A new technique developed by researchers at North Carolina State University (NCSU) could enable wearable health devices to track user physical activity accurately and efficiently. Wearable devices have limited power, but their programs need to know how much data to process when assessing activity and storing that information.
The team set out to find a data signature formula that would enable programs to identify different physical activity. The researchers had graduate students play golf, bike, walk, wave, and sit in a motion-capture lab, and then evaluated the resulting data using taus, or increments, of zero seconds (i.e., one data point), two seconds, four seconds, and so on, all the way up to 40 seconds. The team then experimented with different parameters for classifying activity data into specific profiles.
The researchers say they were able to accurately identify the five relevant activities using a tau of six seconds. "This means we could identify activities and store related data efficiently," says NCSU's Edgar Lobaton. The team is confident their approach will provide the best opportunity to track and record physical activity data in a practical way.
From North Carolina State University
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found