Automatic car driving detection using raw accelerometry data

Abstract

Measuring physical activity using wearable devices has become increasingly popular. Raw data collected from such devices is usually summarized as “activity counts”, which combine information of human activity with environmental vibrations. Driving is a major sedentary activity that artificially increases the activity counts due to various car and body vibrations that are not connected to human movement. Thus, it has become increasingly important to identify periods of driving and quantify the bias induced by driving in activity counts. To address these problems, we propose a Detection Algorithm of Driving via Accelerometry (DADA), designed to detect time periods when an individual is driving a car. DADA is based on detection of vibrations generated by a moving vehicle and recorded by an accelerometer. The methodological approach is based on short-time Fourier transform (STFT) applied to the raw accelerometry data and identifies and focuses on frequency vibration ranges that are specific to car driving. We test the performance of DADA on data collected using wrist-worn ActiGraph devices in a controlled experiment conducted on 24 subjects. The median area under the receiver-operating characteristic curve (AUC) for predicting driving periods was 0.94, indicating an excellent performance of the algorithm. We also quantify the size of the bias induced by driving and obtain that per unit of time the activity counts generated by driving are, on average, 16% of the average activity counts generated during walking.

Classification of human physical activity based on the raw accelerometry data via spherical coordinate transformation

“…The first set uses the aggregated signal to provide different measures of the energy expenditure, physical activity volume or its intensity (see: Bai et al (2016); van Hees et al (2013); ). The second set, which our work expands on, provides classification techniques for the human activity modes (see: Pober et al (2006); Mannini et al (2013); Krause et al (2003); Staudenmayer et al (2009) ;Trost et al (2012); Zhang et al (2012); Xiao et al (2015); Urbanek et al (2015); Straczkiewicz et al (2016)).…”

“…The procedure classified 5 activity types: standing, lying, walking, upper body activities and getting up from a chair. Urbanek et al (2015) and Straczkiewicz et al (2016) proposed methods based on short-time Fourier transformation to detect sustained harmonic walking and the identification of car driving periods in human activity, respectively. Each of the methods mentioned above have different limitations.…”

“…These are important activities for comparative analysis of different methods of rehabilitation. Other techniques (Zhang et al (2012); Mannini et al (2013); Urbanek et al (2015); Straczkiewicz et al (2016)) transform data into the frequency domain and use the dominant frequencies for classification. Such features, in order to be useful, require systematic and periodic repetition of activity which is not common in everyday life.…”

“…Such features, in order to be useful, require systematic and periodic repetition of activity which is not common in everyday life. An example where such approach is beneficial one can find in Straczkiewicz et al (2016); Urbanek et al (2015). In the first paper the authors utilize periodicity in signal which is generated by car vibrations.…”

“…This feature is defined by the device manufactures based on a proprietary algorithm. Other published work, which uses the raw accelerometry data, often works exclusively with the statistics constructed from the acceleration vector magnitude (r = x 2 + y 2 + z 2 ; radius) and neglects the angular information (Zhang et al (2012); Mannini et al (2013); Urbanek et al (2015); Straczkiewicz et al (2016)). These approaches rely on the rotational independence of the activity counts and the vector length, which enables the signal comparisons for different devices and participants.…”