A pioneering approach to programming is helping to develop software that could be used to save the lives of pensioners living alone.
Twelve million pensioners live in the UK and injuries resulting from falls account for more than half of hospital admissions for accidental injury, according to the charity Help the Aged.
By submitting your email address, you agree to receive emails regarding relevant topic offers from TechTarget and its partners. You can withdraw your consent at any time. Contact TechTarget at 275 Grove Street, Newton, MA.
The developed world is expected to have an elderly population of about two billion people by the year 2050. As a result, experts say that technology will need to play an increasingly significant role in supporting and monitoring people in their homes.
De Montfort University and the US University of Missouri are co-developing computer sensors that can be installed in pensioners' homes to automatically detect if a pensioner has collapsed.
The sensors will be progammed with software to interpret odd or unusual behaviour patterns in general, such as a person falling down or a fridge door not having been opened for long time.
By calculating different variables about the pensioner and the environment, the software will be able to learn when a pensioner is in genuine distress and raise an alarm.
Networks ranging from simple motion sensors to bed sensors, which capture sleep restlessness and pulse and respiration levels, have been installed in several apartments at an assisted living facility in Missouri.
The £45,000 project will build on research being carried out at Community Emergency Response Team (CERT), including a study monitoring older adults using sensors. De Montfort University's Simon Coupland will spend four months with the team in Missouri to undertake the research this year.
Coupland said, "There are many factors that can cause problems for assistive technologies in nursing and social care, from the noise of sensors on some equipment, to variations in how well technology performs in different environments, and, of course, the uncertainty involved with human behaviour. This project will look at how computational intelligence can be used to address these kinds of problems."
One example of how this technology might be used is in sensors that detect the sound of somebody falling over.
Robert John of Computer Science at De Montfort said that the secret to programming software which can accurately determine if a person is in trouble lies in a mathmatical concept known as type-2 fuzzy logic. Fuzzy logic could be used to distinguish between the sound of a person falling to the floor and other noises, such as a door being slammed.
"Any sounds suspected to be that of a fall would trigger an alarm summoning medical assistance. In this way, the technology would help to ensure that genuine emergencies are never ignored, while reducing the number of false alarms," said John
Programming with fuzzy logic allows computers to make decisions based on imprecise information and approximates how humans sometimes make decisions.
"If we were examining the height of passengers arriving at an airport, we could group passengers as being either tall or short.
"Using these two groups, we could then build a model to predict the probability of getting numbers of tall or short passengers arriving at the airport," said John.
But in fuzzy logic, rather than viewing people as either tall or short, it assumes that there are degrees of truth - using the airport example, fuzzy logic assumes that all passengers are tall but to different degrees, said John.
In this way, fuzzy logic provides a way of not ignoring imprecision but using it to make better computer systems.
The idea of fuzzy logic has been around for a long time, but applying it in computer systems that can monitor people in real-time had been limited by a lack of processor power and memory required to calculate complex functions. With current systems, the department hopes to make this a reality.
The immediate goals include the development of algorithms for processing data from motion sensors, bed sensors and other passive sensors in the home. Further down the line, the team will investigate correlations between sensor data collected in the home and pertinent health events or trends in the medical records.
The group will also study the reaction of older adults to the sensor network, including privacy issues related to the monitoring, and will develop a secure web interface for displaying the sensor data as well as a smart carpet for recognising falls.