Upload
itaca-tsb
View
542
Download
3
Tags:
Embed Size (px)
DESCRIPTION
Cognitive Networks working on large scale are object of an increasing interest by both the scientific and the commercial point of view in the context of several environments and domains. The natural convergence point for these heterogeneous disciplines is the need of a strong advanced technologic support that enables the generation of distributed observations on large scale as well as the intelligent process of obtained information. An approach based on the Semantic Sensor Web could be the key issue for enabling semantic ecosystems among heterogeneous Cognitive Networks.
Citation preview
Enabling Semantic Ecosystems among heterogeneous Cognitive Networksg
Salvatore F. Pileggi, Carlos Fernandez‐Llatas, Vicente Traver
International Workshop on Semantic Sensor Web 2011 (SSW2011)
October 27th , Paris, France
Salvatore F. Pileggi, PhDResearcher, TSB-ITACA
Universidad Politécnica de Valencia (Spain)( p )[email protected]
www.flaviopileggi.net
Index
• Introduction• Cognitive Networks
• Cognitive Networks: from science to reality• Cognitive Networks: from science to reality• Semantic Ecosystems among heterogeneous Cognitive Networks• Current Approaches and Limitations
• The impact of semantic technologies: distributed approach• Semantic Interoperability• Knowledge buildingg g
• Conclusions
I t d ti C iti N t k
k ( ) f d k h k f
Introduction: Cognitive Networks
• Cognitive network (CN) is a new type of data network that makes use ofcutting edge technology from several research areas (i.e. machinelearning, knowledge representation, computer network, networkmanagement) to solve some problems current networks are faced with.
Too Much genericToo Much generic…..
• Cognitive Networks working on large scale are object of an increasinginterest by both the scientific and the commercial point of view in thecontext of several environments and domainscontext of several environments and domains.
C iti N t k l tiCognitive Networks: scale perspective
Scale Technologic Support
Application UsersComplexity/Knowledge
Climatic/environmental phenomena
Research/Science
Global
phenomena
Cognit
Relationships
Citizens
Wide Area( li )
Human behaviorOthers
tive Netw
o
Relationships
(e.g. metropolitan)
orksCollectives
Improve Quality of Life
Smart Space
Improve Quality of Life
Metropolitan/Urban Ecosystems (1)A t lit ( b ) t i d fi d l l
Metropolitan/Urban Ecosystems (1)• A metropolitan (or urban) ecosystem is defined as a large scale
ecosystem composed of the environment, humans and other livingorganisms, and any structure/infrastructure or object physicallylocated in the reference area.
• We are living in an increasingly urbanized world (tendency will be probably followedalso in the next future)also in the next future).
• Further increases in size and rates of growth of cities will no doubt stress alreadyimpacted environments as well as the social aspect of the problem.
• This tendency is hard to be controlled or modified.y• A great number of interdisciplinary initiatives, studies and researches aimed to
understand the current impact of the phenomena as well as to foresee the evolution ofit (scientific or practice focus).
Metropolitan/Urban Ecosystems (2)h d f h h i i i f h i l d li i h
Metropolitan/Urban Ecosystems (2)• The study of the human activities, of the environmental and climatic phenomena
is object of interest in the context of several disciplines and applications.• All these studies are normally independent initiatives, logically separated
researches and, in the majority of the cases, results are hard to be directly related.
This could appear a paradox: interest phenomena happen in the same physical ecosystem, involving the same actors but the definition of the dependencies/relationships among atomic
results are omitted even if they are probably the most relevantresults are omitted even if they are probably the most relevant results.
Semantic Ecosystems among heterogeneous Cognitive y g g gNetworks
C t h d li it ti (1)
h l h l i f bli k l d i i h
Current approaches and limitations (1)
• The normal technologic support for enabling knowledge environment is thecognitive network that assumes a physical infrastructure (sensors) able to detectinterest information or phenomena and a logic infrastructure able to process the
d t (k l d b ildi ) t ll f i tisensor data (knowledge building) eventually performing actions, responses orcomplex analysis.
• The parameters that can potentially affect the “quality” of the applications orstudies are mainly the sensor technology (constantly increasing in terms ofreliability, precision and capabilities), the coverage area, the amount of data and,f ll h b lfinally, the process capabilities.
C t h d li it ti (2)Current approaches and limitations (2)
• Current solutions are hard to be proposed on large scale due to the currentlimitations of the massive sensors deployment on large scale.
• Furthermore, the following limitations can be clearly identified:
o Lack of social view at the informationo Static coverage models
b lo Obsolete view at resourceso Not always effective business models
I t f S ti T h l iImpact of Semantic Technologies
Centralized Model Interoperability Model
Semantic Technologies
Distributed ModelKnowledge
building/representationModel
I t bilit M d lInteroperability Model
K l d R t ti /B ildi M d lKnowledge Representation/Building Model
Local Knowledge
Ontology i
High‐level Concepts
Ontology i
Domain specific Layersp
Core
Domain‐specific Layers
Layer Data
Low‐level Concepts
Data Source
C l i
h f ll i d l i h d f di ib d i
Conclusions
• The power of collecting and relating heterogeneous data from distributed source isthe real engine of high‐scale cognitive networks.
• The economic sustainability, as well as the social focus on the great part of theapplications, determines the need of an innovative view at networks andarchitectures on the model of most modern virtual organizations.
• These solutions require a high level of interoperability, at both functional andsemantic level.
• The current “Semantic Sensor Web” approach assures a rich and dynamictechnologic environment in which heterogeneous data from distributed source cantechnologic environment in which heterogeneous data from distributed source canbe related, merged and analyzed as part of a unique knowledge ecosystem.
Thank You!
Salvatore F. Pileggi, PhDResearcher, TSB-ITACA
Universidad Politécnica de Valencia (Spain)( p )[email protected]
www.flaviopileggi.net