Enhancing ontological reasoning with uncertainty handling for activity recognition

Abstract

Ontology-based activity recognition is gaining interest due to its expressiveness and comprehensive reasoning mechanism. An obstacle to its wider use is that the imperfect observations result in failure of recognizing activities. This paper proposes a novel reasoning algorithm for activity recognition in smart environments. The algorithm integrates OWL ontological reasoning mechanism with Dempster–Shafer theory of evidence to provide support for handling uncertainty in activity recognition. It quantifies uncertainty while aggregating contextual information and provides a degree of belief that facilitates more robust decision making in activity recognition. The presented approach has been implemented and evaluated on an internal and public datasets and compared with a data-driven approach that is using hidden Markov model. Results have shown that the proposed reasoning approach can accommodate uncertainties and subsequently infer the activities more accurately in comparison with existing ontology-based recognition and perform comparably well to the data-driven approach.