ifsa world congress -nafips 2013 edmonton, alberta. natalia díaz
DESCRIPTION
Presentation on 25.6.13TRANSCRIPT
![Page 1: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/1.jpg)
An approach to improve semantics in
Smart Spaces using reactive fuzzy rules
Natalia Díaz Rodríguez & Johan Lilius Turku Centre for Computer Science (TUCS),
Åbo Akademi University, Turku, Finland M.P. Cuéllar & Miguel Delgado Calvo-Flores
University of Granada, Spain
1
IFSA World Congress - NAFIPS 2013, Edmonton, Canada 25.6.13
![Page 2: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/2.jpg)
Introduction
§ Smart Spaces (UbiComp): interoperability, working on behalf of the user, handle unanticipated situations
§ Human behaviour modelling: crucial task in AmI environments
§ Problem: Sensor data as crisp events.
2
![Page 3: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/3.jpg)
Introduction
§ Context-awareness for machine processing and reasoning.
§ Semantic Technologies and Ontologies:
Independent knowledge sharing minimizing redundancy.
3
![Page 4: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/4.jpg)
4
Related Work: fuzzy reasoners
![Page 5: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/5.jpg)
Related Work: architectures
§ Different semantic storage solutions, some fuzzy extensions of SPARQL (e.g. F-SPARQL).
§ What is missing? An integrated single solution supporting: – W3C standards (RDF, OWL, SPARQL). – RDF stores with support for efficient and real-time
pub/sub event notifications. – Uncertain, imprecise expressions.
5
![Page 6: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/6.jpg)
Our proposal: A hybrid framework for context-aware Smart Space application development
2 main components: Crisp KB and Fuzzy KB, connected by a rule engine which handles each type of event subscriptions. a. CRISP element: SPARQL Subscription-based RDF store with
Pub/Sub architecture: Smart-M3 b. FUZZY element: Expressive Fuzzy DL reasoner, allows
mapping to a fuzzy control system: fuzzyDL
6
![Page 7: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/7.jpg)
7
Fuzzy KB and rules in fuzzyDL
![Page 8: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/8.jpg)
Fuzzy KB and rules in fuzzyDL
8
![Page 9: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/9.jpg)
Hybrid architecture proposal with fuzzy and crisp KBs
9
![Page 10: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/10.jpg)
Equivalent queries to be executed in both crisp M3 and fuzzyDL KBs
10
Mapping of rule antecedent “IF Natalia hasStatus AwayForWeekend” to SPARQL and fuzzyDL queries.
![Page 11: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/11.jpg)
Mapping of subscription pattern types to fuzzyDL queries
11
![Page 12: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/12.jpg)
Conclusions
12
§ Hybrid Fuzzy-Crisp architecture whose – Quantitative (SPARQL, event Pub/Sub) and Qualitative
(semantics + fuzzy reasoning expressive power) views allow a versatile framework for developing Smart Space applications.
– strategy allows loosening of semantics or efficiency (depending on application needs): avoiding continuous querying for changes or fuzzy discretization-based solutions.
– Knowledge representation & queries are + flexible § fuzzyDL still does not support some required semantic constraints § 2 KBs = Redundancy (twofold updates) -> advantage for
optimizing execution time of different queries/ datasets
![Page 13: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/13.jpg)
Future Directions
13
§ Rule serializers (for crisp and fuzzy architectures) § Scalability + performance experiments in real-life applications
(reasoning, querying/updating and subscription response VS ontology size & fuzzy/crisp/hybrid rules)
§ Optimization: Semantic generalization of hybrid antecedents 1. When strict semantics are to be preserved (we sacrifice
performance): – IF (WeatherSituationTurku, isCurrently, VeryStormy) –> IF (WeatherSituationTurku, isCurrently, ?).
2. Transforming patterns into crisp-only (sacrifices semantic precision): – IF(Natalia, isVeryNearTo, JohansOffice) –> IF(Natalia, isNearTo,
JohansOffice).
![Page 14: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/14.jpg)
Future Directions
§ Pub/sub fuzzy reasoner (->Fuzzy SPARQL?) § Alternatives to data redundancy keeping
consistency? § Overall: Standardization of fuzzy SPARQL extension for fuzzy reasoning will achieve more usable, flexible, personalized and adaptive Smart Spaces
14
![Page 15: IFSA World Congress -NAFIPS 2013 Edmonton, Alberta. Natalia Díaz](https://reader034.vdocuments.us/reader034/viewer/2022051817/548096cb5906b50e6d8b4567/html5/thumbnails/15.jpg)
Thank you for your attention!
Natalia Díaz Rodríguez [email protected]
Embedded Systems Lab. Department of Information Technologies Åbo Akademi University, Turku, Finland
TUCS (Turku Centre for Computer Science)
Department of Computer Science and Artificial Intelligence University of Granada, Spain
15