Profiling urban activity hubs using transit smart card data

Rachel Cardell-Oliver, Travis Povey

Research output: Chapter in Book/Conference paperConference paper

2 Citations (Scopus)

Abstract

Understanding why and where people travel by public transport is a key enabler for smart cities because it informs city planning, daily operations, and sustainable city growth. This article introduces a data-driven approach using transit smart card data to discover where activities are concentrated and why people travel to those regions. Our approach is based on the idea of stays between passenger trips. A stay has an arrival time and a period of time spent in a certain region. The regions where stays are concentrated are called hubs. Coherent clusters of stays indicate human activities such as going to work or short errands. An efficient and robust algorithm is proposed for learning hubs and their activities. Triangulation with points of interest and ticket data validates that activity stays and hub activities satisfy common sense expectations. The utility of the activity hub profiles for urban planners and transport managers is demonstrated by use cases for operational, tactical and strategic goals.

Original languageEnglish
Title of host publicationBuildSys 2018 - Proceedings of the 5th Conference on Systems for Built Environments
EditorsGowri Sankar Ramachandran, Nipun Batra
Place of PublicationUSA
PublisherAssociation for Computing Machinery (ACM)
Pages116-125
Number of pages10
ISBN (Electronic)9781450359511
DOIs
Publication statusPublished - 7 Nov 2018
Event5th ACM International Conference on Systems for Built Environments, BuildSys 2018 - Shenzen, China
Duration: 7 Nov 20188 Nov 2018

Conference

Conference5th ACM International Conference on Systems for Built Environments, BuildSys 2018
CountryChina
CityShenzen
Period7/11/188/11/18

Fingerprint

Urban planning
Smart cards
Triangulation
Managers
Smart city

Cite this

Cardell-Oliver, R., & Povey, T. (2018). Profiling urban activity hubs using transit smart card data. In G. S. Ramachandran, & N. Batra (Eds.), BuildSys 2018 - Proceedings of the 5th Conference on Systems for Built Environments (pp. 116-125). USA: Association for Computing Machinery (ACM). https://doi.org/10.1145/3276774.3276778
Cardell-Oliver, Rachel ; Povey, Travis. / Profiling urban activity hubs using transit smart card data. BuildSys 2018 - Proceedings of the 5th Conference on Systems for Built Environments. editor / Gowri Sankar Ramachandran ; Nipun Batra. USA : Association for Computing Machinery (ACM), 2018. pp. 116-125
@inproceedings{8d348d11884b4d6a99d2af72e0e17502,
title = "Profiling urban activity hubs using transit smart card data",
abstract = "Understanding why and where people travel by public transport is a key enabler for smart cities because it informs city planning, daily operations, and sustainable city growth. This article introduces a data-driven approach using transit smart card data to discover where activities are concentrated and why people travel to those regions. Our approach is based on the idea of stays between passenger trips. A stay has an arrival time and a period of time spent in a certain region. The regions where stays are concentrated are called hubs. Coherent clusters of stays indicate human activities such as going to work or short errands. An efficient and robust algorithm is proposed for learning hubs and their activities. Triangulation with points of interest and ticket data validates that activity stays and hub activities satisfy common sense expectations. The utility of the activity hub profiles for urban planners and transport managers is demonstrated by use cases for operational, tactical and strategic goals.",
keywords = "Activity discovery, Human mobility, Public transportation, Smart-card data, Travel behaviour, Urban computing",
author = "Rachel Cardell-Oliver and Travis Povey",
year = "2018",
month = "11",
day = "7",
doi = "10.1145/3276774.3276778",
language = "English",
pages = "116--125",
editor = "Ramachandran, {Gowri Sankar} and Nipun Batra",
booktitle = "BuildSys 2018 - Proceedings of the 5th Conference on Systems for Built Environments",
publisher = "Association for Computing Machinery (ACM)",
address = "United States",

}

Cardell-Oliver, R & Povey, T 2018, Profiling urban activity hubs using transit smart card data. in GS Ramachandran & N Batra (eds), BuildSys 2018 - Proceedings of the 5th Conference on Systems for Built Environments. Association for Computing Machinery (ACM), USA, pp. 116-125, 5th ACM International Conference on Systems for Built Environments, BuildSys 2018, Shenzen, China, 7/11/18. https://doi.org/10.1145/3276774.3276778

Profiling urban activity hubs using transit smart card data. / Cardell-Oliver, Rachel; Povey, Travis.

BuildSys 2018 - Proceedings of the 5th Conference on Systems for Built Environments. ed. / Gowri Sankar Ramachandran; Nipun Batra. USA : Association for Computing Machinery (ACM), 2018. p. 116-125.

Research output: Chapter in Book/Conference paperConference paper

TY - GEN

T1 - Profiling urban activity hubs using transit smart card data

AU - Cardell-Oliver, Rachel

AU - Povey, Travis

PY - 2018/11/7

Y1 - 2018/11/7

N2 - Understanding why and where people travel by public transport is a key enabler for smart cities because it informs city planning, daily operations, and sustainable city growth. This article introduces a data-driven approach using transit smart card data to discover where activities are concentrated and why people travel to those regions. Our approach is based on the idea of stays between passenger trips. A stay has an arrival time and a period of time spent in a certain region. The regions where stays are concentrated are called hubs. Coherent clusters of stays indicate human activities such as going to work or short errands. An efficient and robust algorithm is proposed for learning hubs and their activities. Triangulation with points of interest and ticket data validates that activity stays and hub activities satisfy common sense expectations. The utility of the activity hub profiles for urban planners and transport managers is demonstrated by use cases for operational, tactical and strategic goals.

AB - Understanding why and where people travel by public transport is a key enabler for smart cities because it informs city planning, daily operations, and sustainable city growth. This article introduces a data-driven approach using transit smart card data to discover where activities are concentrated and why people travel to those regions. Our approach is based on the idea of stays between passenger trips. A stay has an arrival time and a period of time spent in a certain region. The regions where stays are concentrated are called hubs. Coherent clusters of stays indicate human activities such as going to work or short errands. An efficient and robust algorithm is proposed for learning hubs and their activities. Triangulation with points of interest and ticket data validates that activity stays and hub activities satisfy common sense expectations. The utility of the activity hub profiles for urban planners and transport managers is demonstrated by use cases for operational, tactical and strategic goals.

KW - Activity discovery

KW - Human mobility

KW - Public transportation

KW - Smart-card data

KW - Travel behaviour

KW - Urban computing

UR - http://www.scopus.com/inward/record.url?scp=85058414421&partnerID=8YFLogxK

U2 - 10.1145/3276774.3276778

DO - 10.1145/3276774.3276778

M3 - Conference paper

SP - 116

EP - 125

BT - BuildSys 2018 - Proceedings of the 5th Conference on Systems for Built Environments

A2 - Ramachandran, Gowri Sankar

A2 - Batra, Nipun

PB - Association for Computing Machinery (ACM)

CY - USA

ER -

Cardell-Oliver R, Povey T. Profiling urban activity hubs using transit smart card data. In Ramachandran GS, Batra N, editors, BuildSys 2018 - Proceedings of the 5th Conference on Systems for Built Environments. USA: Association for Computing Machinery (ACM). 2018. p. 116-125 https://doi.org/10.1145/3276774.3276778