Discovering City Dynamics through Sports Tracking Applications

Abstract

Researchers can use kernel density estimation to analyze spatiotemporal data from mobile devices to uncover human mobility patterns in urban spaces. Such analysis can support various applications ranging from location-based services to urban planning. To better understand city dynamics, we analyzed a large dataset of mobility tracks related to various sports activities. For this purpose, we applied kernel density estimation (KDE) to our data to efficiently analyze changes over time and space. Using KDE to identify these areas enables several novel applications. For example, researchers can compare such areas to the urban infrastructure to assess how people use parks, bike routes, and so on. They also can partition such areas among user groups to highlight differences in the routine behavior of various demographic and social communities.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 7 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.