Checking Models for Activity Recognition

Martin Nyolt, Kristina Yordanova, Thomas Kirste

2015

Abstract

Model checking is well established in system design and business process modelling. Model checking ensures and automatically proves safety and soundness of models used in day-to-day systems. However, the need for model checking in activity recognition has not been realised. Models for activity recognition can be built by prior knowledge. They can encode typical behaviour patterns and allow causal reasoning. As these models are manually designed they suffer from modelling errors. To address the problem, we discuss different classes of sensible properties and evaluate three different models for activity recognition. In all cases, modelling errors and inconsistencies have been found.

Paper Citation

in Harvard Style

Nyolt M., Yordanova K. and Kirste T. (2015). Checking Models for Activity Recognition . In Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-074-1, pages 497-502. DOI: 10.5220/0005275204970502

in Bibtex Style

@conference{icaart15,
author={Martin Nyolt and Kristina Yordanova and Thomas Kirste},
title={Checking Models for Activity Recognition},
booktitle={Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2015},
pages={497-502},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005275204970502},
isbn={978-989-758-074-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Checking Models for Activity Recognition
SN - 978-989-758-074-1
AU - Nyolt M.
AU - Yordanova K.
AU - Kirste T.
PY - 2015
SP - 497
EP - 502
DO - 10.5220/0005275204970502