Exploring the utilization of places through a scalable “Activities in Places” analysis mechanism

People sensing data have been successfully utilized in various domains to support a more livable place with on-demand transport system, green environment, profitable economy and interactive governance, however, their potentials in supporting the design of places are not widely studied and explained. As an on-going multidisciplinary project in Singapore, “Livable Places” mins valuable insights from these data through a novel mechanism, called Scalable “Activities in Places” Analysis Mechanism (SAPAM), which conducts three kinds of analyses on their spatial, temporal and textual information respectively to reveal frequently used places, called Hot Places (HP), and to measure their utilization quantitively and qualitatively for a better understanding of design contexts. Accordingly, three analysis mechanisms are designed and implemented, namely 1) a Scalable sPace Clustering Mechanism (SPCM) based on spatial information to cluster geo-referenced data, 2) a Hot Place Detection Mechanism (HPDM) based on temporal information to detect frequently used places, and 3) a Discussing Topic Detection Mechanism (DTDM) based on textual information to explore people's activities in a place. As proved by a comprehensive evaluation, 1) SPCM, which implements a scalable version of DBSCAN, indeed, can dramatically improve the clustering performance from the baseline 53.57s to less than 5s; 2) HPDM can precisely detect HPs with a high recall of Singaporean regional centers, main transportation hubs and famous attractions; and 3) DTDM classifies discussing topics of a given HP with a high precision about 85%. As the project testbed, Jurong East is detailedly investigated, and comparing to other Singaporean regional centers, it is marked as a growing regional center with a prosperous and stable commercial ecosystem.