TY - GEN
T1 - Using topic modelling algorithms for hierarchical activity discovery
AU - Rogers, Eoin
AU - Kelleher, John D.
AU - Ross, Robert J.
N1 - Publisher Copyright:
© Springer International Publishing Switzerland 2016.
PY - 2016
Y1 - 2016
N2 - Activity discovery is the unsupervised process of discovering patterns in data produced from sensor networks that are monitoring the behaviour of human subjects. Improvements in activity discovery may simplify the training of activity recognition models by enabling the automated annotation of datasets and also the construction of systems that can detect and highlight deviations from normal behaviour. With this in mind, we propose an approach to activity discovery based on topic modelling techniques, and evaluate it on a dataset that mimics complex, interleaved sensor data in the real world. We also propose a means for discovering hierarchies of aggregated activities and discuss a mechanism for visualising the behaviour of such algorithms graphically.
AB - Activity discovery is the unsupervised process of discovering patterns in data produced from sensor networks that are monitoring the behaviour of human subjects. Improvements in activity discovery may simplify the training of activity recognition models by enabling the automated annotation of datasets and also the construction of systems that can detect and highlight deviations from normal behaviour. With this in mind, we propose an approach to activity discovery based on topic modelling techniques, and evaluate it on a dataset that mimics complex, interleaved sensor data in the real world. We also propose a means for discovering hierarchies of aggregated activities and discuss a mechanism for visualising the behaviour of such algorithms graphically.
UR - http://www.scopus.com/inward/record.url?scp=84976471630&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-40114-0_5
DO - 10.1007/978-3-319-40114-0_5
M3 - Conference contribution
AN - SCOPUS:84976471630
SN - 9783319401133
T3 - Advances in Intelligent Systems and Computing
SP - 41
EP - 48
BT - Ambient Intelligence -Software and Applications – 7th International Symposium on Ambient Intelligence, ISAmI 2016
A2 - De Paz, Juan F.
A2 - Yoe, Hyun
A2 - Villarrubia, Gabriel
A2 - Novais, Paulo
A2 - Lindgren, Helena
A2 - Fernández-Caballero, Antonio
A2 - Ramírez, Andres Jiménez
PB - Springer Verlag
T2 - 7th International Symposium on Ambient Intelligence, ISAmI 2016
Y2 - 1 June 2016 through 3 June 2016
ER -