SAPAM: A scalable "activities in places" is mechanism for informed place design

Linlin You, Bige Tunçer

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

3 Citaten (Scopus)

Samenvatting

As a novel concept, "Informed Design" is being practiced in the Future Cities Laboratory at the Singapore-ETH Centre to innovate place design from empirical to evidential by harnessing geo-referenced "Big Data" for a responsive design. Initially, potentials of people sensing data derived from multi-sources, such as social networks, dedicated applications, sensors, etc., shall be explored to measure place utilization for a better understanding of design contexts and elicitation of design requirements. Therefore, an "Activities in Places"service is required to detect frequently used places, called hot places (HPs), and measure their utilizations in various dimensions. In order to fulfill emerging requirements and properly handle big and heterogeneous geo-located data in a near-real time manner for a responsive design, a unsupervised method, called Scalable "Activities in Places" Analysis Mechanism (SAPAM), is proposed with two main analysis mechanisms, namely 1) a scalable density-based spatial clustering of applications with noise (SDBSCAN), which dramatically improves the performance of DBSCAN through concurrent clusterings on data partitions, 2) a hot place detection procedure (HPDP) to extract HPs from clusters based on a continuous place usage pattern (CPUP), and analyze performed activities through a topic model trained by a corpus of daily documents of places. As proved by a comprehensive evaluation, 1) SDBSCAN, indeed, greatly improves the performance as shown by its best performance 4.71s, which is 11 times faster than DBSCAN, 2) HPDP can precisely detect HPs with a high recall of Singaporean regional centers, main transportation hubs and famous attractions, and 3) the utilization of HPs can be unveiled by three indicators, namely the number of visitors, the size of influence area, and the density of people, and also by performed activities in HPs. As a case study, three top 10 HP lists of three utilization indexes are created, and performed activities in a regional center Jurong East are analyzed.

Originele taal-2Engels
TitelProceedings - 3rd IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2016
UitgeverijAssociation for Computing Machinery, Inc
Pagina's158-167
Aantal pagina's10
ISBN van elektronische versie9781450346177
DOI's
StatusGepubliceerd - 6 dec. 2016
Extern gepubliceerdJa
Evenement3rd IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2016 - Shanghai, China
Duur: 6 dec. 20169 dec. 2016

Congres

Congres3rd IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2016
Land/RegioChina
StadShanghai
Periode6/12/169/12/16

Bibliografische nota

Publisher Copyright:
© 2016 ACM.

Vingerafdruk

Duik in de onderzoeksthema's van 'SAPAM: A scalable "activities in places" is mechanism for informed place design'. Samen vormen ze een unieke vingerafdruk.

Citeer dit