Activity classification based on inertial and barometric pressure sensors at different anatomical locations
| Autor: | Kaspar Leuenberger, Roman Gonzenbach, Arturo Moncada-Torres, Roger Gassert, Andreas R. Luft |
|---|---|
| Přispěvatelé: | University of Zurich, Gassert, R |
| Rok vydání: | 2014 |
| Předmět: |
Male
Engineering Physiology Biomedical Engineering Biophysics Wearable computer 2204 Biomedical Engineering Monitoring Ambulatory 610 Medicine & health Motor Activity Accelerometer law.invention Altitude 2737 Physiology (medical) Inertial measurement unit law Physiology (medical) Machine learning Accelerometry Activities of Daily Living medicine Pressure Humans Simulation business.industry Torso Gyroscope Signal Processing Computer-Assisted 1314 Physiology Middle Aged Wrist Trunk Pressure sensor 10040 Clinic for Neurology Stair descent medicine.anatomical_structure Stair ascent Atmospheric Pressure Wearable sensors Female Accelerometers Ankle business Activities of daily living 1304 Biophysics |
| Zdroj: | Physiological Measurement, 35 (7) |
| ISSN: | 1361-6579 0967-3334 |
| Popis: | 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. Physiological Measurement, 35 (7) ISSN:0967-3334 ISSN:1361-6579 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|