Using topic modelling algorithms for hierarchical activity discovery

Eoin Rogers, John D. Kelleher, Robert J. Ross

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationAmbient Intelligence -Software and Applications – 7th International Symposium on Ambient Intelligence, ISAmI 2016
EditorsJuan F. De Paz, Hyun Yoe, Gabriel Villarrubia, Paulo Novais, Helena Lindgren, Antonio Fernández-Caballero, Andres Jiménez Ramírez
PublisherSpringer Verlag
Pages41-48
Number of pages8
ISBN (Print)9783319401133
DOIs
Publication statusPublished - 2016
Event7th International Symposium on Ambient Intelligence, ISAmI 2016 - Seville, Spain
Duration: 1 Jun 20163 Jun 2016

Publication series

NameAdvances in Intelligent Systems and Computing
Volume476
ISSN (Print)2194-5357

Conference

Conference7th International Symposium on Ambient Intelligence, ISAmI 2016
Country/TerritorySpain
CitySeville
Period1/06/163/06/16

Fingerprint

Dive into the research topics of 'Using topic modelling algorithms for hierarchical activity discovery'. Together they form a unique fingerprint.

Cite this