Browsing by Subject "Wearable computing"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Prediction of sustained harmonic walking in the free-living environment using raw accelerometry data
    (IOP Publishing, 2018-02-28) Urbanek, Jacek K.; Zipunnikov, Vadim; Harris, Tamara; Fadel, William; Glynn, Nancy; Koster, Annemarie; Caserotti, Paolo; Crainiceanu, Ciprian; Harezlak, Jaroslaw; Biostatistics, School of Public Health
    OBJECTIVE: Using raw, sub-second-level accelerometry data, we propose and validate a method for identifying and characterizing walking in the free-living environment. We focus on sustained harmonic walking (SHW), which we define as walking for at least 10 s with low variability of step frequency. APPROACH: We utilize the harmonic nature of SHW and quantify the local periodicity of the tri-axial raw accelerometry data. We also estimate the fundamental frequency of the observed signals and link it to the instantaneous walking (step-to-step) frequency (IWF). Next, we report the total time spent in SHW, number and durations of SHW bouts, time of the day when SHW occurred, and IWF for 49 healthy, elderly individuals. MAIN RESULTS: The sensitivity of the proposed classification method was found to be 97%, while specificity ranged between 87% and 97% and the prediction accuracy ranged between 94% and 97%. We report the total time in SHW between 140 and 10 min d-1 distributed between 340 and 50 bouts. We estimate the average IWF to be 1.7 steps-per-second. SIGNIFICANCE: We propose a simple approach for the detection of SHW and estimation of IWF, based on Fourier decomposition.
  • Thumbnail Image
    Item
    Stride variability measures derived from wrist- and hip-worn accelerometers
    (Elsevier, 2017-02) Urbanek, Jacek K.; Harezlak, Jaroslaw; Glynn, Nancy W.; Harris, Tamara; Crainiceanu, Ciprian; Zipunnikov, Vadim; Biostatistics, School of Public Health
    Many epidemiological and clinical studies use accelerometry to objectively measure physical activity using the activity counts, vector magnitude, or number of steps. These measures use just a fraction of the information in the raw accelerometry data as they are typically summarized at the minute level. To address this problem, we define and estimate two measures of temporal stride-to-stride gait variability based on raw accelerometry data: Amplitude Deviation (AD) and Phase Deviation (PD). We explore the sensitivity of our approach to on-body placement of the accelerometer by comparing hip, left and right wrist placements. We illustrate the approach by estimating AD and PD in 46 elderly participants in the Developmental Epidemiologic Cohort Study (DECOS) who worn accelerometers during a 400m walk test. We also show that AD and PD have a statistically significant association with the gait speed and sit-to-stand test performance.