Location
Grand Wailea, Hawaii
Event Website
https://hicss.hawaii.edu/
Start Date
8-1-2019 12:00 AM
End Date
11-1-2019 12:00 AM
Description
Ambient Assisted Living (AAL) research has received extensive attention in recent years. AAL applications combine aspects of Internet of Things (IoT), smart platform design and machine learning to produce an intelligent system. In this paper we describe a personalised IoT-based AAL system that enables an independent and safe life for elderly people within their own home via real-time monitoring and intervention. The system, HalleyAssist underpinned by smart home automation functions includes a novel approach for monitoring the wellbeing and detecting abnormal changes in behavioral patterns of an elderly person. The significance of the approach is in the use of machine learning models to automatically learn normal behavioral pattern for the person from IoT sensor data and using the models derived to detect significant changes in behavioral pattern should they occur. The architecture and developed proof of concept of the proposed system is presented along with discussion of how privacy and security concerns are addressed. We also report on outcomes of real-world in-home trials of an early version of the system where it was installed in four older people's home for a period of six weeks. The response from the older people to the deployed system was very positive. Finally, the paper presents a discussion and an analysis of the results using the data collected during the in-home trials.
HalleyAssist: A Personalised Internet of Things Technology to Assist the Elderly in Daily Living
Grand Wailea, Hawaii
Ambient Assisted Living (AAL) research has received extensive attention in recent years. AAL applications combine aspects of Internet of Things (IoT), smart platform design and machine learning to produce an intelligent system. In this paper we describe a personalised IoT-based AAL system that enables an independent and safe life for elderly people within their own home via real-time monitoring and intervention. The system, HalleyAssist underpinned by smart home automation functions includes a novel approach for monitoring the wellbeing and detecting abnormal changes in behavioral patterns of an elderly person. The significance of the approach is in the use of machine learning models to automatically learn normal behavioral pattern for the person from IoT sensor data and using the models derived to detect significant changes in behavioral pattern should they occur. The architecture and developed proof of concept of the proposed system is presented along with discussion of how privacy and security concerns are addressed. We also report on outcomes of real-world in-home trials of an early version of the system where it was installed in four older people's home for a period of six weeks. The response from the older people to the deployed system was very positive. Finally, the paper presents a discussion and an analysis of the results using the data collected during the in-home trials.
https://aisel.aisnet.org/hicss-52/hc/technologies_for_wellness_management/7