DocumentCode :
2952294
Title :
Computing perception from sensor data
Author :
Barnaghi, Payam ; Ganz, Frieder ; Henson, Cory ; Sheth, Amit
Author_Institution :
Centre for Commun. Syst. Res., Univ. of Surrey, Guildford, UK
fYear :
2012
fDate :
28-31 Oct. 2012
Firstpage :
1
Lastpage :
4
Abstract :
This paper describes a framework for perception creation from sensor data. We propose using data abstraction techniques, in particular Symbolic Aggregate Approximation (SAX), to analyse and create patterns from sensor data. The created patterns are then linked to semantic descriptions that define thematic, spatial and temporal features, providing highly granular abstract representation of the raw sensor data. This helps to reduce the size of the data that needs to be communicated from the sensor nodes to the gateways or highlevel processing components. We then discuss a method that uses abstract patterns created by SAX method and occurrences of different observations in a knowledge-based model to create perceptions from sensor data.
Keywords :
computerised instrumentation; data structures; internetworking; sensors; SAX method; computing perception; data abstraction techniques; gateways; highlevel processing; knowledge-based model; sensor data; sensor nodes; symbolic aggregate approximation method; Cognition; Data mining; Humans; Internet; Ontologies; Semantics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Sensors, 2012 IEEE
Conference_Location :
Taipei
ISSN :
1930-0395
Print_ISBN :
978-1-4577-1766-6
Electronic_ISBN :
1930-0395
Type :
conf
DOI :
10.1109/ICSENS.2012.6411505
Filename :
6411505
Link To Document :
بازگشت