19
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: not found
      • Article: not found

      Automatic identification of physical activity types and sedentary behaviors from triaxial accelerometer: laboratory-based calibrations are not enough

      Read this article at

      ScienceOpenPublisherPubMed
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          "Objective" methods to monitor physical activity and sedentary patterns in free-living conditions are necessary to further our understanding of their impacts on health. In recent years, many software solutions capable of automatically identifying activity types from portable accelerometry data have been developed, with promising results in controlled conditions, but virtually no reports on field tests. An automatic classification algorithm initially developed using laboratory-acquired data (59 subjects engaging in a set of 24 standardized activities) to discriminate between 8 activity classes (lying, slouching, sitting, standing, walking, running, and cycling) was applied to data collected in the field. Twenty volunteers equipped with a hip-worn triaxial accelerometer performed at their own pace an activity set that included, among others, activities such as walking the streets, running, cycling, and taking the bus. Performances of the laboratory-calibrated classification algorithm were compared with those of an alternative version of the same model including field-collected data in the learning set. Despite good results in laboratory conditions, the performances of the laboratory-calibrated algorithm (assessed by confusion matrices) decreased for several activities when applied to free-living data. Recalibrating the algorithm with data closer to real-life conditions and from an independent group of subjects proved useful, especially for the detection of sedentary behaviors while in transports, thereby improving the detection of overall sitting (sensitivity: laboratory model = 24.9%; recalibrated model = 95.7%). Automatic identification methods should be developed using data acquired in free-living conditions rather than data from standardized laboratory activity sets only, and their limits carefully tested before they are used in field studies.

          Related collections

          Most cited references24

          • Record: found
          • Abstract: found
          • Article: found
          Is Open Access

          Objective vs. Self-Reported Physical Activity and Sedentary Time: Effects of Measurement Method on Relationships with Risk Biomarkers

          Purpose Imprecise measurement of physical activity variables might attenuate estimates of the beneficial effects of activity on health-related outcomes. We aimed to compare the cardiometabolic risk factor dose-response relationships for physical activity and sedentary behaviour between accelerometer- and questionnaire-based activity measures. Methods Physical activity and sedentary behaviour were assessed in 317 adults by 7-day accelerometry and International Physical Activity Questionnaire (IPAQ). Fasting blood was taken to determine insulin, glucose, triglyceride and total, LDL and HDL cholesterol concentrations and homeostasis model-estimated insulin resistance (HOMAIR). Waist circumference, BMI, body fat percentage and blood pressure were also measured. Results For both accelerometer-derived sedentary time ( 50% lower for the IPAQ-reported compared to the accelerometer-derived measure (p<0.0001 for both interactions). The relationships for moderate-to-vigorous physical activity (MVPA) and risk factors were less strong than those observed for sedentary behaviours, but significant negative relationships were observed for both accelerometer and IPAQ MVPA measures with glucose, and insulin and HOMAIR values (all p<0.05). For accelerometer-derived MVPA only, additional negative relationships were seen with triglyceride, total cholesterol and LDL cholesterol concentrations, BMI, waist circumference and percentage body fat, and a positive relationship was evident with HDL cholesterol (p = 0.0002). Regression coefficients for HOMAIR, insulin and triglyceride were 43–50% lower for the IPAQ-reported compared to the accelerometer-derived MVPA measure (all p≤0.01). Conclusion Using the IPAQ to determine sitting time and MVPA reveals some, but not all, relationships between these activity measures and metabolic and vascular disease risk factors. Using this self-report method to quantify activity can therefore underestimate the strength of some relationships with risk factors.
            Bookmark
            • Record: found
            • Abstract: not found
            • Book Chapter: not found

            Activity Recognition from User-Annotated Acceleration Data

              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Activity identification using body-mounted sensors--a review of classification techniques.

              With the advent of miniaturized sensing technology, which can be body-worn, it is now possible to collect and store data on different aspects of human movement under the conditions of free living. This technology has the potential to be used in automated activity profiling systems which produce a continuous record of activity patterns over extended periods of time. Such activity profiling systems are dependent on classification algorithms which can effectively interpret body-worn sensor data and identify different activities. This article reviews the different techniques which have been used to classify normal activities and/or identify falls from body-worn sensor data. The review is structured according to the different analytical techniques and illustrates the variety of approaches which have previously been applied in this field. Although significant progress has been made in this important area, there is still significant scope for further work, particularly in the application of advanced classification techniques to problems involving many different activities.
                Bookmark

                Author and article information

                Journal
                Journal of Applied Physiology
                Journal of Applied Physiology
                American Physiological Society
                8750-7587
                1522-1601
                March 15 2015
                March 15 2015
                : 118
                : 6
                : 716-722
                Affiliations
                [1 ]CarMeN INSERM U1060, University of Lyon 1, INRA U1235, Centre de Recherche en Nutrition Humaine Rhône-Alpes, Centre Européen pour la Nutrition &amp; la Santé, Pierre-Bénite, France;
                [2 ]University of Grenoble Alpes, Grenoble, France;
                [3 ]Commissariat à l'Énergie Atomique, Leti, Département Microtechnologies pour la Biologie et la Santé, Laboratoire Électronique et Systèmes pour la Santé, MINATEC, Grenoble, France;
                [4 ]Movea, Grenoble, France;
                [5 ]Hubert Curien Pluridisciplinary Institute, Department of Ecology, Physiology and Ethology, University of Strasbourg, UMR CNRS 7178, Strasbourg, France; and
                [6 ]Service d'Endocrinologie, Diabètes, Nutrition, Centre Hospitalier Lyon Sud, Pierre-Bénite, France
                Article
                10.1152/japplphysiol.01189.2013
                25593289
                57efb8bf-8316-4219-b2ef-090a2e862ee5
                © 2015
                History

                Comments

                Comment on this article