Integrated Spatio-Temporal Data Mining for Quantitative Assessment of Road Network Performance

Lead Research Organisation: University College London
Department Name: Civil Environmental and Geomatic Eng

Abstract

Recent traffic surveys and analysis of road network performance in London show a decline in traffic flows and perversely a decline in speeds and increase in congestion. It is believed that the increases in congestion reflect travellers' responses, both temporary and longer-term, to competition for road network capacity. Continuing adjustments to network capacity in pursuit of mayoral transport priorities, for example, improved safety and amenity, and increased priority for buses, taxis, pedestrians and cyclists, has led to increasing delays for private vehicular traffic. The current annual cost of congestion on London's main roads is estimated to be in the range of 1.8 to 3 billion.Analysis of road network performance is intricate. This is because the road network is essentially an open system with many factors and in which travellers can respond by modifying their choices in many different ways that will affect monitored performance outcomes. The form of these factors, their direction of causality, the fact that some of them interact strongly, and their sheer numbers all contribute to the complexity. These factors have different patterns of influence in both time and space, and analysis of the distinct cause-effect patterns is complicated by the non-linearity of the effects, including the possibility of abrupt growth in congestion once it sets in. Modelling spatial-temporal dependency of the factors is the bottleneck in analysis of the network performance. The challenge is to model dependency in both space and time seamlessly and simultaneously so that the accuracy of analysis can be improved. Another challenge is to fully consider the topology (links and hierarchies) and geometry (distances and directions) of real road networks in the analysis. These are also fundamental challenges in modelling complexity of other types of networks.This research will tackle these challenges. It will be achieved by innovative combination of two chosen novel machine learning methods (Dynamic Recurrent Neural Networks - DRNN and Support Vector Machines - SVM) with the most advanced statistical space-time series analysis (Spatio-Temporal Auto-Regressive Integrated Moving Average - STARIMA) and Geographically Weighted Regression - GWR. These methods are selected because their applications in transport studies are relatively new compared with conventional statistical methods, and, more importantly, they have the potential to improve the representation of the network complexity. The DRNN and SVM can model the non-linearity and non-stationarity existing in most spatio-temporal data which may not be fully accommodated by STARIMA. The STARIMA has the explanatory capability which is missing in DRNN and SVM. The GWR can model the heterogeneity of the networks and improve the understanding of the scales of the networks. Their use in combination will improve the sensitivity and explanatory power of the analysis, to enable the effects of the factors to be assessed separately (isolatable). These methods will also be explored, refined and further developed in the light of experience in this study.The outcome of this research will advance the new and emerging fundamental researches in agent simulations, dynamic network analysis, and computational models and architectures of artificial neural networks, which are widely involved in space-time analysis of social-economic phenomena. It will offer TfL better tools and techniques to manage the road space and mitigate congestion more effectively thereby improving person journey times and overall journey reliability, and in doing so also deliver large economic benefits to London. The benefits of the research will accrue widely to both public and private transport users. The methodology developed here will be transferable to understand the congestion in other big cities around the world with economic, monetary, social and environmental benefits.

Publications

10 25 50
 
Description This project undertook methodology-led research to model the complexity of road networks, and to understand the nature and causes of traffic congestion so that it can be avoided, managed and mitigated effectively. It pioneered integrated modelling of spatio-temporal dependency of networks via combined statistical regression and machine learning. The case study used Central London with data provided by TfL. The major findings are summarised as follows:

1) Short-term journey time prediction - analysis of a large dataset of journeys collected in London, has contributed to the understanding of how traffic conditions spread across road networks. New models based upon statistical and machine learning approaches have been developed for short-term forecast of journey times in road networks. This provides enhanced performance by comparison with existing models and is robust in the presence of missing data.

2) Simulation of driver behaviour and network performance - New theories and models of drivers behaviour have been developed based upon a dataset of 1.5 million taxi journeys. These theories contribute to our understanding of how the behaviour of individuals generates the large scale traffic conditions that we observe on urban transport networks. Agent-based simulations have been developed based on these theories, which are more realistic than existing models.

3) Identifying and modelling the spread of non-recurrent congestion - The most severe traffic delays are caused by non-recurrent events such as traffic incidents, burst water mains, road works and special events; these are responsible for about half of all congestion losses in London and other major cities. When these events take place, modelling the spread of the resulting congestion is crucial to mitigating their effects. This research has developed novel methods to identify non-recurrent congestion in order to provide early warning for traffic engineers.

4) 3D visualisation of traffic data - The collection, and subsequent availability, of massive datasets with both spatial and temporal dimensions has increased rapidly in recent years. However, the development of methods for visualising them still represents a major bottleneck. This research has developed a number of sophisticated 3D visualisation methods, which allow better understanding of spatio-temporal patterns in traffic data. These methods have been applied by Transport for London to the visualisation of journey time reliability during the London 2012 Olympic Games.

5) Identification of macroscopic traffic parameters in Central London - Analytical methods were developed for determining macroscopic traffic parameters for the road network in central London. Methods were developed to fuse data of different kinds (flows, occupancies, travel times) from different sources (automatic number plate recognition, SCOOT) to provide an improved representation of the network state, which enables richer analysis. This stream of work has been supported by quantitative analysis of the effect of weather conditions, road works and tube strikes on travel times in London.

Information and Communications Technology (ICT) offers network managers better tools and techniques to manage road space and to mitigate congestion more effectively. Benefits of this will accrue by travellers by improving their travel experience and network reliability. The methodology developed here will be transferable to monitor, analyse and manage traffic in other major cities around the world with economic, monetary, social and environmental benefits. The outcome of this research also advances the new and emerging fundamental researches in agent-based simulations, dynamic network analysis, and geocomputation, which are widely involved in spatio-temporal analysis of socio-economic phenomena involving big data.
Exploitation Route • Enabling transport authorities to better understand the performance of their urban road networks in big cities around the world.

• Enabling better understanding of drivers' behaviours and congestion propagation on road networks.

• Enabling improved modelling and forecasting of space-time series collected on real world sensor networks, including, but not limited to transportation networks.

• Enabling exploration analysis of dynamic processes evolving along networks through space-time visualisation.

• The methods and algorithms are also being developed as a package for the open source software environment R.

• Several published articles in peer reviewed journals including Computers, Environment and Urban Systems, Journal of Advanced Transportation, Journal of Geographical Systems, Geographic Analysis, the Cartographic Journal, Transportation Planning and Technology and Geoinformatica.

• Oral and poster presentations at various international conferences in Geographical Information Science, transportation studies, regional science, geography, and complexity science.

• The methods developed are being taught as part of an MSc programme at UCL. A number of outstanding MSc theses have resulted directly from collaboration with the project.

• The project has attracted visiting scholars and students from Spain, France, US, Japan, and the UK.

• Several workshops have been organised around the research themes of the project, with participants from academia, industry and government in the UK. Two international conferences have also been organised by the team members of the project, which gave good publicity to the project among academics in geocomputation and spatio-temporal data mining.

• Research outcomes have been reported in a special event: "Transport and the Olympic Legacy: driving innovation", with 200 members of the general public involved. Posters and demonstrations have also been displayed in the event.

• Research outcomes have been regularly presented to Transport for London (TfL) in meetings and demonstrations. TfL have used and continue to use the methods developed within the project to aid road network performance analysis in London.

• A dedicated website (standard.cege.ucl.ac.uk) has been developed for the project which lists major findings, publications, methods and software of the project.
Sectors Digital/Communication/Information Technologies (including Software),Environment,Retail,Security and Diplomacy,Transport

URL http://standard.cege.ucl.ac.uk/
 
Description The work of the STANDARD has partly led to the creation of a new interdisciplinary research centre at UCL, called SpaceTimeLab. SpaceTimeLab brings together researchers from a diverse set of fields, including geography, GIScience, geomatics, computer science, transport, and crime science. Its vision is to gain insight into the spatio-temporal complexity in society, economics and engineering. The SpaceTimeLab launch event was held at UCL on 30th October 2012. To mark the occasion, Prof. Michael Goodchild (UC Santa Barbara) gave a special keynote talk on Geographic Intelligence. Beneficiaries: Researchers and staff in the Department of Civil, Environmental and Geomatic Engineering, UCL, as well as the wider research community and industry. Contribution Method: The project provided evidence of the quality of research taking place in the department, which strengthened the case for the creation of a new research centre. Many of the techniques and tools developed during the STANDARD project are now being taught as part of the spatio-temporal analysis and data mining module at UCL, which is available for MSc students in geographic information science and geospatial analysis, as well as PhD and EngD students from Geography, Crime Science, Archaeology and Engineering. By teaching the methods developed during the STANDARD project to MSc students, the outcomes of the project reach a wider audience. Beneficiaries: Students taking taught MSc courses Contribution Method: Methodological contribution Dr. Andy Chow presented at a special event, entitled Transport and the Olympic Legacy: driving innovation, held at UCL on Tuesday 11th September 2012. The event brought the issues surrounding transportation infrastructure during major events to a wider audience of experts and non-experts. Beneficiaries: Academics and wider society Contribution Method: Dr. Chow's in depth knowledge of London's road transport network, gained through his participation in the STANDARD project, led to him being selected to sit on a panel of experts for a panel discussion. This formed the main part of the event. Software developed within the STANDARD project by Garavig Tanaksaranond was used by Transport for London for visualisation of journey time data on the Olympic Route Network (ORN) during the London 2012 Olympic Games. Analysts at Transport for London used the visualization software to gain a better understanding of the performance of the road network. This enabled improved monitoring of the network during a crucial time, the London 2012 Olympic Games. Beneficiaries: Transport for London beneditted directly. The population of London benefitted indirectly through the insights gained from the visualisations. Contribution Method: The methods used were developed by Garavig Tanaksaranond as part of ongoing PhD research. James Haworth's secondment with TfL will benefit TfL in accurately estimate cycle flows, which will further facilitate the transport planning and safety.
First Year Of Impact 2013
Sector Education,Retail,Security and Diplomacy,Transport
Impact Types Societal,Economic,Policy & public services

 
Description Parking Tickets in Camden Council
Geographic Reach Local/Municipal/Regional 
Policy Influence Type Gave evidence to a government review
Impact We highlighted the parking tickets hot spots and their trends, which has high impact of the councils' income
 
Description Public Health England on their sexual health campain
Geographic Reach National 
Policy Influence Type Implementation circular/rapid advice/letter to e.g. Ministry of Health
Impact WE examined the impact of PHE's health campaign via social media, suggesting the high impacts coming from community twitter account owner
 
Description Secondment to Transport for London (TfL)
Geographic Reach Local/Municipal/Regional 
Policy Influence Type Influenced training of practitioners or researchers
Impact STANDARD team member James Haworth is having secondment to TfL to integrate cycling flows based upon data provided from TfL manual count and auto count and Ostrava (a private company) - so that the estimation of cycling flow is more accurately estimated. This will improve the estimation of road surface being used by cyclers.
 
Description Visualisation of Journey Time Reliability During Olympic Game Period
Geographic Reach Local/Municipal/Regional 
Policy Influence Type Influenced training of practitioners or researchers
Impact TfL has used this to evaluate the journey time reliability during the Olympic Game Period which improve their work efficiency
 
Description Crime, Policing and Citizenship - Space-Time interactions of Dynamic Networks
Amount £1,400,235 (GBP)
Funding ID EP/J004197/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start  
End 04/2016
 
Description Framework Programme 7: INFRARISK - Novel indicators for identifying critical INFRAstructure at RISK from Natural Hazards
Amount € 3,658,480 (EUR)
Funding ID 603960 
Organisation European Commission 
Sector Public
Country European Union (EU)
Start 10/2013 
End 10/2016
 
Description Modelling and Prediction of Space-Time Distribution and Transition of Global Overseas Farmland Investment
Amount £12,000 (GBP)
Funding ID IE151186 
Organisation The Royal Society 
Department International Exchanges Scheme
Sector Charity/Non Profit
Country United Kingdom
Start 04/2016 
End 03/2018
 
Description Phase 2 ESRC Big Data Research Centres - Retail Business Datasafe
Amount £6,117,615 (GBP)
Funding ID ES/L011840/1 
Organisation Economic and Social Research Council 
Sector Public
Country United Kingdom
Start 02/2014 
End 02/2019
 
Description Prototype Project: Landslide susceptibility mapping in data-poor environments
Amount £9,587 (GBP)
Organisation Economic and Social Research Council 
Department ESRC-DFID Joint Fund
Sector Public
Country United Kingdom
Start 04/2015 
End 05/2015
 
Description SECONDMENT OF JAMES HAWORTH TO TRANSPORT FOR LONDON
Amount £5,860 (GBP)
Funding ID EP/K503745/1 F.3.13 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Public
Country United Kingdom
Start 10/2016 
End 03/2017
 
Title A deep learning approach to infer employment status of passengers by using smart card data 
Description A deep learning architecture, called a thresholding multi-channel convolutional neural network, was developed to predict an individual's employment status from their oyster card data 
Type Of Material Model of mechanisms or symptoms - human 
Year Produced 2019 
Provided To Others? Yes  
Impact This method has been used to analyse demographic profiles 
URL https://ieeexplore.ieee.org/document/8645820
 
Title Network-based Deep Learning Methods for traffic prediction 
Description Network-based Deep Learning Methods for traffic prediction 
Type Of Material Model of mechanisms or symptoms - human 
Year Produced 2019 
Provided To Others? Yes  
Impact This tool will enable deep learning to model network-based phenomena which cannot modelled by deep learning at the moment. 
 
Title Network-based space-time DBSCAN (2018) 
Description An innovative method to find hot spots in space-time at network segment level 
Type Of Material Model of mechanisms or symptoms - human 
Year Produced 2018 
Provided To Others? No  
Impact This will be extremely useful to analyse urban movement data 
 
Title STAMRIA 
Description This is the model developed by STANDARD 
Type Of Material Computer model/algorithm 
Year Produced 2010 
Provided To Others? Yes  
Impact We have used STARIMA for our teaching of MSc in STA - every year there are around 25 students joined the course 
 
Description Addison Lee 
Organisation Addison Lee
Country United Kingdom 
Sector Private 
PI Contribution A partnership was formed with Addison Lee Taxi firm for the provision of GPS tracks of approximately 1.5 million taxi journeys in London
Collaborator Contribution They provide their Taxi data for Ed Manley's research
Impact The data provided by them have been used to develop the routing modelling of Ed Manley's PhD dissertation.
Start Year 2011
 
Description Prof. Chris Brunsdon 
Organisation University of Liverpool
Country United Kingdom 
Sector Academic/University 
PI Contribution Prof. Chris Brunsdon was involved with the STANDARD project as a visiting fellow. Then he became an advisor of CPC. Now he is the external examiner of our MSc programme in STA.
Collaborator Contribution He is an advisor of CPC
Impact We have one joint journal publication.
Start Year 2014
 
Description Prof. Michael Goodchild 
Organisation University of California, Santa Barbara
Country United States 
Sector Academic/University 
PI Contribution Prof. Michael Goodchild was involved with the STANDARD project as a visiting fellow.
Start Year 2012
 
Description Transport for London 
Organisation Transport for London
Country United Kingdom 
Sector Public 
PI Contribution Transport for London were the industrial partners of the STANDARD project.
Collaborator Contribution TfL provide the data and the industrial insight
Impact We have a joint publication. We also develop a prototype system for TfL to visualise the journey time reliability during Olympic Game in London 2012
Start Year 2009
 
Title A heuristic approach to extract home and work stations from smart card data 
Description it can extract the home and work stations of London residence based upon Osyter card data 
Type Of Technology New/Improved Technique/Technology 
Year Produced 2017 
Impact not yet 
 
Title Agent-based Simulation of London Traffic 
Description This product could give live simulation of traffic formulation in central London with real road traffic, layout and capacity, and real origin and destination. 
Type Of Technology Software 
Year Produced 2012 
Impact The ABM simulation has been demonstrated in TfL. 
 
Title Online Visualisation of LACP Data 
Description This provide quick access and visualisation of road journey data which is needed for TfL road surface manager 
Type Of Technology Software 
Year Produced 2012 
Impact The prototype has been demonstrated in TfL 
 
Title STARIMA - space-time prediction of traffic data 
Description This is a package developed in R by the STANDARD team 
Type Of Technology Software 
Year Produced 2011 
Impact This has been used for our teaching 
 
Description Broadcast Media: UK Big Data Mission to China 2017 
Form Of Engagement Activity A broadcast e.g. TV/radio/film/podcast (other than news/press)
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact I Joined UK Big Data Mission to China 2017 and received a letter of praise from the Department of International Trade. The mission involved a press conference with 25 leading Chinese publications, which led to over 240 Chinese big data companies for potential business leads. Additionally, over 50,000,000 media impressions and 3,000,000 RMB PR value 12 were generated through media activities, many of which were broadcast across some of China's key media outlets.
Year(s) Of Engagement Activity 2017
 
Description CPC Closing Workshop 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Professional Practitioners
Results and Impact About 150 audience coming from policing practitioners, senior commanders, researchers and companies joined the day event. It was a lively event with talks, live demos and panel debates.
Year(s) Of Engagement Activity 2016
URL http://www.ucl.ac.uk/spacetimelab/stlab-news-publication/CPC_Closing_Workshop
 
Description Campus Visit (ChangAn University), XiAn, China 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Undergraduate students
Results and Impact There are about 200 people (students and colleagues) from several universities in XiAn joined the seminar, and I also met the foreign affair officer of ChangAn University to discuss about possible collobration
Year(s) Of Engagement Activity 2016
 
Description Campus Visit (Huang Zhong University of Technology and Science) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Postgraduate students
Results and Impact 30 PG students of Economic Management joined the research seminar - "Space-Time Analytics for Smart Cities", which sparked questions and discussion afterwards
Year(s) Of Engagement Activity 2016
 
Description Campus visit (Wuhan University), Wuhan China 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Postgraduate students
Results and Impact There are 150 people (students and staff) joined the research seminar - "Space-Time Analytics for Smart Cities", which sparked questions and discussion afterwards, and there were several students asked about study MSc and PHD in UCL
Year(s) Of Engagement Activity 2016
 
Description Delegations from Guiyang Big Data Expo, China; Chinese Embassy and British Embassy - UK Innovation Section 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Policymakers/politicians
Results and Impact The delegates led by Deputy Major of Guiyang visited SpaceTimeLab - we presented our latest progress in big data analytics. The visit was accompanied by the Science & Technology Consular of the Chinese Embassy, and UK Innovation of British Embassy in China
Year(s) Of Engagement Activity 2017
 
Description Digital Shoreditch Panel debate on the talent gap for data skills - Hunting Data Science Unicorns, May 12th 2015 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact Tao Cheng participated in an expert panel debate on the topic of recruiting data scientists. The event raised awareness of the projects she is involved with.
Year(s) Of Engagement Activity 2015
 
Description Distinguished Lecture , Hong Kong Polytechnic University, Dec 2018 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Postgraduate students
Results and Impact An invited lecture, which sparked questions and discussion afterwards, and plan for further collobration
Year(s) Of Engagement Activity 2018
 
Description Exhibition in GeoBusiness 2018, May 22-23 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact We have live demo of the research projects of SpaceTimeLab
Year(s) Of Engagement Activity 2018
URL http://www.geobusinessshow.com/
 
Description GeoBusiness, Workshop - Research of highlights of Geospatial Data Processing and Big Data, May 27th 2015 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Industry/Business
Results and Impact Tao Cheng participated in a workshop on space-time data. The event raised awareness of the projects she is involved with.
Year(s) Of Engagement Activity 2015
 
Description Invited Research Seminar by Leeds Big Data institue 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Postgraduate students
Results and Impact 50 people joined the research seminar - "space-Time Analytics for Total Policing", which was well received as rated the best talk of the day event
Year(s) Of Engagement Activity 2016
 
Description Invited Talk in Benoy, a famous architecture company 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Industry/Business
Results and Impact Benoy invited me to present a seminar on "space-Time Analytics for Smart cities"
Year(s) Of Engagement Activity 2018
 
Description Invited Talk in University of St Andrews 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Postgraduate students
Results and Impact a research seminar, we also discuss about collaboration, and we submitted a joint application to NERC
Year(s) Of Engagement Activity 2017
 
Description Invited Talk in Wuhan Hi-Tech Economic Development Zone 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Industry/Business
Results and Impact More than 2000 people joint event, there is a widely news report of the event at the provincial level.
Year(s) Of Engagement Activity 2018
 
Description Invited talk in Imperial College, February 9th 2019 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Postgraduate students
Results and Impact Invited research seminar, sparked questions and discussion afterwards, and possible further collaboration
Year(s) Of Engagement Activity 2019
 
Description Invited talk, First Transport for London Research Forum, Space-Time Analytics of Smart Card Data for an Improved Understanding of the City and Citizens, Sept, 11th 2015 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Tao Cheng delivered an invited talk at this event, whose participants included members of government and practitioners. Her talk covered aspects of all the major projects she is involved with (CPC, Retail Business Datasafe, STANDARD). The event raised awareness of the current research agenda.
Year(s) Of Engagement Activity 2015
 
Description Keynote Roadshow: across key universities in China 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact I presented at 8 key university departments across China on topics ranging from Crime, Consumer Data and Big Data. Each talk had over 100 delegates in attendance from the field of academia. The universities covered were: Southwest JiaoTong University, Wuhan University, Beijing University, Research Institutes of Chinese Academy of Geography, Electrons, Urban Planning, China Urban Planning, Ministry of Security. Since I also had the opportunity to meet with colleagues from across China I believe the discussions my presentations generated also influenced their own views.
Year(s) Of Engagement Activity 2017
 
Description Keynote talk in JRC-NETTAR Cluster 8 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact About 50 participants coming from Europe, mostly working in JRC. I delivered a keynote - "Space-Time Analytics of Urban Mobility - People and Place".
Year(s) Of Engagement Activity 2016
URL http://www.nectar-eu.eu/wp-content/uploads/2015/11/NECTAR_JRC_big_data.pdf
 
Description Keynote: Space-Time Analytics for Consumers' Data, International workshop of Social Geocomputation, Wuhan 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact I presented to roughly 500 attendees from the field of academia in China; my keynote generated a lot of interest and there was a healthy debate among participants about the key points in my presentations. Additionally, my presentation was broadcast online so I believe the reach was far wider than the main attendees.
Year(s) Of Engagement Activity 2018
 
Description Keynote: Space-Time Analytics for Nature Hazards, International workshop on Data science for high impact weather and flood prediction, University of Reading 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Undergraduate students
Results and Impact I presented to a large audience on the use of data science for high impact weather; with roughly 300 attendees my presentation garnered a lot of interest among colleagues and attendees alike. By presenting to delegates from key international universities my presentation generated interesting discussion afterwards.
Year(s) Of Engagement Activity 2017
 
Description Keynote: WGDC - Rise of Geospatial Big Data, Beijing 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Over 6000 people attended for a keynote on the rise of Geospatial Big Data. With such a large number of delegates my keynote sparked a lot of interest and discussion on the role of GIS in research across national and international academic. Both during the event and after I was contacted by numerous attendees seeking further information and possibilities for collaborations.
Year(s) Of Engagement Activity 2017
 
Description Media interest: WGDC - Rise of Geospatial Big Data, Beijing 
Form Of Engagement Activity A press release, press conference or response to a media enquiry/interview
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Postgraduate students
Results and Impact I hosted a keynote at Beijing University about the 'Rise of Geospatial Big Data' in China and beyond. This attracted good attention from key print media outlets in China.
Year(s) Of Engagement Activity 2017
 
Description Media: Joined UK Big Data Mission to China 2017 
Form Of Engagement Activity A press release, press conference or response to a media enquiry/interview
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact I Joined UK Big Data Mission to China 2017 and received letter of praise from the Department of International Trade. The mission involved a press conference with 25 leading Chinese publications, which led to over 240 Chinese big data companies for potential business leads. Additionally, over 50,000,000 media impressions and 3,000,000 RMB PR value 12 were generated through media activities. Publications such as Guizhou TV, China Daily, China News, Guizhou Daily, Xinhuanet.com, People.com, Huanqiu.com, ifeng.com, Caijing, Cbdio.com, Sohu and Sina all showed significant interest in the mission.
Year(s) Of Engagement Activity 2017
 
Description Meeting with Delegates from Shanghai Municipal Commission of Economy and Informatization and China Industry Design Institute (CIDI), March 16th, 2016 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Policymakers/politicians
Results and Impact Tao Cheng met with 2 visitors from Shanghai who represented Chinese policymakers to discuss aspects of space-time analytics.
Year(s) Of Engagement Activity 2016
 
Description Meeting with delegates from DIDI Technology, China, March 22nd, 2016 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact Tao Cheng met with a delegation from the Chinese firm DIDI Technology. They discussed possible collaborations in the area of space-time analytics.
Year(s) Of Engagement Activity 2016
 
Description Panel discussion - Big Geospatial Data Challenges and Best Practices, International Conference of American Association of Geography (AAG) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact I delivered a presentation to over 500 external delegates from international institutions. The presentation sparked some very interesting debate among my peers and I had significant from attendees post the event.
Year(s) Of Engagement Activity 2017
 
Description Panel discussion: International Open Data and Urban Innovation Submit, Shanghai 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Over 100 people attended the panel session to discuss and debate, particularly, open data within research and beyond. This generated an interesting discussion and debate on the comparisons of open data from an international perspective. Feedback from the session suggests increased interest and initiatives within the delegates' own institutions.
Year(s) Of Engagement Activity 2017
 
Description Presentation - Space-Time Analytics for Smart Cities on COST Workshop - Progress in Transportation and Urban Analytics 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Study participants or study members
Results and Impact It is COST (EU) workshop, which sparked questions and discussion afterwards
Year(s) Of Engagement Activity 2016
URL http://www.tu1305.eu/content/workshop-casa
 
Description Presentation Using Mobility Tracking App Data to Estimate Cycle Flows (James Haworth) COST Workshop 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Study participants or study members
Results and Impact It is a COST (EU) workshop, the talk sparked interesting questions and discussion
Year(s) Of Engagement Activity 2016
URL http://www.tu1305.eu/content/workshop-casa
 
Description Research Seminar, Big Data & Intelligent Policing, University of Warwick 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Postgraduate students
Results and Impact Roughly 40 people from the field of academia attended the seminar. This was followed by a healthy debate about Big Data and it's use in research.
Year(s) Of Engagement Activity 2018
 
Description Research Seminar: Big Data and Intelligent Policing, Manchester Metropolitan University 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Postgraduate students
Results and Impact Over 100 people attended a seminar on Big Data and Policing. There was a lot of debate generated during the seminar; this was followed up by further information being requested from me after the event.
Year(s) Of Engagement Activity 2017
 
Description UK Knowledge Transfer Network Workshop: Digital Forensics and Big Data: Extracting Actionable Information. "Spatio-temporal Analytics for Total Policing", March 27th 2015 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Tao Cheng delivered an invited talk at this event, whose participants included crime practitioners. Her talk covered aspects of all the major projects she is involved with (CPC, Retail Business Datasafe, STANDARD). The event raised awareness of the current research agenda.
Year(s) Of Engagement Activity 2015
URL https://connect.innovateuk.org/web/forensics/events-view/-/events/21675652
 
Description UK-China Big Data Summit, delegates from China includes Ant Finance (Alibaba), Nov 13th, 2015 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact Tao Cheng participated in the UK-China Big Data summit, which included delegates from major Chinese firm Alibaba and academics. The topics covered included Big space-time data analytics.
Year(s) Of Engagement Activity 2015
 
Description UrbanMovements.co.uk: Flows, Behaviour and Networks in the City 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact UrbanMovements is the research blog of Mr. Ed Manley. Ed has published findings from his research during the STANDARD project to the blog, as well as various other projects he has been involved with. These include the Twitter language maps of London and New York.

The blog has allowed Ed's work to reach a wider audience, leading to coverage in national and international media and further consultancy opportunities.
Year(s) Of Engagement Activity 2012
URL http://urbanmovements.co.uk/
 
Description Visit Shenzhen University, China 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Postgraduate students
Results and Impact Discuss collaboration with the group in Shenzhen University, and a research seminar on Space-time Analytics of Smart Card Data, which sparked questions and discussion afterwards
Year(s) Of Engagement Activity 2015
 
Description Visit of CETE to SpaceTimeLab, May 24th and Nov 28th 2018 
Form Of Engagement Activity Participation in an open day or visit at my research institution
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact CETE is the world top 500 enterprise, a state-owned company in China. They are the Chinese partner of sino-uk collobration in smart cities, one of the four themes of scientific
and technology collaboration.
Year(s) Of Engagement Activity 2018
 
Description Visit the Hong Kong Polytechnic University 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Postgraduate students
Results and Impact around 50 people joined the research seminar on "Space-Time Analytics of Urban Mobility", which sparked questions and discussion afterwards
Year(s) Of Engagement Activity 2015