Inferring Model Structures from Inertial Sensor Data in Distributed Activity Recognition

P. Casale, O.D. Amft

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Samenvatting

The Activity-Events-Detectors paradigm describes the rela-tions between activities and sensor nodes under a distributed perspective. The paradigm provides a conceptual abstraction that decouples the full set of activities from the sensor network with the aim of improving the recognition performances and lowering the computational constraints of the detection tasks in the node. In this work, a data-driven methodol-ogy that learns groups of activities and infers the structure of detector models of the nodes of the network under the Activity-Events-Detectors paradigm is proposed. The methodology, defined on a non parametric clustering procedure, makes no assumptions about the number of groups and the relations between detectors and activities: all the relevant in-formation are derived and inferred from the data. Using the inferred structured models, a performance boost of 15% in the final classification accuracy is obtained with a significant reduction of the computational resources of the detectors.
Originele taal-2Engels
TitelAmbient intelligence : 4th International Joint Conference, AmI 2013, Dublin, Ireland, December 3-5, 2013 : proceedings
RedacteurenJ.C. Augusto, R. Wichert, R. Collier, D. Keyson, A. Salah, A. Tan
UitgeverijSpringer
Pagina's62-77
ISBN van geprinte versie978-3-319-03646-5
DOI's
StatusGepubliceerd - 2013
Evenement4th International Joint Conference on Ambient Intelligence (Ami 2013) - Dublin, Ierland
Duur: 3 dec 20135 dec 2013
Congresnummer: 4

Publicatie series

NaamLecture Notes in Computer Science
Volume8309
ISSN van geprinte versie0302-9743

Congres

Congres4th International Joint Conference on Ambient Intelligence (Ami 2013)
Verkorte titelAmI 2013
LandIerland
StadDublin
Periode3/12/135/12/13
Ander4th International Joint Conference on Ambient Intelligence (AmI13)

Vingerafdruk Duik in de onderzoeksthema's van 'Inferring Model Structures from Inertial Sensor Data in Distributed Activity Recognition'. Samen vormen ze een unieke vingerafdruk.

Citeer dit