A Hybrid Approach to Recognising Activities of Daily Living from Object Use in the Home Environment

Accurate recognition of Activities of Daily Living (ADL) plays an important role in providing assistance and support to the elderly and cognitively impaired. Current knowledge-driven and ontology-based techniques model object concepts from assumptions and everyday common knowledge of object use for...

Full description

Bibliographic Details
Main Authors: Isibor Kennedy Ihianle, Usman Naeem, Syed Islam, Abdel-Rahman Tawil
Format: Article
Language:English
Published: MDPI AG 2018-01-01
Series:Informatics
Subjects:
Online Access:http://www.mdpi.com/2227-9709/5/1/6
_version_ 1818289154481455104
author Isibor Kennedy Ihianle
Usman Naeem
Syed Islam
Abdel-Rahman Tawil
author_facet Isibor Kennedy Ihianle
Usman Naeem
Syed Islam
Abdel-Rahman Tawil
author_sort Isibor Kennedy Ihianle
collection DOAJ
description Accurate recognition of Activities of Daily Living (ADL) plays an important role in providing assistance and support to the elderly and cognitively impaired. Current knowledge-driven and ontology-based techniques model object concepts from assumptions and everyday common knowledge of object use for routine activities. Modelling activities from such information can lead to incorrect recognition of particular routine activities resulting in possible failure to detect abnormal activity trends. In cases where such prior knowledge are not available, such techniques become virtually unemployable. A significant step in the recognition of activities is the accurate discovery of the object usage for specific routine activities. This paper presents a hybrid framework for automatic consumption of sensor data and associating object usage to routine activities using Latent Dirichlet Allocation (LDA) topic modelling. This process enables the recognition of simple activities of daily living from object usage and interactions in the home environment. The evaluation of the proposed framework on the Kasteren and Ordonez datasets show that it yields better results compared to existing techniques.
first_indexed 2024-12-13T02:07:46Z
format Article
id doaj.art-64e71aaf6248471f83e385a54587b51a
institution Directory Open Access Journal
issn 2227-9709
language English
last_indexed 2024-12-13T02:07:46Z
publishDate 2018-01-01
publisher MDPI AG
record_format Article
series Informatics
spelling doaj.art-64e71aaf6248471f83e385a54587b51a2022-12-22T00:03:05ZengMDPI AGInformatics2227-97092018-01-0151610.3390/informatics5010006informatics5010006A Hybrid Approach to Recognising Activities of Daily Living from Object Use in the Home EnvironmentIsibor Kennedy Ihianle0Usman Naeem1Syed Islam2Abdel-Rahman Tawil3School of Architecture, Computing and Engineering (ACE), University of East London, London E16 2RD, UKSchool of Architecture, Computing and Engineering (ACE), University of East London, London E16 2RD, UKSchool of Architecture, Computing and Engineering (ACE), University of East London, London E16 2RD, UKSchool of Computing and Digital Technology, Birmingham City University, Birmingham B5 5JU, UKAccurate recognition of Activities of Daily Living (ADL) plays an important role in providing assistance and support to the elderly and cognitively impaired. Current knowledge-driven and ontology-based techniques model object concepts from assumptions and everyday common knowledge of object use for routine activities. Modelling activities from such information can lead to incorrect recognition of particular routine activities resulting in possible failure to detect abnormal activity trends. In cases where such prior knowledge are not available, such techniques become virtually unemployable. A significant step in the recognition of activities is the accurate discovery of the object usage for specific routine activities. This paper presents a hybrid framework for automatic consumption of sensor data and associating object usage to routine activities using Latent Dirichlet Allocation (LDA) topic modelling. This process enables the recognition of simple activities of daily living from object usage and interactions in the home environment. The evaluation of the proposed framework on the Kasteren and Ordonez datasets show that it yields better results compared to existing techniques.http://www.mdpi.com/2227-9709/5/1/6activity recognitiontopic modelontology modelLatent Dirichlet Allocation
spellingShingle Isibor Kennedy Ihianle
Usman Naeem
Syed Islam
Abdel-Rahman Tawil
A Hybrid Approach to Recognising Activities of Daily Living from Object Use in the Home Environment
Informatics
activity recognition
topic model
ontology model
Latent Dirichlet Allocation
title A Hybrid Approach to Recognising Activities of Daily Living from Object Use in the Home Environment
title_full A Hybrid Approach to Recognising Activities of Daily Living from Object Use in the Home Environment
title_fullStr A Hybrid Approach to Recognising Activities of Daily Living from Object Use in the Home Environment
title_full_unstemmed A Hybrid Approach to Recognising Activities of Daily Living from Object Use in the Home Environment
title_short A Hybrid Approach to Recognising Activities of Daily Living from Object Use in the Home Environment
title_sort hybrid approach to recognising activities of daily living from object use in the home environment
topic activity recognition
topic model
ontology model
Latent Dirichlet Allocation
url http://www.mdpi.com/2227-9709/5/1/6
work_keys_str_mv AT isiborkennedyihianle ahybridapproachtorecognisingactivitiesofdailylivingfromobjectuseinthehomeenvironment
AT usmannaeem ahybridapproachtorecognisingactivitiesofdailylivingfromobjectuseinthehomeenvironment
AT syedislam ahybridapproachtorecognisingactivitiesofdailylivingfromobjectuseinthehomeenvironment
AT abdelrahmantawil ahybridapproachtorecognisingactivitiesofdailylivingfromobjectuseinthehomeenvironment
AT isiborkennedyihianle hybridapproachtorecognisingactivitiesofdailylivingfromobjectuseinthehomeenvironment
AT usmannaeem hybridapproachtorecognisingactivitiesofdailylivingfromobjectuseinthehomeenvironment
AT syedislam hybridapproachtorecognisingactivitiesofdailylivingfromobjectuseinthehomeenvironment
AT abdelrahmantawil hybridapproachtorecognisingactivitiesofdailylivingfromobjectuseinthehomeenvironment