A project led by Heriot-Watt University aims to improve the quality of life of people with Alzheimer’s disease and other forms of dementia.
Memory loss in people with Alzheimer’s disease occurs in reverse chronological order, allowing portions of long-term memory to remain accessible even as the disease progresses. Because of the memory loss and resulting difficulties communicating with others, people with dementia often struggle with reduced self-esteem and depression.
Through an EPSRC-funded project called “Agent-based Memory Prosthesis to Momoed Reminiscing” (AMPER), researchers at Heriot-Watt and Strathclyde University aim to develop an agent with a novel, human-like autobiographical memory model that tells stories to preserve memories. to get.
“The basic idea of the project is that we can support reminiscence therapy,” said lead researcher Prof. Ruth Aylett, a professor of computer science at Heriot-Watt, whose academic background is in robotics and AI, with a particular focus on how interacting with robots can support humans.
Machine learning identifies the risk of developing dementia
Dyson and Jackie Stewart support dementia research
“Reminiscence therapy is a way of coordinating storytelling with an older person with dementia, practicing their early memories, which are often retained much longer than more recent ones, and providing them with an interesting interactive experience, often using supportive material – so you could use photos, for example.”
Aylett explained that the idea was conceived by her co-researcher at Heriot-Watt, Dr. Mei Yii Lim, who has spent years modeling human memory. The proposed agent will utilize individualized repositories of life experiences in real social contexts, built around a user-centric design that can be used by individuals with dementia and their caregivers in a domestic environment.
The goal is to surface memories residing in the still-viable regions of the brain, collecting generations and personally relevant multimedia materials organized and recognized by the agent’s autobiographical memory.
“Human memory is not like a database … it’s an associative structure, it has a network, activation spreads across it and memories are indexed both by emotion and location and personality and so on, by the meaning of the memory,” Aylett said.
“You can go from one memory to another, which is what people do when they reminisce, so building a model of how human memory works is likely to yield a much smoother and more interesting approach to reminiscence therapy than taking things from a database to pick.” .”
In addition to running the technology through a tablet-based interface to make it more widely accessible and cheaper, the team plans to examine the use of a desktop robot separately to see if there are benefits to be gained from a 3D rendering of a character.
Project partners include charity Sporty memories, which provides reminiscence therapy to people with dementia through video imaging in day care centres, NHS Scotland Neuroprogressive and Dementia Network and the Latin American Network for Dementia Research.
