Scotland’s innovation centre for internet of things technologies has developed an AI powered device to identify when older or vulnerable people who live alone may need immediate medical support.
CENSIS has worked on the project with partners from the University of Edinburgh, personal data specialist Mydex CIC, care technology company Carebuilder and Blackwood Homes and Care.
It said the device has so far been trialled in 19 households in Glasgow, Dundee and Buckie.
It can be wirelessly linked to a smart or conventional electricity meter to collect data on the use of household appliances ad electrical items such as kettles, microwaves and washing machines. Using machine learning, it can tag each item and determine when they have been turned on and off and can spot any anomalies.
CENSIS provided an example of when the person usually wakes up and boils a kettle at around 8am. If this has not happened by 9m they will receive an automated text message, and if there is no response an alert will be sent to their nominated contacts to check on them.
Processing data at the property
The device uses a hub process algorithm so all the data can be processed at the property rather than at a central point. The person also has access to a Mydex personal data store to have control over who can see the data for their home.
The machine learning algorithm monitors the use of power at 10-second intervals and analyses the power signatures coming from the household. The University of Edinburgh has built up a library of these signatures over the course of the project and tagged each high power item in a home to identify which ones are being used and when.
Stephen Milne, director of strategic projects at CENSIS, said: “This project is all about repurposing energy data to help inform social care and supporting healthy ageing.
“The system learns the typical activity of the individual living in the household and then spots any erratic behaviour, helping to identify when they may have issues. These could be one-off events, like a fall, and with further research, the system may be able to track changes over a longer time period that may indicate gradual, and more difficult to spot health issues, such as the onset of a condition such as dementia.
“While there are other technologies related to monitoring activity, this is the first full service deployment that has been implemented through passively monitoring a property’s smart meter system. The device can also pick out each item being monitored, making it much more likely to spot any anomalies, and is barely noticeable for the householder.
“After these trials, we are looking to develop the technology to the commercial product stage and deploy it at a much bigger scale, and are open to taking this forward with talks with potential long term partners.”
Impacting lives
Lynda Webb, senior researcher at the university’s School of Informatics, said: “A prior project of 250 homes in Edinburgh enabled the development of the algorithms that are used today in this project. It is so exciting to see the application of this idea and the years of algorithm development becoming a service which is already impacting the lives of people in the trial.”
Blackwood Home and Care is running its three-year Peoplehood project to develop a future proof model for independent living for its residents, and is aiming to set out a blueprint that includes the use of new technologies.
Its Peoplehood programme manager, Lindley Kirkpatrick, said: “The development of this new device utilising AI technology could, however, prove to be one of the most exciting that we have seen. For carers and loved ones to get ahead of time notice of potential medical emergencies as well as the onset of conditions of dementia is of huge importance.
“We very much look forward to examining the details that come out of the trial to understand how this has aided participants of the Peoplehood project.”
