Strategies for modelling human behaviour for activity recognition with precondition-effect rules

Authors:
Kristina Yordanova;Frank Krüger;Thomas Kirste
Affiliations:
Institute of Computer Science, MMIS Group, University of Rostock, Germany;Institute of Computer Science, MMIS Group, University of Rostock, Germany;Institute of Computer Science, MMIS Group, University of Rostock, Germany
Venue:
KI'12 Proceedings of the 35th Annual German conference on Advances in Artificial Intelligence
Year:
2012

Citing 1
Cited 1

Towards creating assistive software by employing human behavior models

Journal of Ambient Intelligence and Smart Environments - A software engineering perspective on smart applications for AmI

Situation aware interaction with multi-modal business applications in smart environments

HCI'13 Proceedings of the 15th international conference on Human Interface and the Management of Information: information and interaction for learning, culture, collaboration and business - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

The manner in which the human behaviour and the environment are modelled greatly influences the activity recognition performance in context-aware systems and an inappropriate choice of modelling mechanism could lead to unwanted or unexpected model behaviour. In this work we present an approach for modelling human behaviour based on precondition-effect rules, and discuss in detail different modelling strategies. As a result, the paper provides useful guidelines for modelling human behaviour for activity recognition, including best practices and pitfalls that should be avoided for one to build a successful model.