Activity classification based on inertial and barometric pressure sensors at different anatomical locations

作者：Moncada Torres A; Leuenberger K; Gonzenbach R; Luft A; Gassert R^*

来源：Physiological Measurement, 2014, 35(7): 1245-1263.

DOI：10.1088/0967-3334/35/7/1245

• accelerometers
• inertial measurement unit
• wearable sensors
• machine learning
• activities of daily living
• stair ascent
• stair descent

Miniature, wearable sensor modules are a promising technology to monitor activities of daily living (ADL) over extended periods of time. To assure both user compliance and meaningful results, the selection and placement site of sensors requires careful consideration. We investigated these aspects for the classification of 16 ADL in 6 healthy subjects under laboratory conditions using ReSense, our custom-made inertial measurement unit enhanced with a barometric pressure sensor used to capture activity-related altitude changes. Subjects wore a module on each wrist and ankle, and one on the trunk. Activities comprised whole body movements as well as gross and dextrous upper-limb activities. Wrist-module data outperformed the other locations for the three activity groups. Specifically, overall classification accuracy rates of almost 93% and more than 95% were achieved for the repeated holdout and user-specific validation methods, respectively, for all 16 activities. Including the altitude profile resulted in a considerable improvement of up to 20% in the classification accuracy for stair ascent and descent. The gyroscopes provided no useful information for activity classification under this scheme. The proposed sensor setting could allow for robust long-term activity monitoring with high compliance in different patient populations.

• 出版日期2014-7