicle type from checkpoint data, the model relied on: 1) a cordon network, which is a set of vertices (regions of space), and edges (pathways for direct movement between regions); and 2) observations of movement, such as sensor ID, moving object, time of transaction, environmental attributes, time during the object was detected as present in a region.…”