A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors

Akbar Dehghani; Omid Sarbishei; Tristan Glatard; Emad Shihab

doi:10.3390/s19225026

journal article Open Access Nov 18, 2019

A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors

Akbar Dehghani Omid Sarbishei

Tristan Glatard

Emad Shihab

Sensors Vol. 19 No. 22 pp. 5026 · MDPI AG

View at Publisher Save 10.3390/s19225026

Abstract

The sliding window technique is widely used to segment inertial sensor signals, i.e., accelerometers and gyroscopes, for activity recognition. In this technique, the sensor signals are partitioned into fix sized time windows which can be of two types: (1) non-overlapping windows, in which time windows do not intersect, and (2) overlapping windows, in which they do. There is a generalized idea about the positive impact of using overlapping sliding windows on the performance of recognition systems in Human Activity Recognition. In this paper, we analyze the impact of overlapping sliding windows on the performance of Human Activity Recognition systems with different evaluation techniques, namely, subject-dependent cross validation and subject-independent cross validation. Our results show that the performance improvements regarding overlapping windowing reported in the literature seem to be associated with the underlying limitations of subject-dependent cross validation. Furthermore, we do not observe any performance gain from the use of such technique in conjunction with subject-independent cross validation. We conclude that when using subject-independent cross validation, non-overlapping sliding windows reach the same performance as sliding windows. This result has significant implications on the resource usage for training the human activity recognition systems.

Topics

No keywords indexed for this article. Browse by subject →

References

29

[1]

Bianchi "Barometric pressure and triaxial accelerometry-based falls event detection" IEEE Trans. Neural Syst. Rehabil. Eng. (2010) 10.1109/tnsre.2010.2070807

[2]

Chen "Implementing technology-based embedded assessment in the home and community life of individuals aging with disabilities: A participatory research and development study" Disabil. Rehabil. Assist. Technol. (2014) 10.3109/17483107.2013.805824

[3]

Janidarmian, M., Roshan Fekr, A., Radecka, K., and Zilic, Z. (2017). A comprehensive analysis on wearable acceleration sensors in human activity recognition. Sensors, 17. 10.3390/s17030529

[4]

Banos "Window size impact in human activity recognition" Sensors (2014) 10.3390/s140406474

[5]

A Survey on Human Activity Recognition using Wearable Sensors

Oscar D. Lara, Miguel A. Labrador

IEEE Communications Surveys & Tutorials 2013 10.1109/surv.2012.110112.00192

[6]

Bao, L., and Intille, S.S. (2004, January 21–23). Activity recognition from user-annotated acceleration data. Proceedings of the International Conference on Pervasive Computing, Linz and Vienna, Austria. 10.1007/978-3-540-24646-6_1

[7]

Tapia, E.M., Intille, S.S., Haskell, W., Larson, K., Wright, J., King, A., and Friedman, R. (2007, January 11–13). Real-time recognition of physical activities and their intensities using wireless accelerometers and a heart monitor. Proceedings of the 2007 11th IEEE International Symposium on Wearable Computers 2007, Boston, MA, USA. 10.1109/iswc.2007.4373774

[8]

Lara "Centinela: A human activity recognition system based on acceleration and vital sign data" Pervasive Mob. Comput. (2012) 10.1016/j.pmcj.2011.06.004

[9]

Morris, D., Saponas, T.S., Guillory, A., and Kelner, I. (May, January 26). RecoFit: Using a wearable sensor to find, recognize, and count repetitive exercises. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Toronto, ON, Canada.

[10]

Minnen, D., Westeyn, T., Ashbrook, D., Presti, P., and Starner, T. (2007, January 26–28). Recognizing soldier activities in the field. Proceedings of the 4th International Workshop on Wearable and Implantable Body Sensor Networks (BSN 2007), Aachen, Germany. 10.1007/978-3-540-70994-7_40

[11]

Reddy "Using mobile phones to determine transportation modes" ACM Trans. Sens. Networks (TOSN) (2010)

[12]

Cheng, J., Amft, O., and Lukowicz, P. (2010, January 17–20). Active capacitive sensing: Exploring a new wearable sensing modality for activity recognition. Proceedings of the International Conference on Pervasive Computing, Helsinki, Finland. 10.1007/978-3-642-12654-3_19

[13]

(2019, November 16). BioHarness™ BT Chest Sensor Strap. Available online: http://www.zephyr-technology.com/bioharness-bt.html.

[14]

(2019, November 16). GitHub Repository. Available online: http://www.github.com/big-data-lab-team/paper-generalizability-window-size.

[15]

Bulling "A tutorial on human activity recognition using body-worn inertial sensors" ACM Comput. Surv. (CSUR) (2014) 10.1145/2499621

[16]

Baños, O., Damas, M., Pomares, H., Rojas, I., Tóth, M.A., and Amft, O. (2012, January 5–8). A benchmark dataset to evaluate sensor displacement in activity recognition. Proceedings of the 2012 ACM Conference on Ubiquitous Computing, Pittsburgh, PA, USA. 10.1145/2370216.2370437

[17]

A survey of cross-validation procedures for model selection

Sylvain Arlot, Alain Celisse

Statistics Surveys 2010 10.1214/09-ss054

[18]

Selles "Automated estimation of initial and terminal contact timing using accelerometers; development and validation in transtibial amputees and controls" IEEE Trans. Neural Syst. Rehabil. Eng. (2005) 10.1109/tnsre.2004.843176

[19]

Najafi "Ambulatory system for human motion analysis using a kinematic sensor: Monitoring of daily physical activity in the elderly" IEEE Trans. Biomed. Eng. (2003) 10.1109/tbme.2003.812189

[20]

Janidarmian, M., Radecka, K., and Zilic, Z. (2014, January 3–5). Automated diagnosis of knee pathology using sensory data. Proceedings of the 2014 4th International Conference on Wireless Mobile Communication and Healthcare-Transforming Healthcare Through Innovations in Mobile and Wireless Technologies (MOBIHEALTH), Athens, Greece. 10.4108/icst.mobihealth.2014.257526

[21]

Coggeshall, S., and Wu, G. (2019, October 30). Asset Allocation and Long-Term Returns: An Empirical Approach. Available online: https://ssrn.com/abstract=873184.

[22]

The Elements of Statistical Learning

Trevor Hastie, Robert Tibshirani, Jerome Friedman

Springer Series in Statistics 10.1007/978-0-387-84858-7

[23]

Al Machot, F., Elmachot, A., Ali, M., Al Machot, E., and Kyamakya, K. (2019). A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity Sensors. Sensors, 19. 10.3390/s19071659

[24]

Dehghani, A., Glatard, T., and Shihab, E. (2019). Subject Cross Validation in Human Activity Recognition. arXiv.

[25]

(2019, November 16). Xsens. Available online: https://www.xsens.com.

[26]

(2019, November 16). A SparkFun “Razor IMU” Inertial Sensor. Available online: https://www.sparkfun.com.

[27]

Pedregosa "Scikit-learn: Machine learning in Python" J. Mach. Learn. Res. (2011)

[28]

Sarbishei, O. (2019, January 15–18). A platform and methodology enabling real-time motion pattern recognition on low-power smart devices. Proceedings of the 2019 IEEE 5th World Forum on Internet of Things (WF-IoT), Limerick, Ireland. 10.1109/wf-iot.2019.8767219

[29]

Nearest neighbor pattern classification

T. Cover, P. Hart

IEEE Transactions on Information Theory 1967 10.1109/tit.1967.1053964

Cited By

116

Composite human activity recognition utilizing knowledge distillation and sensor fusion focusing on resource constrained microcontrollers

Athar Noor Mohammad Rafee, John Clear · 2026

Expert Systems with Applications

Metrics

116

Citations

29

References

Details

Published: Nov 18, 2019
Vol/Issue: 19(22)
Pages: 5026
License: View

Authors

A

Akbar Dehghani

Department of Computer Science and Software Engineering, Concordia University, Montreal, QC H3G 1M8, Canada

O

Omid Sarbishei

Research and Development Department, Motsai Research, Saint Bruno, QC J3V 6B7, Canada

T

Tristan Glatard

Department of Computer Science and Software Engineering, Concordia University, Montreal, QC H3G 1M8, Canada

E

Emad Shihab

Department of Computer Science and Software Engineering, Concordia University, Montreal, QC H3G 1M8, Canada

Cite This Article

Akbar Dehghani, Omid Sarbishei, Tristan Glatard, et al. (2019). A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors. Sensors, 19(22), 5026. https://doi.org/10.3390/s19225026

A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors

You May Also Like