SmartResource:%20Proactive%20Self-Maintained%20Resources%20in%20Semantic%20Web

1
SmartResource Proactive Self-Maintained
Resources in Semantic Web

• TEKES Project proposal
• Vagan Terziyan, Project Leader
• Industrial Ontologies Group
• Agora Center, University of Jyväskylä

2
Content

• Introduction
• Project Essentials
• Project Potential and Future Market
• Relation to TEKES Programs
• Project Team
• Relation to InBCT TEKES Project (3.1.3.)
• Project Budget

3
Semantic Web in Networked BusinessEnvironment
Networked Business Environment requires new
advanced ways of data and knowledge
management Industrial Maintenance domain is a
good application case for the concept of the
Networked Business Environment Networked
Maintenance Environment will bring all benefits
of the knowledge management, delivering
value-added services and integration of businesses
In a networked business environment Metso will
be a business hub controlling the flow of
information in the network of installed Metso
devices and solutions, and Metsos customers and
partners.
Semantic Web technology provides standards for
metadata and ontology development such as
semantic annotations (Resource Description
Framework) and knowledge representation (Web
Ontology Language). It facilitates
interoperability of heterogeneous components,
authoring reusable data and intelligent,
automated processing of data. Semantic Web is
an enabling technology for the future Networked
Business Environment
4
Project Essentials
S m a r t R e s o u r c e

• Project goal is to combine the emerging Semantic
  Web, Web Services, Peer-to-Peer and Agent
  technologies for the development of a global and
  smart maintenance management environment, to
  provide Web-based support for the predictive
  maintenance of industrial devices by utilizing
  heterogeneous and interoperable Web resources,
  services and human experts

Tekes Project Application, Submitted January 2004
5
Industrial Resources

• Classes of resources in maintenance systems
• Devices - increasingly complex machines,
  equipment, etc., that require costs-demanding
  support
• Processing Units (Services) embedded, local and
  remote systems, for automated intelligent
  monitoring, diagnostics and control over devices
• Humans (Experts) qualified users of the system,
  operators, maintenance experts, a limited
  resource that should be reused

6
Smart Maintenance Environment
Experts
Devices with on-line data
exchange
data
Maintenance
7
Project Objectives (Year 1)
Define Semantic Web-based framework for
unification of maintenance data and
interoperability in maintenance system

• Research and Development
• Resource State/Condition Description Framework
  (RSCDF) based on Semantic Web and extension of
  RDF (Resource Description Framework)
• RSCDF adapters (wrappers)
• for devices, services and experts
• - browsable devices
• - application-expert interface
• - RSCDF-enabled services

8
Project Objectives (Year 2)
Development of agent-based resource management
framework and enabling meaningful resource
interaction

• Adding agents to resources
• Making resource proactive
• Enabling communication
• with resource
• Implementation of agent-communication scenarios
• service learning
• remote diagnostics

9
Project Objectives (Year 3)
Development of networked maintenance environment

• Development of P2P agent-communication system
• Resource Discovery
• Maintenance Data Knowledge Integration
• Certification and credibility assessment of
  services
• Research of the Resource Goal/Behavior
  Description Framework
• Semantic modelling of a resource proactive
  behavior
• Exchanging integrating models of resource
  (maintenance) behavior
• Testing on-the-field using
• Real devices
• Existing diagnostic software as Web-services
• Experts

10
Maintenance Networking Environment
Semantic Web environment
11
P2P networking
- network of hubs
- highly scalable
- fault-tolerable

• supports dynamic changes
• of network structure

• does not need
• administration

• Why to interact?
• Resource summarizes opinions from multiple
  services
• Services learns from multiple teachers
• One service for multiple similar clients
• Resources exchange lists of services
• Services exchange lists of clients.

12
Integrating services
Device
Labelled data
Service
Service
13
Integrating knowledge
Service

• Service builds classification model many
  techniques are possible, e.g.
• own model for each device
• one model from several devices of the same
  type (provides device experience exchange) .

Diagnostic model
1
Diagnostic model
n
Device
Device
Device
Labelled data
Device
Device
Device
Labelled data
Labelled data
Labelled data
Labelled data
Labelled data
14
Certification
Sure, there are security threats as in any
open environment. Security is to be ensured using
existing solutions for Internet environment.
Existence of certification authorities is
required in the network. Certificates gained by
services and trust to the certificate issuer are
factors that influence optimal service selection.
The quality of service is evaluated by users as
well.
15
Development Stages
Project will produce 3 versions of prototype
software by implementing the following components
and functionality

• Year 1 Resource Adapters to the RSCDF-based
  unification of resource data Remote resource
  access in Semantic Web environment
• Year 2 Resource Agents for remote diagnostics
  Learnability of services
• Year 3 Support for semantic P2P networking and
  diagnostic services integration

16
Project Results
Adaptation of resources (devices, services,
experts) to the Environment
Support for service learning
Resource Proactivity
Resource Agent
Interaction One device many services
17
Project Potential and Future Market
Tekes Project Application, Submitted January 2004
18
Universality

• We are heading to a development of comprehensive
  and universal frameworks for intelligent
  information management
• SmartResource project is one step in our
  advancement towards applications of our vision,
  approach and expertise in many other domains
• Semantic Web-based solutions enable to combine
  heterogeneous information, methods and resources
  together

19
Smart Maintenance Environment
exchange
data
Maintenance
On-line learning
20
Smart Maintenance Environment
exchange
data
Maintenance
On-line learning
21
Smart Maintenance Environment
exchange
data
Maintenance
On-line learning
22
Smart Maintenance Environment
exchange
data
Maintenance
On-line learning
23
Customers of the system
Experts, which want to provide their experience
and knowledge in domain of remote diagnostics,
condition monitoring and maintenance of
industrial devices.
Experts
Web Service and Application providers
Producers of the Field Devices
Producers of the Field Devices, which are
interested to provide more effective product
maintenance and remote diagnostic for their
customers.
Providers of the diagnostic, maintenance,
condition monitoring services, which want to make
them available for customers through the net.
24
Smart Maintenance Environment
IT Providers applications, services, solutions
Manufacturer of industrial products
User
Expert
Service- mediator
Sensor
Web Service
Smart-Device
Smart-System
Application
Smart Maintenance Environment
25
Application domainsTelemedicineWellness
Doctor/Expert
Doctor/Expert
Service
Health Maintenance
Service
Service
Health Maintenance
Symptom data
26
Application domainsBuilding Conditioning
Automation of the Building Conditioning via
a House Maintenance System, embedded sensor
system of a house state, local house- condition
alarm system, and global system for house remote
diagnostics and predictive maintenance
Service
Service
Service
Expert
Expert
Expert
House systems sensors
27
Relation to TEKES Programs
Tekes Project Application, Submitted January 2004
28
Relation to TEKES programs

• SmartResource project is positioned out of
  particular TEKES program, because
• It deals with basic and hottest ICT
  technologies (Semantic Web, agents, web services,
  P2P...)
• It aims at development of expertise and killer
  application for innovative universal solutions
  that contribute to competitiveness and know-how
  in the long run
• Research results are potentially applicable in
  many other domains (beyond being studied in the
  industrial case).

29
Relation to TEKES programs

• FENIX - Interactive Computing.
• human as initiators and coordinators in resource
  maintenance
• domain experts, operators as resources
• human interaction with Semantic Web-based
  environment.
• Intelligent Automation Systems
• prototype development of industrial system
• proactivity of resources Agent technology
• integration of heterogeneous systems
• Semantic Web Web Services P2P Agents
• DENSY - Distributed energy systems technology
  program
• SmartResource-environment is an excellent base
  for launching intelligent software, which
  implements various collaborative logics
  knowledge share, management, etc.
• Drug 2000 - biomedicine, drug development and
  pharmaceutical technology
• We could suggest Ontology-Based Automated
  Maintenance of Globally Distributed Approved
  Medications and New Drags Lists. Large amounts
  of various electronic resources (databases,
  documents, media, hypertexts) about drugs makes
  difficult their management and update. Making
  these resources active according to our concepts
  we automate their maintenance.

30
Project Team
Tekes Project Application, Submitted January 2004
31
Our Team Industrial Ontologies Group

• Head
• Vagan Terziyan
• Contact Person (University of Jyväskylä)
• Timo Tiihonen
• Researchers
• Oleksandr Kononenko
• Andriy Zharko
• Oleksiy Khriyenko
• Olena Kaykova
• Consultant (Metso Automation)
• Jouni Pyötsiä

Industrial Ontologies Group http//www.cs.jyu.f
i/ai/OntoGroup/
32
Project Members

• Timo Tiihonen
• Project Contact Person
• Profile
• Mathematical Modeling and Simulation
• Modeling and Control of Industrial Paper-Making
  Processes, Metal and Semiconductor Industries
• Data Integration in Management and Administration

• Vice-Rector, Professor, Ph.D.

Professor Timo Tiihonen who acts as the contact
person has, as a professor of mathematical
modeling and simulation, broad experience of
modeling and control of industrial processes in
paper making, metal and semiconductor industries.
Currently he is actively integrating the data
administration of the university as a vice-rector
and exploiting the results of this project to
management of diverse human resources.
http//www.mit.jyu.fi/tiihonen/
33
Project Members

• Vagan Terziyan
• Project Leader
• Profile
• Artificial Intelligence
• Knowledge Management
• Agent Technology
• Semantic Web
• Machine Learning
• Data Mining

• Head of AI Department, Professor, Dr. (Habil)
  Tech.
• Associate Professor, Senior Researcher
  (Agora Centre)

1981 Ms. Eng. (Applied mathematics) 1985 Dr.
Tech. (Cybernetics and IT) 1993 Dr. (Habil)
Tech. (IS and AI) 1996 Professor (Software
Engineering) 2001 Docent, University of
Jyvaskyla (AI and Knowledge
Management) 2002-2004 Ass. Prof., Department of
Mathematical Information
Technology, Senior Researcher,
Agora Center, University of Jyvaskyla,
Visiting Prof., Free University of
Amsterdam
http//www.cs.jyu.fi/ai/vagan/
34
Project Members

• Olena Kaykova
• Researcher
• Profile
• Control Systems
• Artificial Intelligence
• Temporal Logic
• Machine Learning
• Integrated Models
• International Relations
• Management

• Associate Professor, Dr. Tech.
• Senior Researcher (Agora Centre)

1982 Ms. Eng. (Control Systems) 1989 Dr. Tech.
(Cybernetics and IT) 1992 Ass. Prof. (Software
Engineering) 2002-2003 Lecturer, Department
of Mathematical Information
Technology, University of Jyvaskyla 2004 Senior
Researcher, Agora Center
http//www.cs.jyu.fi/ai/helen/
35
Project Members

• Oleksandr Kononenko
• Researcher-Developer
• Main Duties
• Software design
• RSCDF and RGBDF design/ Ontology development
• Resource Adapter development
• Project documentation

2002 2003 Degree student at MIT Department,
University of Jyväskylä. His thesis
Ontological Support for Industrial Maintenance
of Smart-Devices gets laudatur grade, and he
becomes M.Sc. in Information Technology 2004-pres
ent PhD student at the MIT Department,
University of Jyväskylä
Human-Computer Interaction in Semantic Web
http//www.cc.jyu.fi/olkonone/
36
Project Members

• Oleksiy Khriyenko
• Researcher-Developer
• Main Duties
• Resource Agent development
• Resource Adapter development
• Software documentation

2002 2003 Degree student at MIT Department,
University of Jyväskylä. He writes thesis
Distributed Mobile Web Services Based on
Semantic Web (laudatur grade), and becomes
M.Sc. in Information Technology 2004-present
PhD student at the MIT Department, University of
Jyväskylä Adaptive Semantic Web based
Environment for Web Resources
http//www.cc.jyu.fi/olkhriye/
37
Project Members

• Andriy Zharko
• Researcher-Developer
• Duties
• Ontology development
• P2P communication subsystem development
• Web services development

2002 2003 Degree student at MIT Department,
University of Jyväskylä. His thesis
Peer-to-Peer Ontological Discovery of Mobile
Service Components in Semantic Web wins
departments award, he is M.Sc. in Information
Technology 2004-present PhD student at the
MIT Department, University of Jyväskylä
Active Resources in Semantic Web
http//www.cc.jyu.fi/anzharko/
38
Project Members

• Andriy Zharko
• Researcher-Developer
• Profile
• Semantic Web
• P2P
• Web Services

Educational backgrounds and Expertise
2002 2003 Degree student at MIT Department,
University of Jyväskyla. Thesis Peer-to-Peer
Ontological Discovery of Mobile Service
Components in Semantic Web wins departments
award, he is M.Sc. in Information
Technology 2004-present PhD student at the
MIT Department, University of Jyväskylä
Active Resources in Semantic Web
http//www.cc.jyu.fi/anzharko/
39
International Cooperation (1)
Prof. Frank Harmelen
Prof. Catholijn Jonker
Dynamics of agent behavior
Reasoning about diagnostic systems
Multiagent systems design
Semantic Web
Ontology Learning
Diagnostics of organizations
Ontology Integration
Prof. Jan Treur
Borys Omelayenko
40
International Cooperation (2)
Volodymyr Kushnaryov
Prof. Yevgeniy Bodyanskiy
Industrial Automation
Neuro-Fuzzy Networks
Industrial diagnostics, prediction and control
Machine Learning
Telemedicine
Kharkov National University of Radioelectronics
Ukraine
Data Mining and Knowledge Discovery
Ontologies in Education
Bayesian Networks
Dr. Oleksandra Vitko
Statistics
Prof. Natalya Lesna
41
Related European Research Initiatives (1)

• There are several going on EU funded
  projects, which are targeting various aspects of
  emerging Semantic Web. Among most strong
  consortiums and initiatives are
• OntoWeb1 network with more than 100 academic
  and industrial participants, which creates a
  technical roadmap of the next generation Web and
  provides guidelines to industrial and commercial
  applications
• SWAP2 (Semantic Web and Peer-to-Peer)
• provides a comprehensive study of the potential
  of Semantic Web and Peer-to-Peer for knowledge
  management and plan to provide an appropriate
  integrated software environment
• SWWS3 (Semantic Web Enabled Web Services)
• researching for scalable mediation between
  different and heterogeneous services based on
  semantic-driven descriptions and business logic
• 1 http//www.ontoweb.org
• 2 http//swap.semanticweb.org
• 3 http//swws.semanticweb.org

42
Related European Research Initiatives (2)

• SEWASIE4 (Semantic Web and Agents in Integrated
  Economies)
• fights the problem of access to heterogeneous
  data sources on the Web
• SCULPTEUR5 (Semantic and Content-Based
  Multimedia Exploitation for European Benefit)
• develops the technology to create, manipulate
  and manage cultural archives to make European
  cultural heritage accessible to all
• MOSES6 (Modular and Scalable Environment for
  the Semantic Web)
• sets out to create scalable ontology based
  Knowledge Management System and ontology-based
  search engine that will accept queries and
  produce answers in natural language
• and many other projects
• 4 http//www.sewasie.org
• 5 http//www.sculpteurweb.org
• 6 http//www.hum.ku.dk/moses/

43
Related Industrial Initiatives

• Among recent initiatives aimed at development of
  adoption of open information standards for
  operations and maintenance and implementation of
  interoperable cooperative industrial environments
  are
• MIMOSA 1 (Machinery Information Management Open
  System Alliance) The project consortium pretends
  to build an open, industry-built, robust
  Enterprise Application Integration and
  condition-based maintenance specifications.
• PROTEUS2, funded by industrial companies and
  led with a goal to develop a generic
  maintenance-oriented platform for industry.
• These initiatives are very expensive, labor and
  resource consuming, and still does not attempt to
  apply and benefit from the Semantic Web
  technology.
• We believe, however, that without comprehensive
  metadata description framework, ontologies and
  open knowledge/semantics representation standards
  their results will be just next consortium-wide
  standards, rather than comprehensive, flexible
  and extensible framework. We will contribute with
  Semantic Web technology to industrial needs
• 1 http//www.mimosa.org/
• 2 http//www.proteus-iteaproject.com/

44
Semantic Facilitators for Web Information
Retrieval
Current activities
InBCT Tekes PROJECT Chapter 3.1.3 Industrial
Ontologies and Semantic Web
45
Pre-Project Activities (2003)

• During 2003 Industrial Ontologies Group
  concentrated its point of research on Semantic
  Web technology applications and web-service based
  information management systems (particularly, in
  the field of maintenance of industrial devices),
  which can be considered as an important research
  input into the Project
• Among results are
• Developed concepts
•  OntoServ.Net, GUN, OntoAdapter, OntoShell,
  Mobile Resource,
• about 20 research papers, including
• publications in scientific journals and
  international conferences, on the topics related
  to this project
• project reports and presentation in InBCT Tekes
  project (section 3.1 - Semantic Web and
  Industrial Ontologies), University of Jyväskylä,
  Agora Center
• 3 M.Sc. theses on the topics of industrial
  maintenance automation and Semantic Web
• Resources in 2003 17 m/months
• Detailed list of publications can be found at
  http//www.cs.jyu.fi/ai/OntoGroup/

46
Semantic Facilitators for Web Information
Retrieval (2004)
InBCT Tekes PROJECT Chapter 3.1.3 Industrial
Ontologies and Semantic Web (year 2004)

• Main Deliverables
• Generic Semantic Search Facilitator concept,
  architecture and ideas for future utilization of
  semantic wrappers for non-semantic search systems
• Implementation of Semantic Search Assistant for
  Google with semantic interface and domain
  ontology.
• Resources
• about 30 KEURO for 24 m/months

47
Enabling the Semantic Search
Semantic Search Enhancement
Common (linguistic) ontology
Semantic Search Assistant (Facilitator) uses
ontologically (WordNet) defined knowledge about
words and embedded support of advanced
Google-search query features in order to
construct more efficient queries from formal
textual description of searched information.
Semantic Search Assistant hides from users the
complexity of query language of concrete search
engine and performs routine actions that most of
users do in order to achieve better performance
and get more relevant results.
Domain ontology
(
)
Query
48
Project Budget
S m a r t R e s o u r c e
Tekes Project Application, Submitted January 2004
49
Budget
Y1 Y2 Y3 Total
Salaries 101564 157402 154938 413904
Taxes 29453 45646 44932 120031 29
Expenses 60268 93402 91940 245610 46
Travels 9000 13000 18000 40000
Materials and supplies 1715 550 190 2455
Equipment 8000 0 0 8000
TOTAL 210000 310000 310000 830000 EURO

• Among Project Members
• 3 Senior Researchers, Dr.Tech.
• 3 Researcher-developers, PhD students, MIT
  Department, JYU
• 3 Researchers, Agora Center
• 3 Researcher-trainees, MIT Department, JYU
• 2 Visiting researchers
• Total person-years 16,3

50
Budget (Year 1)
Year
Salaries 101564
Taxes 29453
Expenses 60268
Travels 9000
Materials and supplies 1715
Equipment 8000
TOTAL 210000
1 Senior Researcher Timo Tiihonen 5300 x 1 5 300
2 Project Leader Vagan Terziyan 3028 x 0,5 x 12 18 168
3 Researcher Helen Kaykova 2369 x 10 23 685
4 Researcher-Developer Oleksandr Kononenko 1814 x 10 18 137
5 Researcher-Developer Oleksiy Khriyenko 1814 x 10 18 137
6 Researcher-Developer Andriy Zharko 1814 x 10 18 137
Person-months 47
51
Project Management Board

• Veikko Hara, Dr.Tech., Senior Vice President,
  TeliaSonera (Head of Project Management Board)
• Jouni Pyötsiä, Dr.Tech., Metso Automation
• Jukka Valkonen, Director, Digital Business
  Development, TietoEnator
• Jutta Nyblom, Paper ICT Expert, Jyväskylä
  Science Park
• Marko Heikkinen, Tekes/Helsinki
• Vagan Terziyan, Dr.Tech., Project Leader, Senior
  Researcher, University of Jyväskylä
• Timo Tiihonen, Prof, Project Contact person,
  Vice-Rector, University of Jyväskylä
• Pekka Neittaanmäki, Prof., Head of Agora Center,
  University of Jyväskylä

52
Industrial Partners and resources in 2004

• TeliaSonera 20 000 EURO
• TietoEnator 10 000
• Jyväskylä Science Park 10 000
• Jyväskylä University 10 000
• Metso Automation 10 000 (own work)
• Applied from Tekes 160 000
• Total (2004) 210 000