By Dorothy Monekosso | July 4, 2022
Dorothy Monekosso, professor of computer science, looks at the potential of truly ‘smart’ homes to help people with dementia live more independently.
You may already have what is often referred to as a ‘smart home’, where your lights or music are connected with voice-activated technology like Alexa or Siri. But when researchers talk about smart homes, we usually mean technologies that use artificial intelligence to learn your habits and automatically customize your home in response to them. Perhaps the most obvious example of this is thermostats that learn when you’re likely to be home and what temperature you prefer, and adjust themselves accordingly without you having to change any settings.
My colleagues and I are interested in how this kind of real smart home technology can help people with dementia. We hope it’s possible learn to recognize the various household activities that a dementia patient carries out during the day and helps them do so. This could even lead to the introduction of domestic robots to help with chores automatically.
The growing number of people with dementia encourages caregivers to look at technology as a way to support human caregivers and improve patients’ quality of life. In particular, we want to use technology to enable people with dementia to live more independently for as long as possible.
Dementia affects people cognitive skills (things like perception, learning, memory and problem solving). There are many ways in which smart home technology can help with this. It can improve safety by closing doors automatically if they are left open or turning off stoves if they are left unattended. Bed and chair sensors or wearable devices can detect how well someone is sleeping or whether they have been inactive for an unusual amount of time.
Lights, TVs and telephones can be controlled with voice-activated technology or a graphical interface for those with memory problems. Appliances such as kettles, refrigerators and washing machines can be controlled remotely.
People with dementia can also become disoriented, wander, and get lost. Advanced Surveillance Systems using radio waves indoors and GPS outdoors can track people’s movements and give a warning if they travel outside a certain area.
All the data from these devices can be fed into complex artificial intelligence that automatic learning the typical things people do at home. This is the classic AI problem of pattern recognition (searching for patterns and learning from a lot of data). For starters, the computer would create a rough model of the residents’ daily routines and then detect when something out of the ordinary happens, such as not getting up or eating at the usual time.
A finer model could then show the steps in a certain activity like washing hands or make a cup of tea. By following step-by-step what the person is doing, if he forgets halfway through, the system can remind him and help him keep going.
The more general model of the daily routine could use harmless sensors, such as those in beds or doors. But to give the software a more granular understanding of what’s going on in the house, you need cameras and video processing that can detect specific actions, such as someone falling over. The downside of these improved models is a loss of privacy.
The smart home of the future can also be equipped with a humanoid robot to help with chores. Research in this area is progressing at a steady, albeit slow pace, with Japan leading the way with nursing robots†
The biggest challenge with robots in the home or care home is operating in an unstructured environment. Factory robots can work with speed and precision because they perform specific, pre-programmed tasks in a specially designed space. But the average home is less structured and often changes as furniture, objects and people move around. This is an important problem that researchers are investigating using artificial intelligence techniques, such as capturing data from images (computer vision).
Robots don’t just have the potential to help with physical labor. While most smart home technologies focus on mobility, strength and other physical attributes, emotional well-being is equally important. A good example is the PARO robotwhich looks like a cute toy seal, but is designed to provide therapeutic emotional support and comfort.
The real cleverness of all this technology comes from automatically discovering how the person interacts with their environment to provide support at the right time. If we built technology to do everything for people, it would reduce their independence.
Emotion recognition software can, for example, assess a person’s feelings by their expression, adjust the house or suggest activities, for example by changing the lighting or encouraging the patient to exercise. As the resident’s physical and cognitive decline increases, the smart home would adapt to provide more appropriate support.
There are still many challenges to overcome, from improving the reliability and robustness of sensors, to preventing annoying or disturbing alarms, to ensuring the technology safe from cyber criminals† And for all technology, there will always be a need for a human in the loop. The technology is intended to complement human caregivers and must be adapted to individual users. But the potential is there for real smart homes to help people with dementia live richer, fuller and hopefully longer lives.