Hierarchical activity recognition using automatically clustered actions

Tim L.M. van Kasteren*, Gwenn Englebienne, Ben J.A. Kröse

*Corresponding author for this work

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

49 Citations (Scopus)


The automatic recognition of human activities such as cooking, showering and sleeping allows many potential applications in the area of ambient intelligence. In this paper we show that using a hierarchical structure to model the activities from sensor data can be very beneficial for the recognition performance of the model. We present a two-layer hierarchical model in which activities consist of a sequence of actions. During training, sensor data is automatically clustered into clusters of actions that best fit to the data, so that sensor data only has to be labeled with activities, not actions. Our proposed model is evaluated on three real world datasets and compared to two non-hierarchical temporal probabilistic models. The hierarchical model outperforms the non-hierarchical models in all datasets and does so significantly in two of the three datasets.

Original languageEnglish
Title of host publicationAmbient Intelligence
Subtitle of host publicationSecond International Joint Conference, AmI 2011, Amsterdam, The Netherlands, November 16-18, 2011, Proceedings
EditorsDavid V. Keyson, Mary Lou Maher, Norbert Streitz
Place of PublicationBerlin, Heidelberg
Number of pages10
ISBN (Electronic)978-3-642-25167-2
ISBN (Print)978-3-642-25166-5
Publication statusPublished - 2011
Externally publishedYes
Event2nd International Joint Conference on Ambient Intelligence, AmI 2011 - Amsterdam, Netherlands
Duration: 16 Nov 201118 Nov 2011

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference2nd International Joint Conference on Ambient Intelligence, AmI 2011


  • Activity recognition
  • Hierarchical models
  • Sensor networks
  • n/a OA procedure


Dive into the research topics of 'Hierarchical activity recognition using automatically clustered actions'. Together they form a unique fingerprint.

Cite this