Automatic car driving detection using raw accelerometry data

M. Straczkiewicz, J. K. Urbanek, W. F. Fadel, C. M. Crainiceanu, Jaroslaw Harezlak

Research output: Contribution to journalArticle

5 Citations (Scopus)

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.

Original languageEnglish (US)
Pages (from-to)1757-1769
Number of pages13
JournalPhysiological Measurement
Volume37
Issue number10
DOIs
StatePublished - Sep 21 2016

Fingerprint

Accelerometry
Vibration
Railroad cars
Equipment and Supplies
Fourier Analysis
Wrist
Accelerometers
Human Activities
ROC Curve
Walking
Area Under Curve
Fourier transforms
Experiments

Keywords

  • algorithm
  • driving detection
  • frequency domain
  • overestimation of physical activity
  • raw accelerometry data

ASJC Scopus subject areas

  • Biophysics
  • Physiology
  • Physiology (medical)

Cite this

Straczkiewicz, M., Urbanek, J. K., Fadel, W. F., Crainiceanu, C. M., & Harezlak, J. (2016). Automatic car driving detection using raw accelerometry data. Physiological Measurement, 37(10), 1757-1769. https://doi.org/10.1088/0967-3334/37/10/1757

Automatic car driving detection using raw accelerometry data. / Straczkiewicz, M.; Urbanek, J. K.; Fadel, W. F.; Crainiceanu, C. M.; Harezlak, Jaroslaw.

In: Physiological Measurement, Vol. 37, No. 10, 21.09.2016, p. 1757-1769.

Research output: Contribution to journalArticle

Straczkiewicz, M, Urbanek, JK, Fadel, WF, Crainiceanu, CM & Harezlak, J 2016, 'Automatic car driving detection using raw accelerometry data', Physiological Measurement, vol. 37, no. 10, pp. 1757-1769. https://doi.org/10.1088/0967-3334/37/10/1757
Straczkiewicz, M. ; Urbanek, J. K. ; Fadel, W. F. ; Crainiceanu, C. M. ; Harezlak, Jaroslaw. / Automatic car driving detection using raw accelerometry data. In: Physiological Measurement. 2016 ; Vol. 37, No. 10. pp. 1757-1769.
@article{204f5503cbe845969e66fc4aedf713de,
title = "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.",
keywords = "algorithm, driving detection, frequency domain, overestimation of physical activity, raw accelerometry data",
author = "M. Straczkiewicz and Urbanek, {J. K.} and Fadel, {W. F.} and Crainiceanu, {C. M.} and Jaroslaw Harezlak",
year = "2016",
month = "9",
day = "21",
doi = "10.1088/0967-3334/37/10/1757",
language = "English (US)",
volume = "37",
pages = "1757--1769",
journal = "Physiological Measurement",
issn = "0967-3334",
publisher = "IOP Publishing Ltd.",
number = "10",

}

TY - JOUR

T1 - Automatic car driving detection using raw accelerometry data

AU - Straczkiewicz, M.

AU - Urbanek, J. K.

AU - Fadel, W. F.

AU - Crainiceanu, C. M.

AU - Harezlak, Jaroslaw

PY - 2016/9/21

Y1 - 2016/9/21

N2 - 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.

AB - 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.

KW - algorithm

KW - driving detection

KW - frequency domain

KW - overestimation of physical activity

KW - raw accelerometry data

UR - http://www.scopus.com/inward/record.url?scp=84989809616&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84989809616&partnerID=8YFLogxK

U2 - 10.1088/0967-3334/37/10/1757

DO - 10.1088/0967-3334/37/10/1757

M3 - Article

AN - SCOPUS:84989809616

VL - 37

SP - 1757

EP - 1769

JO - Physiological Measurement

JF - Physiological Measurement

SN - 0967-3334

IS - 10

ER -