Classifying Diverse Physical Activities Using “Smart Garments”

Physical activities can have important impacts on human health. For example, a physically active lifestyle, which is one of the most important goals for overall health promotion, can diminish the risk for a range of physical disorders, as well as reducing health-related expenditures. Thus, a long-term goal is to detect different physical activities, and an important initial step toward this goal is the ability to classify such activities. A recent and promising technology to discriminate among diverse physical activities is the smart textile system (STS), which is becoming increasingly accepted as a low-cost activity monitoring tool for health promotion. Accordingly, our primary aim was to assess the feasibility and accuracy of using a novel STS to classify physical activities. Eleven participants completed a lab-based experiment to evaluate the accuracy of an STS that featured a smart undershirt (SUS) and commercially available smart socks (SSs) in discriminating several basic postures (sitting, standing, and lying down), as well as diverse activities requiring participants to walk and run at different speeds. We trained three classification methods—K-nearest neighbor, linear discriminant analysis, and artificial neural network—using data from each smart garment separately and in combination. Overall classification performance (global accuracy) was ~98%, which suggests that the STS was effective for discriminating diverse physical activities. We conclude that, overall, smart garments represent a promising area of research and a potential alternative for discriminating a range of physical activities, which can have positive implications for health promotion.

Abstract licence: CC BY

1. 4.

   Gait Analysis Methods: An Overview of Wearable and Non-Wearable Systems, Highlighting Clinical Applications · 2014

2. 15.

   Wearable Electronics and Smart Textiles: A Critical Review · 2014

3. 22.

   Optimal Placement of Accelerometers for the Detection of Everyday Activities · 2013

4. 38.

   Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers · 2010

36 more references, whose wording the paper’s licence keeps private.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.