Activity Recognition with Wearable Sensors on Loose Clothing

This research (DOI:10.1371/journal.pone.0184642) investigates if motion artefacts inherent in fabric-based sensing systems (e-textiles), can be exploited as an additional source of information in statistical classification tasks. The findings in the corresponding paper suggest that these artefacts can, in fact, be used to distinguish between similar motions, by exploiting additional information provided by the fabric motion. An experimental study is presented whereby factors of both the motion and the properties of the fabric are analysed in the context of motion similarity. The dataset here contains 2-axis acceleration readings from sensorised fabric during a motion task. For more information please see the readme file in the dataset.

Related Publication Michael, Brendan and Howard, Matthew, "Activity Recognition with Wearable Sensors on Loose Clothing", PLoS One, 2017, Accepted (DOI:10.1371/journal.pone.0184642)