Ontological, fully probabilistic knowledge model for human activity recognition

Efficiency and scalability are obstacles that have not yet received a viable response from the human activity recognition research community. This paper proposes an activity recognition method. The knowledge model is in the form of ontology, the state-of-the-art in knowledge representation and reaso...

Full description

Bibliographic Details
Main Authors: Foudeh, Pouya, Salim, Naomie
Format: Article
Language:English
Published: Penerbit UTM Press 2023
Subjects:
Online Access:http://eprints.utm.my/105080/1/PouyaFoudeh2023_OntologicalFullyProbabilisticKnowledgeModel.pdf
_version_ 1796867784666251264
author Foudeh, Pouya
Salim, Naomie
author_facet Foudeh, Pouya
Salim, Naomie
author_sort Foudeh, Pouya
collection ePrints
description Efficiency and scalability are obstacles that have not yet received a viable response from the human activity recognition research community. This paper proposes an activity recognition method. The knowledge model is in the form of ontology, the state-of-the-art in knowledge representation and reasoning. The ontology starts with probabilistic information about subjects’ low-level activities and location and then is populated with the assertion axioms learned from data or defined by the user. Unlike methods that choose only the most probable candidate from sensor readings, the proposed method keeps multiple candidates with the known degree of confidence for each one and involves them in decision making. Using this method, the system is more flexible to deal with unreliable data, readings from sensors, and the final recognition rate is improved. Besides, to resolve the scalability problem, a system is designed and implemented to do reasoning and storing in a relational database management system. Numerical evaluations and conceptual benchmarking prove the proposed system feasibility.
first_indexed 2024-04-09T03:46:05Z
format Article
id utm.eprints-105080
institution Universiti Teknologi Malaysia - ePrints
language English
last_indexed 2024-04-09T03:46:05Z
publishDate 2023
publisher Penerbit UTM Press
record_format dspace
spelling utm.eprints-1050802024-04-07T03:45:06Z http://eprints.utm.my/105080/ Ontological, fully probabilistic knowledge model for human activity recognition Foudeh, Pouya Salim, Naomie Q Science (General) Efficiency and scalability are obstacles that have not yet received a viable response from the human activity recognition research community. This paper proposes an activity recognition method. The knowledge model is in the form of ontology, the state-of-the-art in knowledge representation and reasoning. The ontology starts with probabilistic information about subjects’ low-level activities and location and then is populated with the assertion axioms learned from data or defined by the user. Unlike methods that choose only the most probable candidate from sensor readings, the proposed method keeps multiple candidates with the known degree of confidence for each one and involves them in decision making. Using this method, the system is more flexible to deal with unreliable data, readings from sensors, and the final recognition rate is improved. Besides, to resolve the scalability problem, a system is designed and implemented to do reasoning and storing in a relational database management system. Numerical evaluations and conceptual benchmarking prove the proposed system feasibility. Penerbit UTM Press 2023-03 Article PeerReviewed application/pdf en http://eprints.utm.my/105080/1/PouyaFoudeh2023_OntologicalFullyProbabilisticKnowledgeModel.pdf Foudeh, Pouya and Salim, Naomie (2023) Ontological, fully probabilistic knowledge model for human activity recognition. Jurnal Teknologi, 85 (2). pp. 183-199. ISSN 0127-9696 http://dx.doi.org/10.11113/jurnalteknologi.v85.18942 DOI:10.11113/jurnalteknologi.v85.18942
spellingShingle Q Science (General)
Foudeh, Pouya
Salim, Naomie
Ontological, fully probabilistic knowledge model for human activity recognition
title Ontological, fully probabilistic knowledge model for human activity recognition
title_full Ontological, fully probabilistic knowledge model for human activity recognition
title_fullStr Ontological, fully probabilistic knowledge model for human activity recognition
title_full_unstemmed Ontological, fully probabilistic knowledge model for human activity recognition
title_short Ontological, fully probabilistic knowledge model for human activity recognition
title_sort ontological fully probabilistic knowledge model for human activity recognition
topic Q Science (General)
url http://eprints.utm.my/105080/1/PouyaFoudeh2023_OntologicalFullyProbabilisticKnowledgeModel.pdf
work_keys_str_mv AT foudehpouya ontologicalfullyprobabilisticknowledgemodelforhumanactivityrecognition
AT salimnaomie ontologicalfullyprobabilisticknowledgemodelforhumanactivityrecognition