31
CityPulse: Large-scale data analytics for smart cities 1 Payam Barnaghi Institute for Communication Systems (ICS) University of Surrey Guildford, United Kingdom

CityPulse: Large-scale data analytics for smart cities

Embed Size (px)

DESCRIPTION

IEEE iThings2014, Panel Talk (EU-Taiwan collaboration panel), Taipei, Taiwan, 2014.

Citation preview

Page 1: CityPulse: Large-scale data analytics for smart cities

CityPulse: Large-scale data analytics for smart cities

1

Payam BarnaghiInstitute for Communication Systems (ICS)University of SurreyGuildford, United Kingdom

Page 2: CityPulse: Large-scale data analytics for smart cities

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

Page 3: CityPulse: Large-scale data analytics for smart cities

Smart City Data

3

?

Page 4: CityPulse: Large-scale data analytics for smart cities

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

Page 5: CityPulse: Large-scale data analytics for smart cities

What type of problems we expect to solve in

“smart” cities

Page 6: CityPulse: Large-scale data analytics for smart cities

Back to the future

6

Page 7: CityPulse: Large-scale data analytics for smart cities

7Source LAT Times, http://documents.latimes.com/la-2013/

Future cities: a view from 1998

Page 8: CityPulse: Large-scale data analytics for smart cities

8Source: http://robertluisrabello.com/denial/traffic-in-la/#gallery[default]/0/

Source: wikipedia

Page 9: CityPulse: Large-scale data analytics for smart cities

9

Page 10: CityPulse: Large-scale data analytics for smart cities

The IoT and its applications

10

IoT

Diffusion of innovation

image source: Wikipedia

The Most Hyped Technology

image source: Forbes via Gartner

Page 11: CityPulse: Large-scale data analytics for smart cities

Moving fast forward

11

Source: AdamKR via Flicker, http://www.flickr.com/photos/adamkr/5045295251/in/photostream/

Page 12: CityPulse: Large-scale data analytics for smart cities

12

We need an Integrated Approach

Page 13: CityPulse: Large-scale data analytics for smart cities

13

CityPulse Consortium

Industrial SIE (Austria,

Romania), ERIC

SME AI

HigherEducation

UNIS, NUIG,UASO, WSU

City BR, AA

Partners:

Duration: 36 months

Page 14: CityPulse: Large-scale data analytics for smart cities

14

Processing steps

AnalyticsToolbox

Context-awareDecision Support,

Visualisation

Knowledge-based

Stream Processing

Real-TimeMonitoring &

Testing

Accuracy & Trust

Modelling

SemanticIntegration

On Demand Data

Federation

OpenReferenceData Sets

Real-TimeIoT InformationExtraction

IoT StreamProcessing

Federation ofHeterogenousData Streams

Design-Time Run-Time Testing

Exposure APIs

Page 15: CityPulse: Large-scale data analytics for smart cities

CityPulse – what we are going to deliver

...

Data Streams

Smart City Framework

Smart City Scenarios

a) Software tools/librariesin an integrated frameworkb) Back-end support servers

a) 101 scenariosb) 10 will be chosen to be prototyped

a) Data portals/ real-time access interfacesb) Interoperable formatsc) Common interfaces (REST/annotated)

a) Proof-of-Concepts and demonstrators and evaluations;Applications/Apps/Demos

Link: http://www.ict-citypulse.eu/page/content/smart-city-use-cases-and-requirements

Page 16: CityPulse: Large-scale data analytics for smart cities

Stream Processing

...

Data Streams

CityPulse

Page 17: CityPulse: Large-scale data analytics for smart cities

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

Page 18: CityPulse: Large-scale data analytics for smart cities

Some of our recent in this domain

18

Page 19: CityPulse: Large-scale data analytics for smart cities

Use cases

Page 20: CityPulse: Large-scale data analytics for smart cities

Scenario ranking

Page 21: CityPulse: Large-scale data analytics for smart cities

101 Smart City Use-case Scenarios

http://www.ict-citypulse.eu/page/content/smart-city-use-cases-and-requirements

Page 22: CityPulse: Large-scale data analytics for smart cities

101 Scenarios

− http://www.ict-citypulse.eu/page/content/smart-city-use-cases-and-requirements

Page 23: CityPulse: Large-scale data analytics for smart cities

Data abstraction

23F. Ganz, P. Barnaghi, F. Carrez, "Information Abstraction for Heterogeneous Real World Internet Data", IEEE Sensors Journal, 2013.

Page 24: CityPulse: Large-scale data analytics for smart cities

Ontology learning from real world data

24

Page 25: CityPulse: Large-scale data analytics for smart cities

Adaptable and dynamic learning methods

http://kat.ee.surrey.ac.uk/

Page 26: CityPulse: Large-scale data analytics for smart cities

Social media analysis (collaboration with Kno.e.sis, Wright State University)

26

City Infrastructure

Tweets from a city

P. Anantharam, P. Barnaghi, K. Thirunarayan, A. Sheth, "Extracting city events from social streams,“, under review, 2014.

https://osf.io/b4q2t/

Page 27: CityPulse: Large-scale data analytics for smart cities

Correlation analysis

27

Page 28: CityPulse: Large-scale data analytics for smart cities

28

Page 29: CityPulse: Large-scale data analytics for smart cities

Data analytics framework

29

Data:

Data

Domain

Knowledge

Socialsystems

InteractionsOpen Interfaces

Ambient

IntelligenceQuality and Trust

Privacy and

Security

Open Data

Page 30: CityPulse: Large-scale data analytics for smart cities

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

Page 31: CityPulse: Large-scale data analytics for smart cities

Q&A

− Thank you.

− EU FP7 CityPulse Project:

http://www.ict-citypulse.eu/

@ictcitypulse

[email protected]