The document discusses using big data and new technologies to improve transport planning and operations. It provides examples of collecting lifelogging data through wearable sensors to analyze travel behavior, crowdsourced bicyclist data to evaluate infrastructure investments, and using various data sources to examine links between transport and labor market outcomes. The document emphasizes that transport systems need to be re-evaluated in some areas to better match changing job locations and needs of workers.
Polis Conference 2015: OGD for bicycle promotionMartin L
In this presentation I demonstrate how the standardization and publication of authoritative road data as OGD can boost efforts in bicycle promotion. The case study is from Salzburg, Austria, where a comprehensive bicycle routing portal (www.radlkarte.info) is fueld by OGD.
Agent-based simulation of bicycle traffic - Background informationMartin L
Brief introduction for a student project which deals with the possibilities of agent-based simulation approaches for estimating bicycle traffic in an urban road network.
Lessons learned from the winter cycling surveyMartin L
For a recently finished project we conducted an online survey on winter cycling in February 2015. The outcome serve as evidence basis for future developments of information tools for winter cyclists.
Apart from the results as such (which were enormously helpful, to some extent surprising and indeed relevant for what we are doing), we have learned quite a lot about the winter cycling community and how to engage with them. Additionally some fundamental and methodological insights could have been gained.
Polis Conference 2015: OGD for bicycle promotionMartin L
In this presentation I demonstrate how the standardization and publication of authoritative road data as OGD can boost efforts in bicycle promotion. The case study is from Salzburg, Austria, where a comprehensive bicycle routing portal (www.radlkarte.info) is fueld by OGD.
Agent-based simulation of bicycle traffic - Background informationMartin L
Brief introduction for a student project which deals with the possibilities of agent-based simulation approaches for estimating bicycle traffic in an urban road network.
Lessons learned from the winter cycling surveyMartin L
For a recently finished project we conducted an online survey on winter cycling in February 2015. The outcome serve as evidence basis for future developments of information tools for winter cyclists.
Apart from the results as such (which were enormously helpful, to some extent surprising and indeed relevant for what we are doing), we have learned quite a lot about the winter cycling community and how to engage with them. Additionally some fundamental and methodological insights could have been gained.
Spatial analysis and modelling of bicycle accidents and safety threatsMartin L
This presentation was given at the International Cycling Safety Congress 2015 in Hannover/Germany.
I have argued, that bicycle accidents are spatial by their very nature. Thus GIS analysis and geospatial models can help to gain a better understanding of bicycle accidents and to develop evidence-based safety strategies.
An agent-based simulation model for estimating bicycle flows at the local scale level.
Presentation slides from International Cycling Safety Congress (ICSC) 2018 in Barcelona.
Safety and accessibility as major keys for bicycle-friendly citiesMartin L
Bikeability can significantly contribute to liveable cities. This presentation presents 3 spatial analysis tools that support planners and decision makers in their effort for more bicycle-friendly cities. The presentation was given at a miniconference on "Quality of Life" at the Department of Geoinformatics, University of Salzburg
Planning for accessibility in growing citiespeter_kant
How to keep your city/region accessible if there is no such thing as an average day? The transport network is contiously under disruption due to roadworks and events. Inhabitants, visitors and companies are faced with (unexpected) hindrance. The Road Works Optimizer is a planning instrument that helps cities in optimizing their road works and event schedules to minimize hindrance.
Innovations in London's Transport: Big Data for a Better Customer ServiceGovnet Events
Presentation on Innovations in London's Transport: Big Data for a Better Customer Service by Andrew Hyman, TFL at HPC and Big Data 2016 in Central London
Spatial analysis and modelling of bicycle accidents and safety threatsMartin L
This presentation was given at the International Cycling Safety Congress 2015 in Hannover/Germany.
I have argued, that bicycle accidents are spatial by their very nature. Thus GIS analysis and geospatial models can help to gain a better understanding of bicycle accidents and to develop evidence-based safety strategies.
An agent-based simulation model for estimating bicycle flows at the local scale level.
Presentation slides from International Cycling Safety Congress (ICSC) 2018 in Barcelona.
Safety and accessibility as major keys for bicycle-friendly citiesMartin L
Bikeability can significantly contribute to liveable cities. This presentation presents 3 spatial analysis tools that support planners and decision makers in their effort for more bicycle-friendly cities. The presentation was given at a miniconference on "Quality of Life" at the Department of Geoinformatics, University of Salzburg
Planning for accessibility in growing citiespeter_kant
How to keep your city/region accessible if there is no such thing as an average day? The transport network is contiously under disruption due to roadworks and events. Inhabitants, visitors and companies are faced with (unexpected) hindrance. The Road Works Optimizer is a planning instrument that helps cities in optimizing their road works and event schedules to minimize hindrance.
Innovations in London's Transport: Big Data for a Better Customer ServiceGovnet Events
Presentation on Innovations in London's Transport: Big Data for a Better Customer Service by Andrew Hyman, TFL at HPC and Big Data 2016 in Central London
Case Studies in Managing Traffic in a Developing Country with Privacy-Preserv...Biplav Srivastava
Simulation is known to be an effective technique to understand
and manage traffic in cities of developed countries. However, in developing countries, traffic management is lacking due to a wide diversity of vehicles on the road, their chaotic movement, little instrumentation to sense traffic state and limited funds to create IT and physical infrastructure to ameliorate the situation. Under these conditions, in this paper, we present our approach of using the Megaffic traffic simulator as a service to gain actionable insights for two use-cases and cities in India, a first. Our approach is general to be readily used in other use cases and cities; and our results give new insights: (a) using demographics data, traffic demand can be reduced if timings of government offices are altered in Delhi, (b) using a mobile company’s Call
Data Record (CDR) data to mine trajectories anonymously,
one can take effective traffic actions while organizing events
in Mumbai at local scale.
Vision on Smart Urban Mobility given during the AITPM conference in Sydney. Talk was about key elements needed to provide the urban transportation system for the future. See http://www.aitpm.com.au/Conference/Program/conference-home for the conference details.
Short talk impact Covid-19 on supply and demand during the RA webinarSerge Hoogendoorn
We sketch a conceptual framework showing (lasting) impact on demand and supply. We illustrate complications at the supply side due to changing behaviour. We show how to include interventions and how to assess them.
Examining challenges in data collection and use for better urban transport policy. Presented by Jerome Pourbaix at Transforming Transportation 2015.
Transforming Transportation 2015: Smart Cities for Shared Prosperity is the annual conference co-organized by the World Resources Institute and the World Bank.
The presentation was illustrated at the CEEM CoP Webinar: “Achieving Low Carbon Mobility: Urban Transportation Modelling, Public Awareness and Behavioural Change" on tge 10th of October 2013
CEEM CoP stands for Community Energy and Emissions Modelling (CEEM) Community of Practice (CoP).
CEEM CoP is an informal group supporting CEEM practitioners and local governments in furthering greenhouse gas modelling, target-setting and action in communities across BC – www.toolkit.bc.ca/ceem
Mobility is an important part of daily life. Progressive community planning and transportation design can greatly reduce the need for automobile travel, instead providing a diverse range of active transportation alternatives.
This presentation on the CATCH project looks at how transportation-related data can be used to understand a city’s travel footprint and help to inform city planning and programs to promote individual behaviour change.
It reviews the findings and lessons learned from the ‘CATCH Project’ (Carbon Aware Travel Choice): a 2 million euro-funded project, involving 11 partners across 6 European Union countries, aimed to develop a knowledge platform to help urban communities move to less carbon-intensive transportation systems. This presentation touches on the important role of developing a system to compare and contrast best practices, identify the many motivators for change to low carbon mobility, and use tools for engaging the public and decision makers to support innovation and change.
A presentation by Jack van der Merwe (Chief Executive Officer: Gautrain Management Agency), at the Transport Forum SIG: "Cost Effective Public Transport Management Systems" on 12 May 2016 hosted by University of Johannesburg. The theme of the presentation was: "Is profitable public transport possible?"
A low cost method of real time pavement condition data sharing to expedite ma...UVision
A low cost method of real time pavement condition data sharing to expedite maintenance intervention
Pavements for roads in cities and highways are degraded with potholes, cracking, and rutting distresses. There is a strong need to identify these locations and sections with undesired longitudinal roughness quickly and accurately every year. Traditionally, expensive standalone survey vehicles for roughness measurements and more expensive multi-function vehicles are employed by highway agencies or through contract services, which most cities and local agencies can’t afford. The primary objective of this study is to describe a low cost method to collect essential pavement condition data and share real time to expedite maintenance intervention needs. This facilitates rapid identification of pavement sections with undesired longitudinal roughness and local defects. This paper discusses the impact of social media, crowd sourcing, and advances in cheaper accurate motion sensors and cloud server data processing. These tools make it possible to develop easy-to-use low cost methods, which are affordable by city public work and smaller road agencies.
With collaborations with various City divisions and private service providers (in this case Streetlight data providers), our North York mobility innovation team uncovered several surprising suburban travel behaviour, patterns and distributions of trips that lead to meaningful and quantitative multimodal mobility planning. This presentation is a summary of project experiences and describes the key findings.
Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...John Andrews
SlideShare Description for "Chatty Kathy - UNC Bootcamp Final Project Presentation"
Title: Chatty Kathy: Enhancing Physical Activity Among Older Adults
Description:
Discover how Chatty Kathy, an innovative project developed at the UNC Bootcamp, aims to tackle the challenge of low physical activity among older adults. Our AI-driven solution uses peer interaction to boost and sustain exercise levels, significantly improving health outcomes. This presentation covers our problem statement, the rationale behind Chatty Kathy, synthetic data and persona creation, model performance metrics, a visual demonstration of the project, and potential future developments. Join us for an insightful Q&A session to explore the potential of this groundbreaking project.
Project Team: Jay Requarth, Jana Avery, John Andrews, Dr. Dick Davis II, Nee Buntoum, Nam Yeongjin & Mat Nicholas
1. Transport Planning and Operations with
Big Data
Piyushimita (Vonu) Thakuriah
Director, Urban Big Data Centre
and
Ch2m Chair Professor of Transport
UNIVERSITY OF GLASGOW, UK
July 10, 2015
2. Urban Big Data CentreUrban Big Data Centre
Changing Nature of Transport
▪ Autonomous
▪ Connected, cooperative, anticipatory
▪ Shared – “uberification”
▪ Integrated with other services – Mobility
as a Service
3. Urban Big Data CentreUrban Big Data Centre
Trends
Courtesy ETSI
An
explosion
of ICT
solutions
and data
Disruptive
Technology and
Effects on Travel
Behaviour
Previous Link
▪ Increase in speed
New link
▪ Substitution?
▪ Complementary?
▪ Modification?
4. Urban Big Data CentreUrban Big Data CentreTrends…
Peak Car – End of Carmageddon? Declining Millennial Travel
Economic
Recession as
Natural
Experiment?
Peak Oil and Energy Futures
Significant Infrastructure
Funding Shortfalls
Rise in Human-Powered Transportation
Transportation
ExpenditureUSD
http://www.economist.com/node/21563280
5. Urban Big Data Centre
Example 1 – designing and collecting data
from wearable tech
Vonu Thakuriah
Katarzyna Sila-Nowicka
Mesut Yucel
Christina Boididou
6. Lifelogging
A custom 136° eye view lens,
an ultra small GPS unit,
Bluetooth, and 5 in-built
sensors - ambient light /
accelerometer / magnetometer
/ PIR / temperature
Autographer - Still pictures
every 5 seconds both outdoors
and indoors
▪ Lifelogging through
wearable sensors – a
multimedia personal
archive
▪ Image data on citizens’
everyday living
▪ Digital image processing to
retrieve data on multiple
factors on which it is
difficult to survey people
Outdoors Indoors
Research possibilities:
▪ Travel behaviour
research
▪ Driving styles and
eco-friendly
behaviour
▪ Fine-grained data on
quality of built
environment
▪ Social networks
▪ Many others
7. Urban Big Data Centre
Anonymization
Spatial Cloaking of GPS Trajectories
De-identifying image data
Privacy is of paramount importance!
Sila-Nowicka, K., and Thakuriah, P. (2016) The
trade-off between privacy and geographic data
resolution. a case of GPS trajectories combined
with the social survey results. In: XXIII ISPRS
Congress, Prague, Czech Republic, 12-19 Jul
2016, pp. 535-542.
Yucel, P. Thakuriah, K. Sila-Nowicka, A. McHugh. Anonymisation of
lifelogging-based image data. Under preparation for journal
submission.
8. Identifying complete movement profiles and social
interactions
Indoor/outdoor classification -
identify on the basis of
temperature and luminosity values
whether person is indoors or
outdoors. Results show that we
can classify images into outdoor
and indoor locations with 93.24 %
correctly classified instances.
Activity detection - Differences in
acceleration patterns can be used
for annotation of various activities,
as well indoor as outdoor ones.
Various acceleration values for 1-
standing; 2-sitting; 3-walking and
4-driving.
LuminosityTemperature
Indoor
Outdoor
Co-detection problem – find out the extent to which people have
interactions with others, how much time they spend with others, how
often they are in meetings etc
Indicators possible:
▪ Time-varying indicators of waste generation,
energy and water usage
▪ Total (indoor + outdoor) activity levels
▪ Independence in daily living
▪ Degree of uneasiness and disturbance in
mobility
▪ Degree of isolation in everyday living
9. Urban Big Data Centre
Development of traffic disturbance index
▪ Driver inattention is a leading cause of crashes
▪ Pedestrian uncertainty at key locations (looking for cars, conflicts etc) affect
quality of travel
▪ Can we use lifelogging data to sense areas of conflict – disturbance index
▪ By disturbance we mean here looking (turns and reorientation – and extent of
reorientation - of an individual’s body into a direction different to the one the
individual is heading)
Individual disturbance
can be defined as a
difference between GPS
/Road network heading
and Life-logging data
orientation
Images
showing
heading
of a
driving/ri
ding
individual
Using multiple sources of
personal sensor information, we
can index the street network
with the degree of uncertainty
and perceived conflict from
image and related data
10. Urban Big Data Centre
Example 2 – Crowdsourced bicyclist data
(Strava)
Jinhyun Hong
David McArthur
Mark Livingston
11. Cycling has a number of health and environmental
benefits but do interventions work?
• Evaluating the effectiveness of interventions (bicycle
infrastructure) is difficult due to the lack of data
• Manual counts take place on specific links/points, but these
are expensive and hence infrequent
• Automatic counters can be used but these are also
expensive and tend to be sparsely located
• Maintenance and calibration is required to keep them
working properly
12.
13. Three models provide different results for Routes to
Cathkin 1 (Only model 1 shows a significant
association)
Routes to Cathkin 1 is the longest new cycling route
and includes several less developed areas.
Our most conservative results show that the three
infrastructure projects have a positive effect on the
monthly total volume of cyclists, with flows up by
around 8% to 14%.
Statistically evaluate large cycling infrastructure
investments in the Glasgow Clyde Valley planning
area before, during and after the Commonwealth
Games:
Response variable – cycling flows
14. Urban Big Data Centre
Example 3 – Transport and Labour Market
Outcomes
Vonu Thakuriah
Yeran Sun
David McArthur
Rod Walpole
15. Urban Big Data Centre
Transport and Labour Market Outcomes
Motivations
▪ Increasing decentralisation of jobs
▪ 24-hour economy – start times of jobs are changing – more shift jobs
▪ High cost of both private and public transport
▪ Auto ownership takes out a large chunk of household incomes and increases
household debt
▪ Links between transport and labour market (and other economic and employment
conditions) have been examined for a long time – what insights are possible from
new forms of data?
Main Research Questions
▪ Where are the most “transport poor” areas in the UK?
▪ What are the links between transport conditions and employment outcomes?
▪ How do these links vary geographically?
▪ What are the implications for policies such as City Deals and Local Growth Fund?
16. Urban Big Data Centre
Continuously Monitoring Urban Systems in UK – Recession?
Brexit?
Spatial Urban Data System (SUDS)
▪ Synthetic data on UK’s largest built-up areas and settlements;
▪ Creating comprehensive, timely, small-area data for local knowledge,
community-level planning and policy and business innovations
▪ Inputs: census, surveys, sensors, social media, specialised data programs
▪ Processes: simple processing to complex urban models and simulations
▪ Outputs: Simple to complex indicators describing cities and
communities (eg, transport accessibility, PM2.5 emissions, fuel poverty,
walkability etc)
▪ ISO 37120:2014 – 16 categories – 72 total; economy, education,
environment, etc, starting with England and Wales (output areas)
▪ Open-source GIS technology, linked to development tools and online
visualisation and analytics – and planned – gaming environments
17. Urban Big Data Centre
General Transit Feed Specification (GTFS)
(weighted) hourly average trip frequency
Stop-level transport accessibility index (TAI)
1 Measuring and mapping stop-level TAI
Timetables
Station Locations
18. Urban Big Data Centre
Identifying areas at high risk of transport poverty Geography level: MSOA
1.78 million
people at risk
of transport
poverty in
England and
Wales
19. Urban Big Data Centre
Public
Transport
Availability
Index
Public
transport stop
density
Public
transport
route density
Public
transport
night-time
service
20. Urban Big Data Centre
Transport and Labour Market Outcomes for Job Claimants
▪ To what extent are the proportion of people on job seekers allowance explained
by transport conditions?
▪ Outcome variable – proportion of job seekers allowance claimants
▪ Exploratory variables – sociodemographics, geographic conditions, commuting
conditions, transportation(road and public transport) conditions
▪ Transport conditions – public transport schedules (availability of public transport
service at specific stops and stations, frequency between vehicles, extent of
service availability during a 24-hour period, weekday/weekend day), level of
spatial access to jobs and competition for those jobs from other workers within
commuting distance, growth in road congestion
▪ Use “synthetic” data from UBDC’s Spatial Urban Data System (SUDS) programme
– and also use this research problem as a way to generate data
▪ Unit of analysis – Lower Super Output Area (LSOA)
▪ Four cities – Birmingham, Bristol, Liverpool, Manchester
▪ Separate quantile regressions for each city (4 quartiles)
▪ Multilevel (random intercept) quantile regressions on proportions of job claimants
21. Urban Big Data CentreUrban Big Data Centre
Key Findings
– Mean
Service
Hours Public
Transport
Increase in mean
public transport
service hours makes
more difference to
areas of areas with
highest proportion of
job claimants in
Liverpool and
Manchester compared
to similar areas in
Birmingham and
Bristol
Key
Findings –
Increase in
road
traffic
Increase in road traffic
between 2011 and
2015 makes more
difference to higher
job claimant
concentrations in
almost in all cities but
probably more so in
Birmingham and
Manchester
Key Findings –
Access to
“spatially
competitive”
destination
opportunities
Destination
accessibility to jobs
has more effect on the
highest quartile of job
claimants in Liverpool;
it has less of an effect
on the highest
concentrations of job
claimants in
Birmingham and
Bristol
22. Main Findings
What is the role of transport systems in joblessness and
employment outcomes?
By tracking UK-wide public transport and roads performance,
UBDC results have indicated that UK public transport schedules
and operations need in certain areas to be re-evaluated to match
the changing nature and location of jobs and locations of workers
and job claimants.
An increase in traffic congestion is negatively impacting workers
in some cities with a rise in job claimants.
23. System to help identify social and functional
concerns and issues potentially for planning or
operational action, eg, where people are not
happy with public services
Example 4: Dynamic Urban Resource Management
Context-Awareness and Semantic Enrichment Using Social Media data to Understand
Local Concerns and Events in Glasgow
Can we use language patterns detected in different parts of the city to understand
underlying uses, activities, and concerns?
W. Liu, W. Lu and P. Thakuriah. Yesterday Once More: Discovering the
“Circadian Rhythm” of Human Activity. Under review for publication
in Urban Studies.
Using WeChat Data to Understand “Circadian
Rhythms” in Beijing
Thakuriah, P., K. S. Nowicka and J. D. G. Paule (2016).
Sensing Spatiotemporal Patterns in Urban Areas:
Analytics and Visualizations using the Integrated
Multimedia City Data Platform. In Journal of Built
Environment, Vol. 42(3), pp. 415-429.
24. Heatmaps of Chicago
Monday (07/03/2016)
Geo-located Tweets
using our methodsGeotagged Tweets
Saturday (12/03/2016)
Twitter users are not
representative of the population;
locations of those who choose to
geotag are further not
representative of the locations of
all Twitter users – but we get a
much larger sample allowing us to
detect more events, and see
activities in more places
25. Urban Big Data Centre
Using our methods, we have discovered traffic-related tweets that are not in incident
databases – in disadvantaged areas as well as in outlying areas;
This has significant potential for filling in underreporting and for more accurate
understanding of risky areas and hazard spaces in cities
Davide-Paule, J. G., Y. Sun and P. Thakuriah. Beyond Geo-Tagged Tweets: Exploring the Geo-Localization of Tweets for
Transportation Applications. Forthcoming in Big Data and Transportation, edited volume to be published by Springer.
Thakuriah, P., J. G. Davide-Paule and Y. Sun. Integrating Heterogeneous Sources of Data to Estimate Composite Social Hazards.
Under preparation for submission to Computers, Environment and Urban Systems
26. Where are the gaps in understanding citizen concerns
regarding personal safety?
Government or administrative databases are not
enough to capture the full range of risks and
discomforts experienced by all citizens; social media
may help to fill in the gaps as people are increasingly
speaking out on social media instead of bringing
concerns to authorities.
27. Urban Big Data CentreUrban Big Data Centre
Selected Examples of Completed Research Work
UCUI'15 : Proceedings of the ACM First
International Workshop on Understanding
the City with Urban Informatics
Moshfeghi, Y., Ounis, I., Macdonald, C., Jose,
J., Triantafillou, P., Livingston,
M. and Thakuriah, P. (2015) UCUI'15 :
Proceedings of the ACM First International
Workshop on Understanding the City with
Urban Informatics. ACM. ISBN
Input into Policy
U.S. Government Accountability Office. Data and Analytics Innovation: Emerging
Opportunities and Challenges. Highlights of a Forum. GAO-16-659SP: Published: Sep
20, 2016. Publicly Released: Sep 20, 2016.
U.K. Parliamentary Office of Science and Technology. Big and Open Data in Transport.
Houses of Parliament POSTNOTE Number 472 July 2014.
U.S. Senate Bill S. 3466 on September 10, 2008 Job Access and Reverse Commute Program
Improvements Act of 2008 - 110th Congress (2007-2008) by Senator Russ Feingold,
Senate - Banking, Housing, and Urban Affairs.
28. Urban Big Data Centre
Innovations for sustainable
and socially-just cities
Urban Big Data Centre
Partners
▪ And a network of UK, European, US,
Australian and Chinese institutions
▪ 10 Academic Disciplines – Urban Social
Science, Data Science and Engineering
▪ 400+ stakeholders and users
Mission: Promote innovative methods and
complex urban data to address social, behavioural
and environmental challenges facing cities:
▪ Strategic Themes - dynamic resource
management; social inclusion; lifelong
learning; economic and business
innovations; citizen engagement and
citizen science, planning and policy
reform
▪ Multiple Urban Sectors: transport,
housing, education, economic
development, environment, energy –
particularly their connections
Operate a national data service for UK
research on cities and urban challenges -
Open data, secure and confidential
data, real-time predictive analytics, data
capture and linkage, synthetic data
generation