Real-time radio remixing for people with mild to moderate dementia who live alone, incorporating agitation reduction, and diary reminders.
Since October 2019 ARU has been running RadioMe, a project using artificial intelligence to adapt and personalise live radio, with the aim of designing and testing a radio system for people with dementia who are still living independently which:
RadioMe will address key causes of hospital admission for people living with dementia, such as agitation and other neuropsychiatric symptoms, and problems adhering to their regular medication program. As a result, it is hoped that quality of life will improve, and people will be able to remain living independently at home for longer.
The Engineering and Physical Sciences Research Council (EPSRC) funded project (EP/S026959/1) will capitalise on the popularity of radio amongst the age group most likely to be living with dementia, developing a way to seamlessly ‘remix’ live digital broadcast so that listeners will receive personalised reminders, information and music.
A user switching on the radio in the morning might find their usual local station. However, at certain points a DJ-like voice could override the real DJ and remind the listener to have a drink or take their prescribed medication. RadioMe might detect that the listener is becoming agitated via their bio-bracelet readings. The software could then override the scheduled song choice and select a song from the user’s personal library, known to be likely to calm them.
We're looking for people with a diagnosis of dementia, or who are showing signs of dementia, to take part in the RadioMe project.
The RadioMe project is a partnership between University of Plymouth’s Interdisciplinary Centre for Computer Music Research and Plymouth’s Faculty of Health: Medicine, Dentistry and Human Sciences, the Glasgow Interactive Systems group at the University of Glasgow, and the Cambridge Institute for Music Therapy Research (CIMTR) at Anglia Ruskin University.
Find out more about CIMTR’s core RadioMe team: