Dynamic Data Analytics for the Internet of Things: Challenges and Opportunities

Similar documents
How To Help The European Single Market With Data And Information Technology

Horizontal IoT Application Development using Semantic Web Technologies

Beyond CRM: a new era for Customer Engagement SAP hybris - Customer Engagement & Commerce

Semantics for the Internet of Things: early progress and back to the future

M2M Communications and Internet of Things for Smart Cities. Soumya Kanti Datta Mobile Communications Dept.

Internet of Things (IoT): A vision, architectural elements, and future directions

Towards Smart and Intelligent SDN Controller

Standards for Big Data in the Cloud

Service Engineering for the Internet of Things

Information Services for Smart Grids

BIG. Big Data Analysis John Domingue (STI International and The Open University) Big Data Public Private Forum

IEEE International Conference on Computing, Analytics and Security Trends CAST-2016 (19 21 December, 2016) Call for Paper

DGE /DG Connect

Key Challenges in Cloud Computing to Enable Future Internet of Things

FoF a: Digital Automation - Collaborative Manufacturing and Logistics. Dr. Alok Choudhary A.Choudhary@lboro.ac.

Cloud computing based big data ecosystem and requirements

How To Make Sense Of Data With Altilia

/ WHITEPAPER / THE BIMODAL IT

Proposal for the Theme on Big Data. Analytics. Qiang Yang, HKUST Jiannong Cao, PolyU Qi-man Shao, CUHK. May 2015

Internet of Things Value Proposition for Europe

Accenture and SAP: Delivering Visual Data Discovery Solutions for Agility and Trust at Scale

ICT 10: Software Technologies

From a World-Wide Web of Pages to a World-Wide Web of Things

3rd International Symposium on Big Data and Cloud Computing Challenges (ISBCC-2016) March 10-11, 2016 VIT University, Chennai, India

The Data Lifecycle: Managing Data through Business. Ewan Willars Friday 27 February

Cloud and Big Data Standardisation

Are You Big Data Ready?

internet of things Patrick Pax Business Development Manager Chris Geary Innovation Manager

Kimmo Rossi. European Commission DG CONNECT

Intrusion Detection via Machine Learning for SCADA System Protection

ATA DRIVEN GLOBAL VISION CLOUD PLATFORM STRATEG N POWERFUL RELEVANT PERFORMANCE SOLUTION CLO IRTUAL BIG DATA SOLUTION ROI FLEXIBLE DATA DRIVEN V

How To Turn Big Data Into An Insight

Web of Things Use Cases and Solutions at FZI

ICT 10: Software Technologies

Web of Systems for a digital world

Navigating Big Data business analytics

CONNECTING DATA WITH BUSINESS

> Solution Overview COGNIZANT CLOUD STEPS TRANSFORMATION FRAMEWORK THE PATH TO GROWTH

MAX DOLGICER THE INTERNET OF THINGS NAVIGATING THE FUTURE OF INFORMATION TECHNOLOGY

Internet of Things The EU research agenda Information Day. Thibaut KLEINER European Commission - DG CONNECT Head of Unit E1: Network Technologies

Tomáš Müller IT Architekt 21/04/2010 ČVUT FEL: SOA & Enterprise Service Bus IBM Corporation

Standards for Big Data in the Cloud

Evolving from SCADA to IoT

IBM Business Analytics and Optimization The Path to Breakaway Performance

Bruhati Technologies. About us. ISO 9001:2008 certified. Technology fit for Business

Big Data, Physics, and the Industrial Internet! How Modeling & Analytics are Making the World Work Better."

UNIVERSITY OF INFINITE AMBITIONS. MASTER OF SCIENCE COMPUTER SCIENCE DATA SCIENCE AND SMART SERVICES

How telcos can benefit from streaming big data analytics

White Paper. Real-time Customer Engagement and Big Data are Changing Marketing

Open Services for IoT Cloud Applications in the Future Internet

"Increasing demand for intelligent cities and IoT devices is expected to drive the Internet of Things (IoT) in smart cities market"

Concept and Project Objectives

FITMAN Future Internet Enablers for the Sensing Enterprise: A FIWARE Approach & Industrial Trialing

Did you know? Accenture can deliver business outcome-focused results for your life sciences research & development organization like these:

Standard Big Data Architecture and Infrastructure

Workprogramme

Trading. Next Generation Monitoring. James Wylie Senior Manager, Product Marketing

An Introduction to Advanced Analytics and Data Mining

Solve your toughest challenges with data mining

H2020-EUJ-2016: EU-Japan Joint Call. EUJ : IoT/Cloud/Big Data platforms in social application contexts

Towards an On board Personal Data Mining Framework For P4 Medicine

Towards a Thriving Data Economy: Open Data, Big Data, and Data Ecosystems

Defining. the. Infrastructure. for. Big Data

Profile. Business solutions with a difference

NSF Workshop: High Priority Research Areas on Integrated Sensor, Control and Platform Modeling for Smart Manufacturing

The IoT/CPS Big Data Challenge

Salmat Customer Engagement Solutions

Your door to future governance solutions

IoT Analytics: Four Key Essentials and Four Target Industries

A Roadmap for Future Architectures and Services for Manufacturing. Carsten Rückriegel Road4FAME-EU-Consultation Meeting Brussels, May, 22 nd 2015

The Internet of Things. Giles Norman MobileFirst Consulting Manager, IBM. Daniel Dombach Director EMEA, Industry Solutions, Zebra Technologies

ICT Perspectives on Big Data: Well Sorted Materials

The 5G Infrastructure Public-Private Partnership

Big Data Analytics in Mobile Environments

Autonomic IoT Systems Realizing Self-* Properties in IoT Systems

An Analysis of Reference Architectures for the Internet of Things

IoT is a King, Big data is a Queen and Cloud is a Palace

The Next Big Thing in the Internet of Things: Real-Time Big Data Analytics"

perspective Progressive Organization

Transcription:

Dynamic Data Analytics for the Internet of Things: Challenges and Opportunities Payam Barnaghi Institute for Communication Systems (ICS) University of Surrey/CityPulse Consortium Guildford, United Kingdom IoT Large-Scale Analytics Workshop IoT Week Lisbon, June 2015 1

Contextual Challenges Data Volume Security, Reliability, Trust and Privacy AnyThing Networking and Communication AnyPlace AnyTime Services and Applications Societal Impacts, Economic Values and Viability 2

IoT Data- Challanges 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 can be biased- we need to know our data! 3

Relying merely on data from sources that are unevenly distributed, without considering background information or social context, can lead to imbalanced interpretations and decisions. It s also about automation in addition to insight and information extraction.? 4

Data Lifecycle Source: The IET Technical Report, Digital Technology Adoption in the Smart Built Environment: Challenges and opportunities of data driven systems for building, community and city-scale applications, http://www.theiet.org/sectors/built-environment/resources/digital-technology.cfm 5

IoT environments are usually dynamic and (near-) real-time Off-line Data analytics Data analytics in dynamic environments Image sources: ABC Australia and 2dolphins.com 6

IoT Data 7

Deep IoT 8

The ultimate goal is transforming the raw data to insights and actionable knowledge and/or creating effective representation forms for machines and also human users and creating automation. This usually requires data from multiple sources, (near-) real time analytics and visualisation and/or semantic representations. 9

Data will come from various source and from different platforms and various systems. This requires an ecosystem of IoT systems with several backend support components (e.g. pub/sub, storage, discovery, and access services). Semantic interoperability is also a key requirement. 10

Search on the Internet/Web in the early days 11

IoT discovery engines? Working across different systems and various platforms is a key requirement. Internet search engines work very well with textual data, but IoT data comes in various forms and often as streams. This requires an ecosystem of IoT systems with several backend support components (e.g. pub/sub, storage, discovery, and access services). 12

IoT discovery engines? To make it more complex, IoT resources are often mobile and/or transient. Quality and trust (and obviously privacy) are among the other key challenges. This requires efficient distributed index and update mechanisms, quality-aware an resourceaware selection and ranking, and privacy control and preservation methods (and governance models). 13

Accessing IoT data The internet/web norm (for now) is usually searching for the data; the search engines are usually information locators return the link to the information; IoT data access is more opportunistic and context aware. This requires context-aware and opportunistic push mechanism, dynamic device/resource associations and (software-defined) data routing networks. 14

Web search is already adapting this model Image credits: the Economist 15

A discovery engine for the IoT A. HosseiniTabatabaie, P. Barnaghi, C. Wang, L. Dong, R. Tafazolli, "Method and Apparatus for Scalable Data Discovery in IoT Systems, US Patents, May 2014. 16

CityPulse demo 17

KAT- Knowledge Acquisition Toolkit http://kat.ee.surrey.ac.uk/

The future: borders will blend Source: IEEE Internet Computing, Special issue on Physical-Cyber-Social Computing 19

In conclusion IoT data analytics is different from common big data analytics. Data collection in the IoT comes at the cost of bandwidth, network, energy and other resources. Data collection, delivery and processing is also depended on multiple layers of the network. We need more resource-aware data analytics methods and cross-layer optimisations (Deep IoT). The solutions should work across different systems and multiple platforms (Ecosystem of systems). Data sources are more than physical (sensory) observation. The IoT requires integration and processing of physical-cyber-social data. The extracted insights and information should be converted to a feedback and/or actionable information. 20

Smart city datasets http://iot.ee.surrey.ac.uk:8080 21

IET sector briefing report Available at: http://www.theiet.org/sectors/built-environment/resources/digital-technology.cfm 22

Q&A Thank you. EU FP7 CityPulse Project: http://www.ict-citypulse.eu/ @pbarnaghi p.barnaghi@surrey.ac.uk