The accuracy of a simple, low-cost GPS data logger/receiver to study outdoor human walking in view of health and clinical studies

Abstract

Introduction: Accurate and objective measurements of physical activity and lower-extremity function are important in health and disease monitoring, particularly given the current epidemic of chronic diseases and their related functional impairment.

Purpose: The aim of the present study was to determine the accuracy of a handy (lightweight, small, only one stop/start button) and low-cost (∼$75 with its external antenna) Global Positioning System (GPS) data logger/receiver (the DG100) as a tool to study outdoor human walking in perspective of health and clinical research studies. Methods. Healthy subjects performed two experiments that consisted of different prescribed outdoor walking protocols. Experiment 1. We studied the accuracy of the DG100 for detecting bouts of walking and resting. Experiment 2. We studied the accuracy of the DG100 for estimating distances and speeds of walking.

Results: Experiment 1. The performance in the detection of bouts, expressed as the percentage of walking and resting bouts that were correctly detected, was 92.4% [95% Confidence Interval: 90.6-94.3]. Experiment 2. The coefficients of variation [95% Confidence Interval] for the accuracy of estimating the distances and speeds of walking were low: 3.1% [2.9-3.3] and 2.8% [2.6-3.1], respectively.

Conclusion: The DG100 produces acceptable accuracy both in detecting bouts of walking and resting and in estimating distances and speeds of walking during the detected walking bouts. However, before we can confirm that the DG100 can be used to study walking with respect to health and clinical studies, the inter- and intra-DG100 variability should be studied.

Trial registration: ClinicalTrials.gov NCT00485147.

Figure 1. A typical example of GPS processed speed data obtained from a prescribed outdoor walking protocol, both for the DG100 and the GPS60.

The entire PWP is not represented on the graph to simplify the figure. The period represented on the graph lasts ∼24 min (from minute 34.2 to minute 58.3).

Figure 2. Graphical representation for both the DG100 and the GPS60, of the error percentage for time difference between actual and detected bouts according to actual bout time.

Note: concentrations of point near 0% for the DG100 give the impression that there were fewer points, particularly for bouts less than 0.5 min. This was not the case. For instance, there were 65 and 70 bouts of 0.17 min (10 s) for the GPS60 and the DG100, respectivel.