In an age when an increasing number of seniors live by themselves, dogs often provide strong emotional support to those people. Such a strong bond could also be useful for monitoring both the dog’s and its owner’s well-being, according to new research conducted by scientists at Newcastle University. They've developed a sensor to monitor the dog’s movements at home and out of the house.
The research is being led by Dr. Cas Ladha from the university’s Culture Lab, PhD student Nils Hammerla and undergraduate Emma Hughes. The premise of their research is that changes in behavior patterns of the dog, such as the amount of food they are eating, and the length and regularity of their walks, could quickly signal variations in the well-being of their elderly owner.
UPGRADE TO NEW ATLAS PLUS
More than 1,200 New Atlas Plus subscribers directly support our journalism, and get access to our premium ad-free site and email newsletter. Join them for just US$19 a year.UPGRADE
To detect those changes, the team created a waterproof collar-based sensor featuring an accelerometer and micro-controller. It was adapted to different dog sizes in order to include as many breeds as possible, and is protected in a polycarbonate casing.
“In order to set the benchmark we needed to determine which movements correlated to particular behaviors, so in the initial studies, as well as the collars, we also set up cameras to record their behavior,” Ladha says in a press release.
During the analysis of the data collected, the research team classified dog activities into 17 categories that included barking, chewing, drinking, sniffing and several others. The team also assessed the system against different breeds.
"This is just the first step, but the idea behind this research is that it would allow us to discreetly support people without the need for cameras,” says Ladha. Since 30 percent of UK households have at least one pet dog, the research could indeed lead to a new, discrete way of caring for the elderly as well as their four-legged friends.
Details of the research were presented at the 2013 UbiComp conference in Zurich, which took place between September 8 and 12.
Source: Newcastle University