Semantics and Data Analytics for Smart City Applications
Tutorial at 12th Extended Semantic Web Conference (ESWC)
We are witnessing an era where advancements in networking, software and hardware technologies are enabling billions of smart devices and objects to be connected to the Internet. While the new technologies pave the way towards a new generation of smart city applications and services, the variation in modality, quality, formats and representations of smart city data are amongst the crucial issues that hinder effective use of the real world data collected by the sensory devices. Typically in a smart city framework, higher-level abstractions need to be created from real world data streams using data analytics methods for event processing and knowledge extraction purposes in a scalable way. Additionally, Semantic Web technologies and Linked Data play a key role in providing interoperability, association analysis, information and knowledge extractions, and reasoning about trust, privacy, provenance, and security in smart city frameworks. This tutorial will explore different processing steps for smart city data from data acquisition and semantic annotation to event processing, information extraction and pattern analysis in different smart city scenarios and using available cutting-edge tools.
|Payam Barnaghi||Institute for Communication Systems (ICS)
University of Surrey, Guildford, UK
|Ali Intizar||Insight, Centre for Data Analytics (insight)
National University of Ireland, Galway (NUIG)
|Şefki Kolozali||Institute for Communication Systems (ICS)
University of Surrey, Guildford, UK
|Alessandra Mileo||Insight, Centre for Data Analytics (insight)
National University of Ireland, Galway (NUIG)
This full-day tutorial will demonstrate the application of semantics for Smart Cities. We will demonstrate how semantic technologies are key enablers in smart city applications and what is their role in the processing pipeline from row data to actionable knowledge. The tutorial will include four key processing steps that will correspond to four practical sessions of 2.5 hours each, two in the morning and two in the afternoon:
The main topics of the tutorial will include:
- Data collection and semantic annotation
- On-demand Discovery and Federation of Urban IoT Data Streams
- Event pattern detection
- Robustness in Smart City Applications
- Understanding of real world data collection, annotation, discovery and processing techniques
- Ability to discuss and showcase challenges, issues and potential solutions in dealing with large-scale dynamic data in smart city applications
- Ability to apply processing techniques and solutions for providing interoperable smart city data and processing them for extracting higher-level abstractions, including aggregation, mining, query processing and reasoning
- Hands-on experience on working with data annotation and processing tools and software solutions for smart city data analysis
- Ability to describe and analyse different processing steps to extract actionable information from raw sensory data and to show the role of semantic annotation and semantic analysis in the processing chain
- Familiarity with data-enabled smart city applications and use-cases
Participants will be provided with a virtual machine image and an open source layer tool to run semantic annotation (e.g. Protege, X-GSN, LSM), stream analysis software tools (e.g. KAT), the adaptive components (ACEIS), the continuous query processing engine (CQELS) and the inference rules for event filtering (Answer Set Programming solver Clingo4). We will also use use real city datasets available through the EU project CityPulse.
Timeliness, Visibility and Related Tutorials
This is the first tutorial specifically focusing on demonstrating the role of semantic technologies in smart city applications. Following the successful past workshops on Semantics for Smart Cities (SSC) held in conjunction with ISWC over the last few years, we expect the tutorial to capture the interest of a wide growing community working on semantic technologies to tackle the velocity and the variety challenges in the utilisation of Big Data for Smart Cities. There is a specific need to introduce the community to existing Semantic Web and Internet of Things solutions that can be tailored to their needs and can play a crucial role in creating new Smart City Services. We believe this has high potential in attracting a new audience of city stakeholders and industries, as well as researchers in Big Data.
9.00 - 10.30
Background-Theory (90min) [slides]
The first session gives an overview of the CityPulse project, Smart Cities and IoT applications, covering:
- Real world data
- Interoperability and metadata frameworks
- Data quality and reliability
- Intelligent data processing for the Internet of Things
11.00 - 12.30 (90min)
Virtualisation and Validation of Smart City Data [slides]
This session presents and demonstrates the CityPulse information modesl and how they can be used to semantically annotate sensory data and how they can be validated using CityPulse tools.
- An introduction to Linked Data concepts and how and why they should be used in the context of Smart Cities and IoT related studies.
- Using practical examples we will explore what data sets are already available in cities and how they can be used to answer questions in the context of Smart Cities.
- We will also explore how signal processing tools and results can be described as structured data.
- We will demonstrate how Smart City related sensory structured data can be validated with an SSN Validator.
- Finally, we will demonstrate tools and best practice for researchers who wish to publish their own data sets on the Semantic Web in a Linked Data fashion.
Hands on session involves: (1h)
14:00 - 15.30 (90min)
Stream discovery, query, and event processing (90m) [slides]
This session presents stream discovery, query and event processing techniques of CityPulse Framework.
- Data and Process interoperability for RDF stream processing
- QoI-aware Stream Discovery
- On-Demand stream federation and optimization of processing for complex event streams
- Adaptive stream federation and event filtering
- Rule-based decision support for IoT-Intelligence
- Dealing with Uncertainty in IoT-intelligence
16:00 - 17.00 (60min)
This session presents stream query and event processing techniques of CityPulse Framework.
17:00 - 17.45 (45min)
Wrap-up and conclusions
This session covers:
- Achievements of existing approaches w.r.t. IoT intelligence challenges
- Open problems and a revised IoT intelligence research agenda
- Open Q/A
- Sefki Kolozali, Maria Bermudez-Edo, Daniel Puschmann, Frieder Ganz, Payam Barnaghi, "A Knowledge-based Approach for Real-Time IoT Data Stream Annotation and Processing", in Proc. of the 2014 IEEE International Conference on Internet of Things (iThings 2014), Taipei, Taiwan, September 2014.
- Kolozali S, Elsaleh T, Barnaghi P. (2014) “A Validation Tool for the W3C SSN Ontology based Sensory Semantic Knowledge”. The 13th International Semantic Web Conference
- Stefan Bischof, Athanasios Karapantelakis, Cosmin-Septimiu Nechifor, Amit Sheth, Alessandra Mileo and Payam Barnaghi, "Semantic Modeling of Smart City Data", Position Paper in W3C Workshop on the Web of Things: Enablers and services for an open Web of Devices, 25-26 June 2014, Berlin, Germany.
- R. Tönjes, P. Barnaghi, M. Ali, A. Mileo, M. Hauswirth, F. Ganz, S. Ganea, B. Kjærgaard, D. Kuemper, S. Nechifor, D. Puiu, A. Sheth, V. Tsiatsis, L. Vestergaard, "Real Time IoT Stream Processing and Large-scale Data Analytics for Smart City Applications", poster session, European Conference on Networks and Communications 2014.
- Feng Gao, Muhammad Intizar Ali, Edward Curry, Alessandra Mileo: QoS-aware Stream Federation and Optimization based on Service Composition. ACM Transactions on Internet Technology, to appear 2015.
- Matthias Nickles, Alessandra Mileo: Web Stream Reasoning Using Probabilistic Answer Set Programming. RR 2014: 197-205
- Alessandra Mileo, Ahmed Abdelrahman, Sean Policarpio, Manfred Hauswirth: StreamRule: A Nonmonotonic Stream Reasoning System for the Semantic Web. RR 2013: 247-252
- Feng Gao, Edward Curry, Muhammad Intizar Ali, Sami Bhiri, Alessandra Mileo: QoS-Aware Complex Event Service Composition and Optimization Using Genetic Algorithms. ICSOC 2014: 386-393
To register, visit:http://2015.eswc-conferences.org/
p DOT barnaghi AT surrey DOT ac DOT uk