Researchers from Northwestern Medicine and Northwestern Rehabilitation Institute of Chicago (RIC) have developed a way to identify whether activity trackers are being used fraudulently by their wearers.
A growing number of healthcare providers and insurance companies use activity trackers on phones, watches and bracelets, to reward individuals who maintain healthy lifestyles. However, many users have learned methods to ‘trick’ their devices into registering activity, such as shaking their phone while they were actually sitting down
By training devices to recognize normal versus deceptive activity the researchers increased the accuracy of the device to identify genuine activity from 38% to 84%. The technology is also perceptive. Once it recognizes the deceptive behavior, it can track similar behaviors in other individuals. The study included 14 subjects and used a variety of deception techniques (ie, fake walking when they were actually sitting). The test was carried out six times which allowed for the technology to build upon its recognition data.
“Very few studies have tried to make activity tracking recognition robust against cheating,” said senior author Konrad Kording, a research scientist at RIC. “This technology could have broad implications for companies that make activity trackers and insurance companies alike as they seek to more reliably record movement.”
For more information visit PLOS One.