CityPulse: Large-scale data analytics 
for smart cities 
1 
Payam Barnaghi 
Institute for Communication Systems (ICS) 
University of Surrey 
Guildford, United Kingdom
Smart City Data 
− Data is multi-modal and heterogeneous 
− Noisy and incomplete 
− Time and location dependent 
− Dynamic and varies in quality 
− Crowed sourced data can be unreliable 
− Requires (near-) real-time analysis 
− Privacy and security are important issues 
− Data alone may not give a clear picture -we need 
contextual information, background knowledge, multi-source 
information and obviously better data analytics 
solutions… 
2
Smart City Data 
3 
?
What happens if we only focus on data 
− Number of burgers consumed per day. 
− Number of cats outside. 
− Number of people checking their facebook 
account. 
− What insight would you draw? 
4
What type of problems we expect to solve 
in 
“smart” cities
Back to the future 
6
Future cities: a view from 1998 
Source LAT Times, http://documents.latimes.com/la-2013/ 7
Source: http://robertluisrabello.com/denial/traffic-in-la/#gallery[default]/0/ 8 
Source: wikipedia
9
The IoT and its applications 
10 
Diffusion of innovation 
IoT 
image source: Wikipedia 
The Most Hyped Technology 
image source: Forbes via Gartner
Moving fast forward 
11 
Source: AdamKR via Flicker, http://www.flickr.com/photos/adamkr/5045295251/in/photostream/
12 
We need an Integrated Approach
13 
CityPulse Consortium 
Partners: 
Industrial 
SIE (Austria, 
Romania), 
ERIC 
SME AI 
Higher 
Education 
UNIS, NUIG, 
UASO, WSU 
City BR, AA 
Duration: 36 months
14 
Processing steps
CityPulse – what we are going to 
deliver 
... 
Data Streams 
a) Software tools/libraries 
in an integrated framework 
b) Back-end support servers 
Smart City Framework 
Smart City Scenarios 
a) 101 scenarios 
b) 10 will be chosen to be prototyped 
a) Data portals/ real-time access 
interfaces 
b) Interoperable formats 
c) Common interfaces (REST/annotated) 
a) Proof-of- 
Concepts and 
demonstrators 
and evaluations; 
Applications/App 
s/Demos 
Link: http://www.ict-citypulse.eu/page/content/smart-city-use-cases-and-requirements
Stream Processing 
... 
Data Streams 
CityPulse
Some of the key issues 
− Data collection, representation, interoperability 
− Indexing, search and selection 
− Storage and provision 
− Stream analysis, fusion and integration of multi-source, 
multi-modal and variable-quality data 
− Aggregation, abstraction, pattern extraction and 
time/location dependencies 
− Adaptive learning models for dynamic data 
− Reasoning methods for uncertain and incomplete data 
− Privacy, trust, security 
− Scalability and flexibility of the solutions 
17
Some of our recent in this domain 
18
Use cases
Scenario ranking
101 Smart City Use-case Scenarios 
http://www.ict-citypulse.eu/page/content/smart-city-use-cases-and-requirements
101 Scenarios 
− http://www.ict-citypulse.eu/page/content/smart-city- 
use-cases-and-requirements
Data abstraction 
23 
F. Ganz, P. Barnaghi, F. Carrez, "Information Abstraction for Heterogeneous Real World Internet Data", IEEE Sensors Journal, 2013.
Ontology learning from real world data 
24
Adaptable and dynamic learning 
methods 
http://kat.ee.surrey.ac.uk/
Social media analysis (collaboration with Kno.e.sis, 
Wright State University) 
26 
Tweets from a city 
City Infrastructure 
https://osf.io/b4q2t/ 
P. Anantharam, P. Barnaghi, K. Thirunarayan, A. Sheth, "Extracting city events from social streams,“, under review, 2014.
Correlation analysis 
27
28
Data analytics framework 
Ambient 
Intelligence 
Social 
systems Interactions Interactions 
29 
Data Data 
Data: 
Domain 
Knowledge 
Domain 
Knowledge 
Social 
systems 
Open 
Interfaces 
Open 
Interfaces 
Ambient 
Intelligence 
Quality and 
Trust 
Quality and 
Trust 
Privacy and 
Security 
Privacy and 
Security 
Open Data Open Data
In Conclusion 
− Smart cities are complex social systems and no technological and data-analytics- 
driven solution alone can solve the problems. 
− Combination of data from Physical, Cyber and Social sources can give more 
complete, complementary data and contributes to better analysis and 
insights. 
− Intelligent processing methods should be adaptable and handle dynamic, 
multi-modal, heterogeneous and noisy and incomplete data. 
− Effective visualisation and interaction methods are also key to develop 
successful solutions. 
− There are several solution for different parts of a data analytics framework in 
smart cities. An integrated approach is more effective in which IoT devices, 
communication networks, data analytics and learning algorithms and 
methods, services and interaction and visualistions and methods (and their 
optimisation algorithms) can work and cooperate together. 
30
Q&A 
− Thank you. 
− EU FP7 CityPulse Project: 
http://www.ict-citypulse.eu/ 
@ictcitypulse 
p.barnaghi@surrey.ac.uk

CityPulse: Large-scale data analytics for smart cities

  • 1.
    CityPulse: Large-scale dataanalytics for smart cities 1 Payam Barnaghi Institute for Communication Systems (ICS) University of Surrey Guildford, United Kingdom
  • 2.
    Smart City Data − Data is multi-modal and heterogeneous − Noisy and incomplete − Time and location dependent − Dynamic and varies in quality − Crowed sourced data can be unreliable − Requires (near-) real-time analysis − Privacy and security are important issues − Data alone may not give a clear picture -we need contextual information, background knowledge, multi-source information and obviously better data analytics solutions… 2
  • 3.
  • 4.
    What happens ifwe only focus on data − Number of burgers consumed per day. − Number of cats outside. − Number of people checking their facebook account. − What insight would you draw? 4
  • 5.
    What type ofproblems we expect to solve in “smart” cities
  • 6.
    Back to thefuture 6
  • 7.
    Future cities: aview from 1998 Source LAT Times, http://documents.latimes.com/la-2013/ 7
  • 8.
  • 9.
  • 10.
    The IoT andits applications 10 Diffusion of innovation IoT image source: Wikipedia The Most Hyped Technology image source: Forbes via Gartner
  • 11.
    Moving fast forward 11 Source: AdamKR via Flicker, http://www.flickr.com/photos/adamkr/5045295251/in/photostream/
  • 12.
    12 We needan Integrated Approach
  • 13.
    13 CityPulse Consortium Partners: Industrial SIE (Austria, Romania), ERIC SME AI Higher Education UNIS, NUIG, UASO, WSU City BR, AA Duration: 36 months
  • 14.
  • 15.
    CityPulse – whatwe are going to deliver ... Data Streams a) Software tools/libraries in an integrated framework b) Back-end support servers Smart City Framework Smart City Scenarios a) 101 scenarios b) 10 will be chosen to be prototyped a) Data portals/ real-time access interfaces b) Interoperable formats c) Common interfaces (REST/annotated) a) Proof-of- Concepts and demonstrators and evaluations; Applications/App s/Demos Link: http://www.ict-citypulse.eu/page/content/smart-city-use-cases-and-requirements
  • 16.
    Stream Processing ... Data Streams CityPulse
  • 17.
    Some of thekey issues − Data collection, representation, interoperability − Indexing, search and selection − Storage and provision − Stream analysis, fusion and integration of multi-source, multi-modal and variable-quality data − Aggregation, abstraction, pattern extraction and time/location dependencies − Adaptive learning models for dynamic data − Reasoning methods for uncertain and incomplete data − Privacy, trust, security − Scalability and flexibility of the solutions 17
  • 18.
    Some of ourrecent in this domain 18
  • 19.
  • 20.
  • 21.
    101 Smart CityUse-case Scenarios http://www.ict-citypulse.eu/page/content/smart-city-use-cases-and-requirements
  • 22.
    101 Scenarios −http://www.ict-citypulse.eu/page/content/smart-city- use-cases-and-requirements
  • 23.
    Data abstraction 23 F. Ganz, P. Barnaghi, F. Carrez, "Information Abstraction for Heterogeneous Real World Internet Data", IEEE Sensors Journal, 2013.
  • 24.
    Ontology learning fromreal world data 24
  • 25.
    Adaptable and dynamiclearning methods http://kat.ee.surrey.ac.uk/
  • 26.
    Social media analysis(collaboration with Kno.e.sis, Wright State University) 26 Tweets from a city City Infrastructure https://osf.io/b4q2t/ P. Anantharam, P. Barnaghi, K. Thirunarayan, A. Sheth, "Extracting city events from social streams,“, under review, 2014.
  • 27.
  • 28.
  • 29.
    Data analytics framework Ambient Intelligence Social systems Interactions Interactions 29 Data Data Data: Domain Knowledge Domain Knowledge Social systems Open Interfaces Open Interfaces Ambient Intelligence Quality and Trust Quality and Trust Privacy and Security Privacy and Security Open Data Open Data
  • 30.
    In Conclusion −Smart cities are complex social systems and no technological and data-analytics- driven solution alone can solve the problems. − Combination of data from Physical, Cyber and Social sources can give more complete, complementary data and contributes to better analysis and insights. − Intelligent processing methods should be adaptable and handle dynamic, multi-modal, heterogeneous and noisy and incomplete data. − Effective visualisation and interaction methods are also key to develop successful solutions. − There are several solution for different parts of a data analytics framework in smart cities. An integrated approach is more effective in which IoT devices, communication networks, data analytics and learning algorithms and methods, services and interaction and visualistions and methods (and their optimisation algorithms) can work and cooperate together. 30
  • 31.
    Q&A − Thankyou. − EU FP7 CityPulse Project: http://www.ict-citypulse.eu/ @ictcitypulse p.barnaghi@surrey.ac.uk