Using duration to learn activities of daily living in a smart home environment

Research output: Chapter in Book/Report/Conference proceedingConference contribution

23 Citations (Scopus)

Abstract

Recognition of inhabitants' activities of daily living (ADLs) is an important task in smart homes to support assisted living for elderly people aging in place. However, uncertain information brings challenge to activity recognition which can be categorised into environmental uncertainties from sensor readings and user uncertainties of variations in the ways to carry out activities in different contexts, or by different users within the same environment. To address the challenges of these two types of uncertainty, in this paper, we introduce the innovative idea of incorporating activity duration into the framework of learning inhabitants' behaviour patterns on carrying out ADLs in smart home environment. A probabilistic learning algorithm is proposed with duration information in the context of multi-inhabitants in a single home environment. The prediction is for both inhabitant and ADL using the learned model representing what activity is carried out and who performed it. Experiments are designed for the evaluation of duration information in identifying activities and inhabitants. Real data have been collected in a smart kitchen laboratory, and realistic synthetic data are generated for evaluation. Evaluations show encouraging results for higher-level activity identification and improvement on inhabitant and activity prediction in the challenging situation of incomplete observation due to unreliable sensors compared to models that are derived with no duration information. The approach also provides a potential opportunity to identify inhabitants' concept drift in long-term monitoring and respond to a deteriorating situation at as early stage as possible.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages1-8
Number of pages8
DOIs
Publication statusPublished - 20 Mar 2010
EventPervasive Computing Technologies for Healthcare (PervasiveHealth), 2010 4th International Conference on-NO PERMISSIONS - Munich
Duration: 20 Mar 2010 → …

Conference

ConferencePervasive Computing Technologies for Healthcare (PervasiveHealth), 2010 4th International Conference on-NO PERMISSIONS
Period20/03/10 → …

Fingerprint

Kitchens
Sensors
Learning algorithms
Aging of materials
Monitoring
Uncertainty
Experiments
Assisted living

Keywords

  • home automation
  • learning systems
  • probability
  • activity recognition
  • daily living activities
  • multi-inhabitants context
  • probabilistic learning algorithm
  • smart home environment
  • smart kitchen laboratory
  • Aging
  • Dementia
  • Home computing
  • Intelligent sensors
  • Monitoring
  • Predictive models
  • Senior citizens
  • Sensor phenomena and characterization
  • Smart homes
  • Uncertainty
  • ADL
  • duration
  • probabilistic learning
  • reasoning
  • smart home

Cite this

@inproceedings{88a9ccb8a78c4737811f11c90be103b4,
title = "Using duration to learn activities of daily living in a smart home environment",
abstract = "Recognition of inhabitants' activities of daily living (ADLs) is an important task in smart homes to support assisted living for elderly people aging in place. However, uncertain information brings challenge to activity recognition which can be categorised into environmental uncertainties from sensor readings and user uncertainties of variations in the ways to carry out activities in different contexts, or by different users within the same environment. To address the challenges of these two types of uncertainty, in this paper, we introduce the innovative idea of incorporating activity duration into the framework of learning inhabitants' behaviour patterns on carrying out ADLs in smart home environment. A probabilistic learning algorithm is proposed with duration information in the context of multi-inhabitants in a single home environment. The prediction is for both inhabitant and ADL using the learned model representing what activity is carried out and who performed it. Experiments are designed for the evaluation of duration information in identifying activities and inhabitants. Real data have been collected in a smart kitchen laboratory, and realistic synthetic data are generated for evaluation. Evaluations show encouraging results for higher-level activity identification and improvement on inhabitant and activity prediction in the challenging situation of incomplete observation due to unreliable sensors compared to models that are derived with no duration information. The approach also provides a potential opportunity to identify inhabitants' concept drift in long-term monitoring and respond to a deteriorating situation at as early stage as possible.",
keywords = "home automation, learning systems, probability, activity recognition, daily living activities, multi-inhabitants context, probabilistic learning algorithm, smart home environment, smart kitchen laboratory, Aging, Dementia, Home computing, Intelligent sensors, Monitoring, Predictive models, Senior citizens, Sensor phenomena and characterization, Smart homes, Uncertainty, ADL, duration, probabilistic learning, reasoning, smart home",
author = "Shuai Zhang and Sally McClean and Scotney Bryan and Priyanka Chaurasia and Chris Nugent",
year = "2010",
month = "3",
day = "20",
doi = "10.4108/ICST.PERVASIVEHEALTH2010.8804",
language = "English",
isbn = "978-963-9799-89-9",
pages = "1--8",
booktitle = "Unknown Host Publication",

}

Zhang, S, McClean, S, Bryan, S, Chaurasia, P & Nugent, C 2010, Using duration to learn activities of daily living in a smart home environment. in Unknown Host Publication. pp. 1-8, Pervasive Computing Technologies for Healthcare (PervasiveHealth), 2010 4th International Conference on-NO PERMISSIONS, 20/03/10. https://doi.org/10.4108/ICST.PERVASIVEHEALTH2010.8804

Using duration to learn activities of daily living in a smart home environment. / Zhang, Shuai; McClean, Sally; Bryan, Scotney; Chaurasia, Priyanka; Nugent, Chris.

Unknown Host Publication. 2010. p. 1-8.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Using duration to learn activities of daily living in a smart home environment

AU - Zhang, Shuai

AU - McClean, Sally

AU - Bryan, Scotney

AU - Chaurasia, Priyanka

AU - Nugent, Chris

PY - 2010/3/20

Y1 - 2010/3/20

N2 - Recognition of inhabitants' activities of daily living (ADLs) is an important task in smart homes to support assisted living for elderly people aging in place. However, uncertain information brings challenge to activity recognition which can be categorised into environmental uncertainties from sensor readings and user uncertainties of variations in the ways to carry out activities in different contexts, or by different users within the same environment. To address the challenges of these two types of uncertainty, in this paper, we introduce the innovative idea of incorporating activity duration into the framework of learning inhabitants' behaviour patterns on carrying out ADLs in smart home environment. A probabilistic learning algorithm is proposed with duration information in the context of multi-inhabitants in a single home environment. The prediction is for both inhabitant and ADL using the learned model representing what activity is carried out and who performed it. Experiments are designed for the evaluation of duration information in identifying activities and inhabitants. Real data have been collected in a smart kitchen laboratory, and realistic synthetic data are generated for evaluation. Evaluations show encouraging results for higher-level activity identification and improvement on inhabitant and activity prediction in the challenging situation of incomplete observation due to unreliable sensors compared to models that are derived with no duration information. The approach also provides a potential opportunity to identify inhabitants' concept drift in long-term monitoring and respond to a deteriorating situation at as early stage as possible.

AB - Recognition of inhabitants' activities of daily living (ADLs) is an important task in smart homes to support assisted living for elderly people aging in place. However, uncertain information brings challenge to activity recognition which can be categorised into environmental uncertainties from sensor readings and user uncertainties of variations in the ways to carry out activities in different contexts, or by different users within the same environment. To address the challenges of these two types of uncertainty, in this paper, we introduce the innovative idea of incorporating activity duration into the framework of learning inhabitants' behaviour patterns on carrying out ADLs in smart home environment. A probabilistic learning algorithm is proposed with duration information in the context of multi-inhabitants in a single home environment. The prediction is for both inhabitant and ADL using the learned model representing what activity is carried out and who performed it. Experiments are designed for the evaluation of duration information in identifying activities and inhabitants. Real data have been collected in a smart kitchen laboratory, and realistic synthetic data are generated for evaluation. Evaluations show encouraging results for higher-level activity identification and improvement on inhabitant and activity prediction in the challenging situation of incomplete observation due to unreliable sensors compared to models that are derived with no duration information. The approach also provides a potential opportunity to identify inhabitants' concept drift in long-term monitoring and respond to a deteriorating situation at as early stage as possible.

KW - home automation

KW - learning systems

KW - probability

KW - activity recognition

KW - daily living activities

KW - multi-inhabitants context

KW - probabilistic learning algorithm

KW - smart home environment

KW - smart kitchen laboratory

KW - Aging

KW - Dementia

KW - Home computing

KW - Intelligent sensors

KW - Monitoring

KW - Predictive models

KW - Senior citizens

KW - Sensor phenomena and characterization

KW - Smart homes

KW - Uncertainty

KW - ADL

KW - duration

KW - probabilistic learning

KW - reasoning

KW - smart home

U2 - 10.4108/ICST.PERVASIVEHEALTH2010.8804

DO - 10.4108/ICST.PERVASIVEHEALTH2010.8804

M3 - Conference contribution

SN - 978-963-9799-89-9

SP - 1

EP - 8

BT - Unknown Host Publication

ER -