SlideShare a Scribd company logo
1 of 46
SPIIRAS
Context-Based Knowledge Fusion Patterns
in Decision Support System for Emergency Response
Alexander Smirnov, Tatiana Levashova, Nikolay Shilov
Computer Aided Integrated Systems laboratory (CAIS Lab)
St.Petersburg Institute for Informatics and Automation
of the Russian Academy of Sciences (SPIIRAS)
St.Petersburg, Russia
ISCRAM 2013
SPIIRAS
Presentation Outline
 Introduction
 Knowledge Fusion Patterns
 Conclusion
2
“Every person has a pattern language in his mind” *
* Alexander C., The Timeless Way of Building.
Oxford University Press, New York, 1979
SPIIRAS
St.Petersburg Institute for Informatics and
Automation (SPIIRAS)
Russian Academy of Sciences (RAS)
 Founded in 1724
 The research umbrella organization of the Russian
Government
 363 units (Research Institutes and Centers)
 112,000 personnel: 55,100 Researchers (10,000 D.Sc., and
26,000 Ph.D.)
St.Petersburg Institute for Informatics and Automation
(SPIIRAS)
 Founded in 1978
 Only 1 Russian Academy of Science Institute operating in
Northwest Russia in Computer Science discipline
 161 Researchers (38 D.Sc., and 59 Ph.D., 34 Ph.D. students,
1 PostDoc)
 Grants Ph.D and Dr.Sc. (Technical) degrees
SPIIRAS
SPIIRAS’ Location
SPIIRAS
CAIS Laboratory:
Financial Support (2007-2013)
Russian Academy of Sciences
 6 projects
 1 grant
 3 projects
 FP6 IST – 1 project (IP)
 ENPI-Finland - 1 project
 2 grants 5 projects
 1 grant
 1 grant
The Swedish Foundation for
International Cooperation
in Research and Higher
Education
 2 grants
 10 projects
 26 grants
Ministry of Education & Science, Russia
Russian Basic Research Foundation
Russian Humanitarian Scientific Foundation
SPIIRAS
Introduction: Using Cyberspace to link Physical
World Information to Communities
Semantic
Integration
Knowledge
Physical World
Cyber-Physical-Social
Systems (CPSs)
Communities /
Social Networks
CPS is a tight integration of physical systems and cyber
(ICT) systems interacting in real time to decision support.
CPSs rely on communication, computation & control
Infrastructures, and Social networks
SPIIRAS
Introduction: Conceptual Framework of
Information Support
 Correct information and knowledge processed and delivered to
the location and time of need and ability to predict at the level of
understanding are needed
Understanding
Knowledge
Information
Data
Information
Transformation
Process
Source: Anken C.: Information Understanding, 5th Anniversary
Information Workshop. Rome, NY, 2002
SPIIRAS
Introduction: Problem Area
• Environments where decision support systems operate
– Large volumes of data, information, and knowledge available in
different sources
• Knowledge fusion
– Integration of information and knowledge from multiple sources into
a common piece of knowledge that may be used for decision making
and problem solving or may provide a better insight and
understanding of the situation under consideration. The expectation
is that the result of knowledge fusion is a new knowledge that is
more complete, less uncertain, and less conflicting than the original
inputs
• Fusion is context-sensitive
– A common challenge for fusion systems is adaptation to the context
of usage
• Environment heterogeneity
– Overcoming the heterogeneity of the environment sources is a
precondition for knowledge fusion
SPIIRAS
Introduction: Research Objectives
• Analysis and investigation of context-based
knowledge fusion processes in Decision Support
System (DSS)
• Discovery of context-based knowledge fusion
patterns with regard to
– Preservation/change of internal structures of
sources involved in knowledge fusion
– Preservation/loss of autonomies of sources
involved in knowledge fusion
– Knowledge fusion effect(s)
SPIIRAS
Introduction: Main Definitions
• Context - any information about the situation in which decisions are made
• Context aware DSS - a system that uses context to provide the decision
maker with a set of decisions that can be made in the current situation
• Knowledge source - a source of data, information, or knowledge which can
be explicitly specified
• Knowledge source structure – a conceptual structure used in the
representation of the knowledge source
• Autonomous knowledge source – a knowledge source having no relations
to other sources; the changes in the autonomous source do not produce
any changes in other sources
• Non-autonomous knowledge source – a knowledge source relating to other
sources; any changes in a non-autonomous knowledge source are passed
to the related sources and reflected in them
• Knowledge fusion - knowledge processing resulting in a synergetic effect,
i.e. an appearance of new knowledge
• Knowledge fusion result / effect – any new knowledge (new knowledge
source, new concept, new property, etc.)
SPIIRAS
Introduction: Background
• Technology of knowledge logistics
– Configuration of knowledge network from heterogeneous sources to
support decisions on involvement of autonomous resources in joint
activities and on scheduling these activities
• Methodology of context management
– Two-level situation representation
• Abstract context: ontology-based non-instantiated representation
of a situation of the given type
• Operational context: a set of abstract context instances under the
actual settings
• Conceptual framework of context-aware decision support
• Generic knowledge fusion patterns
– Absorption
– Extension
– Selective fusion
– Simple fusion
– Flat fusion
SPIIRAS
Introduction: Knowledge Fusion Processes
 Intelligent fusion of massive amounts of heterogeneous data /
information from a wide range of distributed sources into a form
which may be used by systems and humans as the foundation for
problem solving and decision making.
 Integration of knowledge from various knowledge sources resulting
in a completely different type of knowledge or new idea how to solve
the problem.
 Combining knowledge from different autonomous knowledge
sources in different ways in different scenarios, which results in
discovery of new relations between the knowledge from different
sources or/and between the entities this knowledge.
 Re-configuration of knowledge sources to achieve a new
configuration with new capabilities or competencies.
 Knowledge exchange to improve capabilities or competencies
through learning, interactions, discussions, and practices.
 Involving knowledge from various sources in problem solving, which
results in a solution as a new knowledge.
SPIIRAS
Introduction: Synergetic Effects
1. New knowledge object created from data/information;
2. New knowledge type or knowledge product (service, process,
technology, etc.);
3. New knowledge source;
4. New knowledge about the conceptual scheme (new relations,
concepts, properties, etc.);
5. New explicit knowledge;
6. New capabilities / competencies of a knowledge object (an
object that produces or contains knowledge);
7. New problem solving method;
8. Solution for a problem
SPIIRAS
Introduction: Context-Aware Decision
Support System
2013 Теория и практика системной динамики, Апатиты 14
Purpose
Support of decisions on planning emergency response actions
Application ontology Abstract context Operational context
A
B
C F
D
E
G
J
I
A
F
D
E
G
I A
F
D
E
G
I
Knowledge sources Contextual knowledge
sources
Knowledge source
network
A set of
alternatives
Conceptual framework
SPIIRAS
Introduction: Context-aware stages of DSS
 Abstract context building
 Abstract context refinement
 Abstract context reuse
 Knowledge source network configuration
 Operational context producing
 Problem solving
 Decision making
 Decision implementation
 Archival knowledge management
SPIIRAS
Knowledge Fusion Patterns
SPIIRAS
Concepts of Generalization
 Knowledge sources
 Initial knowledge sources are sources that are integrated leading to
emergence of a new knowledge (producing some knowledge fusion effect)
 Target knowledge sources are sources resulting from the knowledge fusion
or enclosing the knowledge fusion result
 Knowledge source autonomy
 Autonomous
 Non-autonomous
 N/a (for non-existing sources)
 Knowledge source structure
 Changed
 Preserved
 New
 N/a (for non-existing sources)
 Knowledge fusion effect
 Appearing in DSS
 Ontology-based generalization
SPIIRAS
Pattern Language
Name: a name to refer to the pattern;
Problem: a problem the knowledge fusion process solves;
Solution: a meaningful description of the knowledge fusion process;
Initial knowledge source(s): knowledge sources integration or fusion of
knowledge from which produces the knowledge fusion result
Target knowledge source(s): knowledge sources that are organized as a
result of knowledge fusion or that enclose such a result;
Related pattern (may be omitted): an alternative pattern that can be used
instead of the described one or in parallel or after termination of the described;
Exception (may be omitted): a description of conditions / cases when the
pattern is not applicable;
Autonomy pre-states: a degree of autonomy of knowledge sources before
the knowledge fusion process.
Effect in DSS: effect of knowledge fusion as it appears in DSS
Result in ontology paradigm: ontology-based generalization of the effect
produced
Post-states: degrees of knowledge sources’ autonomies and internal
structures preservation after the knowledge fusion process completes
Schematic representation: the knowledge fusion process represented
schematically
Phase of DSS functioning: a stage of DSS functioning where the knowledge
fusion process takes place
SPIIRAS
Emergency Response
Abstract context
Application
ontology
Abstract context Problem solving
knowledge
SPIIRAS
Knowledge Fusion
Abstract context building
Application ontology Abstract context
A – application ontology
C – abstract context
an, cn – internal units in knowledge source
representations
- relationships in conceptual structures
- correspondences between conceptual
structures’ elements
- new knowledge
a1
a5
a3
a4
a2A
c1
c3
c4
c2 C
Knowledge fusion effect
 New knowledge source
SPIIRAS
Simple Fusion
Name: simple fusion
Problem: creation of an abstract ontology-based model of situation
Solution: integration of multiple knowledge pieces from an
ontology that represents knowledge to describe situations
Initial knowledge source: application ontology
Target knowledge source: abstract context
Autonomy pre-states: initial KS target KS
autonomous n/a
Effect in DSS: a new knowledge source of a type coinciding with
the type of the initial knowledge source
Effect in ontology paradigm: new ontology
Post-states: initial KS target KS
Structure: preserved new
Autonomy: autonomous autonomous
Phase of DSS functioning: abstract context building
KS - knowledge source
SPIIRAS
Knowledge Fusion
Abstract context refinement
Resource
Acting
Mobile
Transportation
device
is-a
ass.
Emergency
response
Route
computation
part-of
Mob_Location TDev_Location Mob_Location
Route computation = F3(TDev_Location)
F1(Mob_Loaction)= F2(TDev_Location)
Inferred relationship:
Route computation = F4(Mob_Loaction)
SPIIRAS
Knowledge Fusion
23
 New relationship
Knowledge fusion effect
Abstract context refinement
c1
c3
c4
c2
Abstract context
c1
c3
c4
c2
Abstract context
SPIIRAS
Extension
Name: extension
Problem: introducing new knowledge into a knowledge source
Solution: inference, reconfiguration of knowledge source network
Initial knowledge source: abstract context
Target knowledge source: abstract context
Autonomy pre-states: initial KS target KS
autonomous autonomous
Effect in DSS: extension of the knowledge source with new
knowledge
Effect in ontology paradigm: new ontology representation item
Post-states: initial KS target KS
Structure: preserved changed
Autonomy: autonomous autonomous
Phase of DSS functioning: abstract context refinement and reuse
SPIIRAS
Knowledge Fusion
MedicalCare
Suggestions
Conversion
Organization
Hospital
RequiredService (I)
ListOfServices (O)
Sug_Address (O)
Address (I)
Map_Location (O)
Contextual
knowledge
sources
A B
Knowledge source
network
A B
Address
Domain knowledge
Routing
GetLocation
Sensor_ID (I)
Map_Point (O)
Alternative
Problem solving knowledge
Abstract context reuse
SPIIRAS
Knowledge fusion
 New (alternative) problem-
solving method
Abstract context reuse
c1
c3
c4
c2
Abstract context
c1
c3
c4
c2
Abstract context
KS1
KS2
KS1
KS3
KS4
c5 c6
KS – knowledge source
reference to instantiated concept
execution sequence of knowledge
sources
Knowledge fusion effect
SPIIRAS
Configured Fusion
Name: configured fusion
Problem: knowledge sources are not intended to be used in the current
situation
Solution: configuration of available knowledge sources for the current
purposes
Initial knowledge source: abstract context
Target knowledge source: abstract context
Related pattern: extension
Exception: when alternative sources are not introduced in the
abstract context the pattern is inapplicable
Autonomy pre-states: initial KS target KS
autonomous autonomous
Effect in DSS: new (alternative) knowledge source
Effect in ontology paradigm : new ontology representation items
Post-states: : initial KS target KS
Structure changed changed
Autonomy autonomous autonomous
Phase of DSS functioning: abstract context reuse
SPIIRAS
Emergency Response
Emergency
location
Operational context
SPIIRAS
Knowledge Fusion
Abstract context
Operational context
c1
c3
c4
c2
Abstract context
c1
c3
c4
c2
c1
1
c3
1
c4
1c3
2
Knowledge fusion effect
Operational context producing
• New (dynamic) knowledge
type
• New knowledge source
• New knowledge created
from data / information
cmn – instance n
of concept mKS1
KS2
KS3
relation between knowledge source
and concept being instantiated
Operational context
SPIIRAS
Instantiated Fusion
Name: instantiated fusion
Problem: instantiation of a non-instantiated knowledge source
Solution: semantic fusion of values from multiple knowledge
sources within the structure of the non-instantiated knowledge
source
Initial knowledge source: abstract context
Target knowledge source: operational context
Autonomy pre-states: initial KS target KS
autonomous n/a
Effect in DSS: a new knowledge source of a new type
Effect in ontology paradigm: a new dynamic ontology
Post-states: initial KS target KS
Structure: preserved new
Autonomy: autonomous non-autonomous
Phase of DSS functioning: operational context producing
SPIIRAS
Emergency Response
Problem solving
Problem: to plan joint emergency response actions
SPIIRAS
Knowledge Fusion
Problem solving
c1
c3
c4
c2
Operational context
c11
c31
c41
c32
KS1
KS2
KS3
c1
c3
c4
c2
New knowledge
c11
c31
c41
c32
d1 d2
KS1
KS2
KS3
d – solution
Knowledge fusion effect
• A problem solution
SPIIRAS
Flat Fusion
Name: flat fusion
Problem: providing the decision maker with a set of alternative
decisions
Solution: solving the problems, to which the decision maker has to
find solutions in the current situation, as a constraint satisfaction
problem
Initial knowledge source: operational context
Target knowledge source: knowledge source fusing operational
context and the set of alternatives
Autonomy pre-states: initial KS target KS
non-autonomous n/a
Effect in DSS: a new knowledge source of a new type
Effect in ontology paradigm: a new knowledge product
representing the dynamic ontology fused with the set of alternative
decisions
Post-states: initial KS target KS
Structure: changed new
Autonomy: non-autonomous non-autonomous
Phase of DSS functioning: problem solving
SPIIRAS
Selection of an efficient
plan
Emergency responder1
Emergency responder2
Emergency respondern
An efficient plan
Producing of a set of
feasible plans
or
A set of feasible plans
Is any plan
adjustment
possible?
Yes
No
and
Approval Refusal
Confirmed
plan for actions
Knowledge Fusion
Emergency response
community
Decision implementation
SPIIRAS
Knowledge Fusion
Decision implementation
c1
c3
c4
c2
Decision
c11
c31
c41
c32
d1
p2
p3
p1
Profile
missing knowledge
Knowledge fusion effect
• New capabilities / competencies of knowledge object
SPIIRAS
Adaptation
Name: adaptation
Problem: adaptation of decision implementation to the current
circumstances
Solution: actions redistribution
Initial knowledge sources: knowledge source representing the
decision, actors’ profiles
Target knowledge sources: knowledge source representing the
decision, actors’ profiles
Autonomy pre-states: initial KS target KS
non-autonomous non-autonomous
Effect in DSS: new capabilities / capacities of actors responsible
for decision implementation
Effect in ontology paradigm: a new property
Post-states: initial KS target KS
Structure: changed changed
Autonomy: non-autonomous non-autonomous
Phase of DSS functioning: decision implementation
SPIIRAS
Context archive
Knowledge Fusion
Archival knowledge management
Operational
context
Abstract
context
Knowledge
source network
Decision
Operational
context
Knowledge
source network
Knowledge
source network
Operational
context
DecisionDecision
1
1
1
1 1DecisionDecisionSet of solutions1
SPIIRAS
Emergency Response
Archival knowledge management
5
SPIIRAS
Knowledge Fusion
Archival knowledge management
a1
a5
a3
a4
a2
A
c1
Operational
context1
c11
a2a3
Operational context2
c1
c3
c31
c32
a2
a3
Operational
context3
c4
c2
c41
a2
a3
Knowledge fusion effect
• New relation between originally unrelated knowledge
SPIIRAS
Historical Fusion
Name: historical fusion
Problem: discovery of new knowledge about entities
Solution: an analysis of the archived knowledge
Initial knowledge sources: operational contexts
Target knowledge source: application ontology
Autonomy pre-states: initial KS target KS
non-autonomous autonomous
Effect in DSS: a new property
Effect in ontology paradigm: a new property
Post-states: initial KS target KS
Structure: preserved changed
Autonomy: non-autonomous autonomous
Phase of DSS functioning: archival knowledge management
SPIIRAS
Knowledge Fusion Processes
and their Effects(1)
Synergetic effect Knowledge
fusion process
Process in DSS DSS phase
New knowledge
type
Integration of
knowledge from
various knowledge
sources resulting in
a new type of
knowledge
Coping knowledge
fragments from
various ontologies into
the application
ontology
Application ontology
creation
Instantiation of the
abstract context with
dynamic information
from multiple sources
Operational context
producing
New knowledge
source
Integration of
knowledge from
multiple sources into
a new knowledge
source
Capturing knowledge
fragments from the
existing ontology and
their integration in a
new knowledge
source
Abstract context
building
SPIIRAS
Knowledge Fusion Processes
and their Effects(2)
Synergetic
effect
Knowledge fusion
process
Process in DSS DSS phase
New relations
between
knowledge
Combining knowledge from
different knowledge
sources, which results in
discovery of new relations
between the knowledge
from these sources and
(or) between instances this
knowledge represents
Deductive inference Abstract context
refinement
Inductive inference Archival
knowledge
management
New problem-
solving method or
idea hoe to solve
the problem
Integration of knowledge
from various knowledge
sources resulting in new
problem-solving method
Re-configuration of
knowledge source
network
Abstract context
reuse
SPIIRAS
Knowledge Fusion Processes
and their Effects (3)
Synergetic
effect
Knowledge fusion
process
Process in
DSS
DSS phase
New knowledge
created from data /
information
Intelligent fusion of
heterogeneous data /
information from a wide
range of sources into a form
which may be used by
systems and humans as the
foundation for problem
solving and decision making
Abstract
context
instantiation
Operational context
producing
A problem solution Involving knowledge from
various sources in problem
solving, which results in a
solution as a new
knowledge.
Problem
solving
Generation of a set
of alternative
solutions
New capabilities /
competencies of
knowledge object
Re-configuration of
knowledge source network
Adaptation of
the decision to
the current
circumstances
Decision
implementation
SPIIRAS
Knowledge Fusion Patterns
Synergetic effect Effect in DSS Effect in ontology
paradigm
Pattern
New knowledge
source
Ontology-based non-
instantiated representation of
the emergency situation
New ontology of an
existing type
Simple fusion
New relation
between knowledge
Refined ontology New ontology
representation items
Extension.
Historical
fusion
New problem solving
method
New (alternative) knowledge
source
New ontology
representation items
Configured
fusion
New knowledge type.
New knowledge
created from data /
information
Dynamic instantiated
representation of the
emergency situation
New ontology of new
type
Instantiation
Problem solution A set of alternative response
plans fused with the
instantiated representation of
the emergency situation
New knowledge source
representing the fusion
of ontological and not-
ontological knowledge
Flat fusion
New capabilities /
competencies
Adapted emergency response
plan
New ontology
representation items
Adaptation
SPIIRAS
Conclusion
 Synergetic effects the knowledge fusion processes produce have
been analyzed and systematized
 The synergetic effects have been discovered in the context aware
decision support system intended to support decisions on
planning emergency response actions
 Knowledge fusion patterns of context-based knowledge fusion
have been discovered and described
 A pattern language has been proposed. The language
generalizes the knowledge fusion processes in terms of
autonomies and structures of knowledge sources involved in
knowledge fusion and in terms of knowledge fusion effects
SPIIRAS
Thank you!
Contact information:
Prof. Alexander Smirnov
E-mail:
smir@iias.spb.su
Phone:
+7 812 328 8071
+7 812 328 2073
Fax:
+7 812 328 0685

More Related Content

Viewers also liked

Viewers also liked (8)

ASC Model: A Process Model for the Evaluation of Simulated Field Exercises in...
ASC Model: A Process Model for the Evaluation of Simulated Field Exercises in...ASC Model: A Process Model for the Evaluation of Simulated Field Exercises in...
ASC Model: A Process Model for the Evaluation of Simulated Field Exercises in...
 
Information Infrastructure for Crisis Response Coordination: A Study of local...
Information Infrastructure for Crisis Response Coordination: A Study of local...Information Infrastructure for Crisis Response Coordination: A Study of local...
Information Infrastructure for Crisis Response Coordination: A Study of local...
 
Ontologies for Emergency & Disaster Management
Ontologies for Emergency & Disaster Management Ontologies for Emergency & Disaster Management
Ontologies for Emergency & Disaster Management
 
Towards a Model-Based Analysis of Place-Related Information in Disaster Respo...
Towards a Model-Based Analysis of Place-Related Information in Disaster Respo...Towards a Model-Based Analysis of Place-Related Information in Disaster Respo...
Towards a Model-Based Analysis of Place-Related Information in Disaster Respo...
 
Validating Procedural Knowledge in the Open Virtual Collaboration Environment
Validating Procedural Knowledge in the Open Virtual Collaboration EnvironmentValidating Procedural Knowledge in the Open Virtual Collaboration Environment
Validating Procedural Knowledge in the Open Virtual Collaboration Environment
 
Comparing Performance and Situation Awareness in USAR Unit Tasks in a virtual...
Comparing Performance and Situation Awareness in USAR Unit Tasks in a virtual...Comparing Performance and Situation Awareness in USAR Unit Tasks in a virtual...
Comparing Performance and Situation Awareness in USAR Unit Tasks in a virtual...
 
Ontologies for Crisis Management: A Review of State of the Art in Ontology De...
Ontologies for Crisis Management: A Review of State of the Art in Ontology De...Ontologies for Crisis Management: A Review of State of the Art in Ontology De...
Ontologies for Crisis Management: A Review of State of the Art in Ontology De...
 
Understanding Crises: Investigating Organizational Safety Culture by Combinin...
Understanding Crises: Investigating Organizational Safety Culture by Combinin...Understanding Crises: Investigating Organizational Safety Culture by Combinin...
Understanding Crises: Investigating Organizational Safety Culture by Combinin...
 

Similar to Context-Based Knowledge Fusion Patterns in Decision Support System for Emergency Response

Reproducibility in human cognitive neuroimaging: a community-­driven data sha...
Reproducibility in human cognitive neuroimaging: a community-­driven data sha...Reproducibility in human cognitive neuroimaging: a community-­driven data sha...
Reproducibility in human cognitive neuroimaging: a community-­driven data sha...
Nolan Nichols
 
Theory And Methodology In Networked Learning
Theory And Methodology In Networked LearningTheory And Methodology In Networked Learning
Theory And Methodology In Networked Learning
grainne
 

Similar to Context-Based Knowledge Fusion Patterns in Decision Support System for Emergency Response (20)

Grounded theory
Grounded theoryGrounded theory
Grounded theory
 
Theory-based Learning Analytics
Theory-based Learning AnalyticsTheory-based Learning Analytics
Theory-based Learning Analytics
 
Writing an effective research proposal
Writing an effective research proposalWriting an effective research proposal
Writing an effective research proposal
 
Lecture 1 research methods
Lecture 1 research methodsLecture 1 research methods
Lecture 1 research methods
 
2015 03 19 (EDUCON2015) eMadrid UPM Towards a Learning Analytics Approach for...
2015 03 19 (EDUCON2015) eMadrid UPM Towards a Learning Analytics Approach for...2015 03 19 (EDUCON2015) eMadrid UPM Towards a Learning Analytics Approach for...
2015 03 19 (EDUCON2015) eMadrid UPM Towards a Learning Analytics Approach for...
 
Linking Heterogeneous Scholarly Data Sources in an Interoperable Setting: the...
Linking Heterogeneous Scholarly Data Sources in an Interoperable Setting: the...Linking Heterogeneous Scholarly Data Sources in an Interoperable Setting: the...
Linking Heterogeneous Scholarly Data Sources in an Interoperable Setting: the...
 
Knowledge Representation on the Web
Knowledge Representation on the WebKnowledge Representation on the Web
Knowledge Representation on the Web
 
Knowledge Management in the AI Driven Scintific System
Knowledge Management in the AI Driven Scintific SystemKnowledge Management in the AI Driven Scintific System
Knowledge Management in the AI Driven Scintific System
 
Reproducibility in human cognitive neuroimaging: a community-­driven data sha...
Reproducibility in human cognitive neuroimaging: a community-­driven data sha...Reproducibility in human cognitive neuroimaging: a community-­driven data sha...
Reproducibility in human cognitive neuroimaging: a community-­driven data sha...
 
Theory And Methodology In Networked Learning
Theory And Methodology In Networked LearningTheory And Methodology In Networked Learning
Theory And Methodology In Networked Learning
 
Introduction To Research
Introduction To ResearchIntroduction To Research
Introduction To Research
 
Introduction To Research Er
Introduction To Research ErIntroduction To Research Er
Introduction To Research Er
 
MELJUN CORTES research seminar_1__theoretical_framework_2nd_updated
MELJUN CORTES research seminar_1__theoretical_framework_2nd_updatedMELJUN CORTES research seminar_1__theoretical_framework_2nd_updated
MELJUN CORTES research seminar_1__theoretical_framework_2nd_updated
 
Holmes "Institutional Infrastructure for Data Sharing"
Holmes "Institutional Infrastructure for Data Sharing"Holmes "Institutional Infrastructure for Data Sharing"
Holmes "Institutional Infrastructure for Data Sharing"
 
Business research methods 1
Business research methods 1Business research methods 1
Business research methods 1
 
Jonathan Breeze, Symplectic
Jonathan Breeze, SymplecticJonathan Breeze, Symplectic
Jonathan Breeze, Symplectic
 
BLC & Digital Science: Jonathan Breeze, Symplectic
BLC & Digital Science: Jonathan Breeze, SymplecticBLC & Digital Science: Jonathan Breeze, Symplectic
BLC & Digital Science: Jonathan Breeze, Symplectic
 
Learning as a Complex Phenomenon: Challenges for Learning Analytics
Learning as a Complex Phenomenon: Challenges for Learning Analytics Learning as a Complex Phenomenon: Challenges for Learning Analytics
Learning as a Complex Phenomenon: Challenges for Learning Analytics
 
MELJUN CORTES research seminar_1_theoretical_framework
MELJUN CORTES research seminar_1_theoretical_frameworkMELJUN CORTES research seminar_1_theoretical_framework
MELJUN CORTES research seminar_1_theoretical_framework
 
Martone acs presentation
Martone acs presentationMartone acs presentation
Martone acs presentation
 

More from streamspotter

More from streamspotter (19)

Exploring Shared Situational Awareness using Serious Gaming in Supply Chain D...
Exploring Shared Situational Awareness using Serious Gaming in Supply Chain D...Exploring Shared Situational Awareness using Serious Gaming in Supply Chain D...
Exploring Shared Situational Awareness using Serious Gaming in Supply Chain D...
 
LVC Training Environment for Strategic and Tactical Emergency Operations
LVC Training Environment for Strategic and Tactical Emergency OperationsLVC Training Environment for Strategic and Tactical Emergency Operations
LVC Training Environment for Strategic and Tactical Emergency Operations
 
Ethical Challenges of Participatory Sensing for Crisis Information Management
Ethical Challenges of Participatory Sensing for Crisis Information Management Ethical Challenges of Participatory Sensing for Crisis Information Management
Ethical Challenges of Participatory Sensing for Crisis Information Management
 
The Impact of IT on the Management of Mass Casualty Incidents in Germany
The Impact of IT on the Management of Mass Casualty Incidents in GermanyThe Impact of IT on the Management of Mass Casualty Incidents in Germany
The Impact of IT on the Management of Mass Casualty Incidents in Germany
 
Towards a Knowledge-Intensive Serious Game for Training Emergency Medical Ser...
Towards a Knowledge-Intensive Serious Game for Training Emergency Medical Ser...Towards a Knowledge-Intensive Serious Game for Training Emergency Medical Ser...
Towards a Knowledge-Intensive Serious Game for Training Emergency Medical Ser...
 
Communication Interface for Virtual Training of Crisis Management
Communication Interface for Virtual Training of Crisis ManagementCommunication Interface for Virtual Training of Crisis Management
Communication Interface for Virtual Training of Crisis Management
 
Optimization Modeling and Decision Support for Wireless Infrastructure Deploy...
Optimization Modeling and Decision Support for Wireless Infrastructure Deploy...Optimization Modeling and Decision Support for Wireless Infrastructure Deploy...
Optimization Modeling and Decision Support for Wireless Infrastructure Deploy...
 
A System Dynamics Model of the 2005 Hatlestad Slide Emergency Management
A System Dynamics Model of the 2005 Hatlestad Slide Emergency Management A System Dynamics Model of the 2005 Hatlestad Slide Emergency Management
A System Dynamics Model of the 2005 Hatlestad Slide Emergency Management
 
Inter-organizational Collaboration Structures during Emergency Response: A Ca...
Inter-organizational Collaboration Structures during Emergency Response: A Ca...Inter-organizational Collaboration Structures during Emergency Response: A Ca...
Inter-organizational Collaboration Structures during Emergency Response: A Ca...
 
Unexpected Effects of Rescue Robots’ Team-Membership in a virtual Environment
Unexpected Effects of Rescue Robots’ Team-Membership in a virtual EnvironmentUnexpected Effects of Rescue Robots’ Team-Membership in a virtual Environment
Unexpected Effects of Rescue Robots’ Team-Membership in a virtual Environment
 
A Typology to facilitate Multi-Agency Coordination
A Typology to facilitate Multi-Agency CoordinationA Typology to facilitate Multi-Agency Coordination
A Typology to facilitate Multi-Agency Coordination
 
Exercises for Crisis Management Training in intra-organizational Settings
Exercises for Crisis Management Training in intra-organizational SettingsExercises for Crisis Management Training in intra-organizational Settings
Exercises for Crisis Management Training in intra-organizational Settings
 
A Novel Architecture for Disaster Response Workflow Management Systems
A Novel Architecture for Disaster Response Workflow Management SystemsA Novel Architecture for Disaster Response Workflow Management Systems
A Novel Architecture for Disaster Response Workflow Management Systems
 
A flexible network of sensors: case study
A flexible network of sensors: case studyA flexible network of sensors: case study
A flexible network of sensors: case study
 
Framework Design for Operational Scenario-based Emergency Response System
Framework Design for Operational Scenario-based Emergency Response SystemFramework Design for Operational Scenario-based Emergency Response System
Framework Design for Operational Scenario-based Emergency Response System
 
The Seven Main Challenges of an Early Warning System Architecture
The Seven Main Challenges of an Early Warning System ArchitectureThe Seven Main Challenges of an Early Warning System Architecture
The Seven Main Challenges of an Early Warning System Architecture
 
Training, Testing and Experimentation: A classification of command post exer...
 Training, Testing and Experimentation: A classification of command post exer... Training, Testing and Experimentation: A classification of command post exer...
Training, Testing and Experimentation: A classification of command post exer...
 
Location Information Interoperability of CAP and PIDF-LO for Early Warning Sy...
Location Information Interoperability of CAP and PIDF-LO for Early Warning Sy...Location Information Interoperability of CAP and PIDF-LO for Early Warning Sy...
Location Information Interoperability of CAP and PIDF-LO for Early Warning Sy...
 
Harmonization of Data Formats for Tsunami Simulation Products
Harmonization of Data Formats for Tsunami Simulation ProductsHarmonization of Data Formats for Tsunami Simulation Products
Harmonization of Data Formats for Tsunami Simulation Products
 

Recently uploaded

CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
giselly40
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
Enterprise Knowledge
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
vu2urc
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
Earley Information Science
 

Recently uploaded (20)

Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
Evaluating the top large language models.pdf
Evaluating the top large language models.pdfEvaluating the top large language models.pdf
Evaluating the top large language models.pdf
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 

Context-Based Knowledge Fusion Patterns in Decision Support System for Emergency Response

  • 1. SPIIRAS Context-Based Knowledge Fusion Patterns in Decision Support System for Emergency Response Alexander Smirnov, Tatiana Levashova, Nikolay Shilov Computer Aided Integrated Systems laboratory (CAIS Lab) St.Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS) St.Petersburg, Russia ISCRAM 2013
  • 2. SPIIRAS Presentation Outline  Introduction  Knowledge Fusion Patterns  Conclusion 2 “Every person has a pattern language in his mind” * * Alexander C., The Timeless Way of Building. Oxford University Press, New York, 1979
  • 3. SPIIRAS St.Petersburg Institute for Informatics and Automation (SPIIRAS) Russian Academy of Sciences (RAS)  Founded in 1724  The research umbrella organization of the Russian Government  363 units (Research Institutes and Centers)  112,000 personnel: 55,100 Researchers (10,000 D.Sc., and 26,000 Ph.D.) St.Petersburg Institute for Informatics and Automation (SPIIRAS)  Founded in 1978  Only 1 Russian Academy of Science Institute operating in Northwest Russia in Computer Science discipline  161 Researchers (38 D.Sc., and 59 Ph.D., 34 Ph.D. students, 1 PostDoc)  Grants Ph.D and Dr.Sc. (Technical) degrees
  • 5. SPIIRAS CAIS Laboratory: Financial Support (2007-2013) Russian Academy of Sciences  6 projects  1 grant  3 projects  FP6 IST – 1 project (IP)  ENPI-Finland - 1 project  2 grants 5 projects  1 grant  1 grant The Swedish Foundation for International Cooperation in Research and Higher Education  2 grants  10 projects  26 grants Ministry of Education & Science, Russia Russian Basic Research Foundation Russian Humanitarian Scientific Foundation
  • 6. SPIIRAS Introduction: Using Cyberspace to link Physical World Information to Communities Semantic Integration Knowledge Physical World Cyber-Physical-Social Systems (CPSs) Communities / Social Networks CPS is a tight integration of physical systems and cyber (ICT) systems interacting in real time to decision support. CPSs rely on communication, computation & control Infrastructures, and Social networks
  • 7. SPIIRAS Introduction: Conceptual Framework of Information Support  Correct information and knowledge processed and delivered to the location and time of need and ability to predict at the level of understanding are needed Understanding Knowledge Information Data Information Transformation Process Source: Anken C.: Information Understanding, 5th Anniversary Information Workshop. Rome, NY, 2002
  • 8. SPIIRAS Introduction: Problem Area • Environments where decision support systems operate – Large volumes of data, information, and knowledge available in different sources • Knowledge fusion – Integration of information and knowledge from multiple sources into a common piece of knowledge that may be used for decision making and problem solving or may provide a better insight and understanding of the situation under consideration. The expectation is that the result of knowledge fusion is a new knowledge that is more complete, less uncertain, and less conflicting than the original inputs • Fusion is context-sensitive – A common challenge for fusion systems is adaptation to the context of usage • Environment heterogeneity – Overcoming the heterogeneity of the environment sources is a precondition for knowledge fusion
  • 9. SPIIRAS Introduction: Research Objectives • Analysis and investigation of context-based knowledge fusion processes in Decision Support System (DSS) • Discovery of context-based knowledge fusion patterns with regard to – Preservation/change of internal structures of sources involved in knowledge fusion – Preservation/loss of autonomies of sources involved in knowledge fusion – Knowledge fusion effect(s)
  • 10. SPIIRAS Introduction: Main Definitions • Context - any information about the situation in which decisions are made • Context aware DSS - a system that uses context to provide the decision maker with a set of decisions that can be made in the current situation • Knowledge source - a source of data, information, or knowledge which can be explicitly specified • Knowledge source structure – a conceptual structure used in the representation of the knowledge source • Autonomous knowledge source – a knowledge source having no relations to other sources; the changes in the autonomous source do not produce any changes in other sources • Non-autonomous knowledge source – a knowledge source relating to other sources; any changes in a non-autonomous knowledge source are passed to the related sources and reflected in them • Knowledge fusion - knowledge processing resulting in a synergetic effect, i.e. an appearance of new knowledge • Knowledge fusion result / effect – any new knowledge (new knowledge source, new concept, new property, etc.)
  • 11. SPIIRAS Introduction: Background • Technology of knowledge logistics – Configuration of knowledge network from heterogeneous sources to support decisions on involvement of autonomous resources in joint activities and on scheduling these activities • Methodology of context management – Two-level situation representation • Abstract context: ontology-based non-instantiated representation of a situation of the given type • Operational context: a set of abstract context instances under the actual settings • Conceptual framework of context-aware decision support • Generic knowledge fusion patterns – Absorption – Extension – Selective fusion – Simple fusion – Flat fusion
  • 12. SPIIRAS Introduction: Knowledge Fusion Processes  Intelligent fusion of massive amounts of heterogeneous data / information from a wide range of distributed sources into a form which may be used by systems and humans as the foundation for problem solving and decision making.  Integration of knowledge from various knowledge sources resulting in a completely different type of knowledge or new idea how to solve the problem.  Combining knowledge from different autonomous knowledge sources in different ways in different scenarios, which results in discovery of new relations between the knowledge from different sources or/and between the entities this knowledge.  Re-configuration of knowledge sources to achieve a new configuration with new capabilities or competencies.  Knowledge exchange to improve capabilities or competencies through learning, interactions, discussions, and practices.  Involving knowledge from various sources in problem solving, which results in a solution as a new knowledge.
  • 13. SPIIRAS Introduction: Synergetic Effects 1. New knowledge object created from data/information; 2. New knowledge type or knowledge product (service, process, technology, etc.); 3. New knowledge source; 4. New knowledge about the conceptual scheme (new relations, concepts, properties, etc.); 5. New explicit knowledge; 6. New capabilities / competencies of a knowledge object (an object that produces or contains knowledge); 7. New problem solving method; 8. Solution for a problem
  • 14. SPIIRAS Introduction: Context-Aware Decision Support System 2013 Теория и практика системной динамики, Апатиты 14 Purpose Support of decisions on planning emergency response actions Application ontology Abstract context Operational context A B C F D E G J I A F D E G I A F D E G I Knowledge sources Contextual knowledge sources Knowledge source network A set of alternatives Conceptual framework
  • 15. SPIIRAS Introduction: Context-aware stages of DSS  Abstract context building  Abstract context refinement  Abstract context reuse  Knowledge source network configuration  Operational context producing  Problem solving  Decision making  Decision implementation  Archival knowledge management
  • 17. SPIIRAS Concepts of Generalization  Knowledge sources  Initial knowledge sources are sources that are integrated leading to emergence of a new knowledge (producing some knowledge fusion effect)  Target knowledge sources are sources resulting from the knowledge fusion or enclosing the knowledge fusion result  Knowledge source autonomy  Autonomous  Non-autonomous  N/a (for non-existing sources)  Knowledge source structure  Changed  Preserved  New  N/a (for non-existing sources)  Knowledge fusion effect  Appearing in DSS  Ontology-based generalization
  • 18. SPIIRAS Pattern Language Name: a name to refer to the pattern; Problem: a problem the knowledge fusion process solves; Solution: a meaningful description of the knowledge fusion process; Initial knowledge source(s): knowledge sources integration or fusion of knowledge from which produces the knowledge fusion result Target knowledge source(s): knowledge sources that are organized as a result of knowledge fusion or that enclose such a result; Related pattern (may be omitted): an alternative pattern that can be used instead of the described one or in parallel or after termination of the described; Exception (may be omitted): a description of conditions / cases when the pattern is not applicable; Autonomy pre-states: a degree of autonomy of knowledge sources before the knowledge fusion process. Effect in DSS: effect of knowledge fusion as it appears in DSS Result in ontology paradigm: ontology-based generalization of the effect produced Post-states: degrees of knowledge sources’ autonomies and internal structures preservation after the knowledge fusion process completes Schematic representation: the knowledge fusion process represented schematically Phase of DSS functioning: a stage of DSS functioning where the knowledge fusion process takes place
  • 20. SPIIRAS Knowledge Fusion Abstract context building Application ontology Abstract context A – application ontology C – abstract context an, cn – internal units in knowledge source representations - relationships in conceptual structures - correspondences between conceptual structures’ elements - new knowledge a1 a5 a3 a4 a2A c1 c3 c4 c2 C Knowledge fusion effect  New knowledge source
  • 21. SPIIRAS Simple Fusion Name: simple fusion Problem: creation of an abstract ontology-based model of situation Solution: integration of multiple knowledge pieces from an ontology that represents knowledge to describe situations Initial knowledge source: application ontology Target knowledge source: abstract context Autonomy pre-states: initial KS target KS autonomous n/a Effect in DSS: a new knowledge source of a type coinciding with the type of the initial knowledge source Effect in ontology paradigm: new ontology Post-states: initial KS target KS Structure: preserved new Autonomy: autonomous autonomous Phase of DSS functioning: abstract context building KS - knowledge source
  • 22. SPIIRAS Knowledge Fusion Abstract context refinement Resource Acting Mobile Transportation device is-a ass. Emergency response Route computation part-of Mob_Location TDev_Location Mob_Location Route computation = F3(TDev_Location) F1(Mob_Loaction)= F2(TDev_Location) Inferred relationship: Route computation = F4(Mob_Loaction)
  • 23. SPIIRAS Knowledge Fusion 23  New relationship Knowledge fusion effect Abstract context refinement c1 c3 c4 c2 Abstract context c1 c3 c4 c2 Abstract context
  • 24. SPIIRAS Extension Name: extension Problem: introducing new knowledge into a knowledge source Solution: inference, reconfiguration of knowledge source network Initial knowledge source: abstract context Target knowledge source: abstract context Autonomy pre-states: initial KS target KS autonomous autonomous Effect in DSS: extension of the knowledge source with new knowledge Effect in ontology paradigm: new ontology representation item Post-states: initial KS target KS Structure: preserved changed Autonomy: autonomous autonomous Phase of DSS functioning: abstract context refinement and reuse
  • 25. SPIIRAS Knowledge Fusion MedicalCare Suggestions Conversion Organization Hospital RequiredService (I) ListOfServices (O) Sug_Address (O) Address (I) Map_Location (O) Contextual knowledge sources A B Knowledge source network A B Address Domain knowledge Routing GetLocation Sensor_ID (I) Map_Point (O) Alternative Problem solving knowledge Abstract context reuse
  • 26. SPIIRAS Knowledge fusion  New (alternative) problem- solving method Abstract context reuse c1 c3 c4 c2 Abstract context c1 c3 c4 c2 Abstract context KS1 KS2 KS1 KS3 KS4 c5 c6 KS – knowledge source reference to instantiated concept execution sequence of knowledge sources Knowledge fusion effect
  • 27. SPIIRAS Configured Fusion Name: configured fusion Problem: knowledge sources are not intended to be used in the current situation Solution: configuration of available knowledge sources for the current purposes Initial knowledge source: abstract context Target knowledge source: abstract context Related pattern: extension Exception: when alternative sources are not introduced in the abstract context the pattern is inapplicable Autonomy pre-states: initial KS target KS autonomous autonomous Effect in DSS: new (alternative) knowledge source Effect in ontology paradigm : new ontology representation items Post-states: : initial KS target KS Structure changed changed Autonomy autonomous autonomous Phase of DSS functioning: abstract context reuse
  • 29. SPIIRAS Knowledge Fusion Abstract context Operational context c1 c3 c4 c2 Abstract context c1 c3 c4 c2 c1 1 c3 1 c4 1c3 2 Knowledge fusion effect Operational context producing • New (dynamic) knowledge type • New knowledge source • New knowledge created from data / information cmn – instance n of concept mKS1 KS2 KS3 relation between knowledge source and concept being instantiated Operational context
  • 30. SPIIRAS Instantiated Fusion Name: instantiated fusion Problem: instantiation of a non-instantiated knowledge source Solution: semantic fusion of values from multiple knowledge sources within the structure of the non-instantiated knowledge source Initial knowledge source: abstract context Target knowledge source: operational context Autonomy pre-states: initial KS target KS autonomous n/a Effect in DSS: a new knowledge source of a new type Effect in ontology paradigm: a new dynamic ontology Post-states: initial KS target KS Structure: preserved new Autonomy: autonomous non-autonomous Phase of DSS functioning: operational context producing
  • 31. SPIIRAS Emergency Response Problem solving Problem: to plan joint emergency response actions
  • 32. SPIIRAS Knowledge Fusion Problem solving c1 c3 c4 c2 Operational context c11 c31 c41 c32 KS1 KS2 KS3 c1 c3 c4 c2 New knowledge c11 c31 c41 c32 d1 d2 KS1 KS2 KS3 d – solution Knowledge fusion effect • A problem solution
  • 33. SPIIRAS Flat Fusion Name: flat fusion Problem: providing the decision maker with a set of alternative decisions Solution: solving the problems, to which the decision maker has to find solutions in the current situation, as a constraint satisfaction problem Initial knowledge source: operational context Target knowledge source: knowledge source fusing operational context and the set of alternatives Autonomy pre-states: initial KS target KS non-autonomous n/a Effect in DSS: a new knowledge source of a new type Effect in ontology paradigm: a new knowledge product representing the dynamic ontology fused with the set of alternative decisions Post-states: initial KS target KS Structure: changed new Autonomy: non-autonomous non-autonomous Phase of DSS functioning: problem solving
  • 34. SPIIRAS Selection of an efficient plan Emergency responder1 Emergency responder2 Emergency respondern An efficient plan Producing of a set of feasible plans or A set of feasible plans Is any plan adjustment possible? Yes No and Approval Refusal Confirmed plan for actions Knowledge Fusion Emergency response community Decision implementation
  • 35. SPIIRAS Knowledge Fusion Decision implementation c1 c3 c4 c2 Decision c11 c31 c41 c32 d1 p2 p3 p1 Profile missing knowledge Knowledge fusion effect • New capabilities / competencies of knowledge object
  • 36. SPIIRAS Adaptation Name: adaptation Problem: adaptation of decision implementation to the current circumstances Solution: actions redistribution Initial knowledge sources: knowledge source representing the decision, actors’ profiles Target knowledge sources: knowledge source representing the decision, actors’ profiles Autonomy pre-states: initial KS target KS non-autonomous non-autonomous Effect in DSS: new capabilities / capacities of actors responsible for decision implementation Effect in ontology paradigm: a new property Post-states: initial KS target KS Structure: changed changed Autonomy: non-autonomous non-autonomous Phase of DSS functioning: decision implementation
  • 37. SPIIRAS Context archive Knowledge Fusion Archival knowledge management Operational context Abstract context Knowledge source network Decision Operational context Knowledge source network Knowledge source network Operational context DecisionDecision 1 1 1 1 1DecisionDecisionSet of solutions1
  • 39. SPIIRAS Knowledge Fusion Archival knowledge management a1 a5 a3 a4 a2 A c1 Operational context1 c11 a2a3 Operational context2 c1 c3 c31 c32 a2 a3 Operational context3 c4 c2 c41 a2 a3 Knowledge fusion effect • New relation between originally unrelated knowledge
  • 40. SPIIRAS Historical Fusion Name: historical fusion Problem: discovery of new knowledge about entities Solution: an analysis of the archived knowledge Initial knowledge sources: operational contexts Target knowledge source: application ontology Autonomy pre-states: initial KS target KS non-autonomous autonomous Effect in DSS: a new property Effect in ontology paradigm: a new property Post-states: initial KS target KS Structure: preserved changed Autonomy: non-autonomous autonomous Phase of DSS functioning: archival knowledge management
  • 41. SPIIRAS Knowledge Fusion Processes and their Effects(1) Synergetic effect Knowledge fusion process Process in DSS DSS phase New knowledge type Integration of knowledge from various knowledge sources resulting in a new type of knowledge Coping knowledge fragments from various ontologies into the application ontology Application ontology creation Instantiation of the abstract context with dynamic information from multiple sources Operational context producing New knowledge source Integration of knowledge from multiple sources into a new knowledge source Capturing knowledge fragments from the existing ontology and their integration in a new knowledge source Abstract context building
  • 42. SPIIRAS Knowledge Fusion Processes and their Effects(2) Synergetic effect Knowledge fusion process Process in DSS DSS phase New relations between knowledge Combining knowledge from different knowledge sources, which results in discovery of new relations between the knowledge from these sources and (or) between instances this knowledge represents Deductive inference Abstract context refinement Inductive inference Archival knowledge management New problem- solving method or idea hoe to solve the problem Integration of knowledge from various knowledge sources resulting in new problem-solving method Re-configuration of knowledge source network Abstract context reuse
  • 43. SPIIRAS Knowledge Fusion Processes and their Effects (3) Synergetic effect Knowledge fusion process Process in DSS DSS phase New knowledge created from data / information Intelligent fusion of heterogeneous data / information from a wide range of sources into a form which may be used by systems and humans as the foundation for problem solving and decision making Abstract context instantiation Operational context producing A problem solution Involving knowledge from various sources in problem solving, which results in a solution as a new knowledge. Problem solving Generation of a set of alternative solutions New capabilities / competencies of knowledge object Re-configuration of knowledge source network Adaptation of the decision to the current circumstances Decision implementation
  • 44. SPIIRAS Knowledge Fusion Patterns Synergetic effect Effect in DSS Effect in ontology paradigm Pattern New knowledge source Ontology-based non- instantiated representation of the emergency situation New ontology of an existing type Simple fusion New relation between knowledge Refined ontology New ontology representation items Extension. Historical fusion New problem solving method New (alternative) knowledge source New ontology representation items Configured fusion New knowledge type. New knowledge created from data / information Dynamic instantiated representation of the emergency situation New ontology of new type Instantiation Problem solution A set of alternative response plans fused with the instantiated representation of the emergency situation New knowledge source representing the fusion of ontological and not- ontological knowledge Flat fusion New capabilities / competencies Adapted emergency response plan New ontology representation items Adaptation
  • 45. SPIIRAS Conclusion  Synergetic effects the knowledge fusion processes produce have been analyzed and systematized  The synergetic effects have been discovered in the context aware decision support system intended to support decisions on planning emergency response actions  Knowledge fusion patterns of context-based knowledge fusion have been discovered and described  A pattern language has been proposed. The language generalizes the knowledge fusion processes in terms of autonomies and structures of knowledge sources involved in knowledge fusion and in terms of knowledge fusion effects
  • 46. SPIIRAS Thank you! Contact information: Prof. Alexander Smirnov E-mail: smir@iias.spb.su Phone: +7 812 328 8071 +7 812 328 2073 Fax: +7 812 328 0685