Researchers at the U.K.'s Lancaster University and the University of Bath analyzed smartphone data from 780 people and found that the time a person spends on different apps can help identify them in a larger group. Researchers fed 4,680 days of app usage data, with each day paired with one of the 780 users, into statistical models so they could learn their daily app use patterns.
"Our models, which were trained on only six days of app usage data per person, could identify the correct person from a day of anonymous data one third of the time," said Bath's David Ellis.
From Lancaster University
View Full Article
Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA