Statistical Analysis of Window Sizes and Sampling Rates in Human Activity Recognition

Anzah H. Niazi, Delaram Yazdansepas, Jennifer L. Gay, Frederick W. Maier, Lakshmish Ramaswamy, Khaled Rasheed, Matthew Buman

2017

Abstract

Accelerometers are the most common device for data collection in the field of Human Activity Recognition (HAR). This data is recorded at a particular sampling rate and then usually separated into time windows before classification takes place. Though the sampling rate and window size can have a significant impact on the accuracy of the trained classifier, there has been relatively little research on their role in activity recognition. This paper presents a statistical analysis on the effect the sampling rate and window sizes on HAR data classification. The raw data used in the analysis was collected from a hip-worn Actigraphy G3X+ at 100Hz from 77 subjects performing 23 different activities. It was then re-sampled and divided into windows of varying sizes and trained using a single data classifier. A weighted least squares linear regression model was developed and two-way factorial ANOVA was used to analyze the effects of sampling rate and window size for different activity types and demographic categories. Based upon this analysis, we find that 10-second windows recorded at 50Hz perform statistically better than other combinations of window size and sampling rate.

References

  1. ActiGraph. Actisoft analysis software 3.2 user's manual. fort walton beach, fl: Mti health services.
  2. Banos, O., Galvez, J.-M., Miguel Damas, H. P., and Rojas, I. (2014). Window size impact in human activity recognition. Sensors, pages 6474-6499.
  3. Beiber, G., Voskamp, J., and Urban, B. (2009). Activity recognition for everyday life on mobile phones. International Conference on Universal Access in HumanComputer Interaction, pages 289-296.
  4. Demsar, J. (2006). Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research, 7:1-30.
  5. Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., and Witten, I. H. (2009). The WEKA data mining software: an update. SIGKDD Explor. Newsl., 11(1):10-18.
  6. Lara, O. D. and Labrador, M. A. (2013). A survey on human activity recognition using wearable sensors. IEEE Communication Surveys and Tutorials, 15:1192-1209.
  7. Lau, S. and David, K. (2010). Movement recognition using the accelerometer in smartphones. IEEE Future Network ands Mobile Summit 2010, pages 1-9.
  8. Maurer, U., Smailagic, A., Siewiorek, D. P., and Deisher, M. (2006). Activity recognition and monitoring using multiple sensors on different body position. International Workshop on Wearable and Implantable Body Sensor Networks.
  9. Niazi, A., Yazdensepas, D., Gay, J., Maier, F., Rasheed, K., Ramaswamy, L., and Buman, M. (2016). A hierarchical meta-classifier for human activity recognition. IEEE International Conference on Machine Learning and Applications.
  10. Preece, S. J., Goulermas, J. Y., Kenney, L. P. J., Howard, D., Meijer, K., and Crompton, R. (2009). Activity identification using body-mounted sensorsa review of classification techniques. Physiological Measurement, 30(4):R1.
  11. RStudio Team (2015). RStudio: Integrated Development Environment for R. RStudio, Inc., Boston, MA.
  12. Tapia, E., Intille, S., Haskell, W., Larson, K., Wright, J., King, A., and Friedman, R. (2007). Real-time recognition of physical activities and their intensities using wireless accelerometers and a heart rate monitor. IEEE 11th IEEE international symposium on wearable computers, pages 37-40.
  13. Yazdansepas, D., Niazi, A. H., Gay, J. L., Maier, F. W., Ramaswamy, L., Rasheed, K., and Buman, M. P. (2016). A multi-featured approach for wearable sensor-based human activity recognition. IEEE International Conference on Healthcare Informatics (ICHI), Chicago, IL.
Download


Paper Citation


in Harvard Style

Niazi A., Yazdansepas D., Gay J., Maier F., Ramaswamy L., Rasheed K. and Buman M. (2017). Statistical Analysis of Window Sizes and Sampling Rates in Human Activity Recognition . In Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: HEALTHINF, (BIOSTEC 2017) ISBN 978-989-758-213-4, pages 319-325. DOI: 10.5220/0006148503190325


in Bibtex Style

@conference{healthinf17,
author={Anzah H. Niazi and Delaram Yazdansepas and Jennifer L. Gay and Frederick W. Maier and Lakshmish Ramaswamy and Khaled Rasheed and Matthew Buman},
title={Statistical Analysis of Window Sizes and Sampling Rates in Human Activity Recognition},
booktitle={Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: HEALTHINF, (BIOSTEC 2017)},
year={2017},
pages={319-325},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006148503190325},
isbn={978-989-758-213-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: HEALTHINF, (BIOSTEC 2017)
TI - Statistical Analysis of Window Sizes and Sampling Rates in Human Activity Recognition
SN - 978-989-758-213-4
AU - Niazi A.
AU - Yazdansepas D.
AU - Gay J.
AU - Maier F.
AU - Ramaswamy L.
AU - Rasheed K.
AU - Buman M.
PY - 2017
SP - 319
EP - 325
DO - 10.5220/0006148503190325