Next Article in Journal
Recent Progress in Lab-On-a-Chip Systems for the Monitoring of Metabolites for Mammalian and Microbial Cell Research
Next Article in Special Issue
Application of Fuzzy Logic for Selection of Actor Nodes in WSANs —Implementation of Two Fuzzy-Based Systems and a Testbed
Previous Article in Journal
Tracking Multiple Marine Ships via Multiple Sensors with Unknown Backgrounds
Previous Article in Special Issue
MIGOU: A Low-Power Experimental Platform with Programmable Logic Resources and Software-Defined Radio Capabilities
Article

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

1
Department of Computer Science and Software Engineering, Concordia University, Montreal, QC H3G 1M8, Canada
2
Research and Development Department, Motsai Research, Saint Bruno, QC J3V 6B7, Canada
*
Author to whom correspondence should be addressed.
Sensors 2019, 19(22), 5026; https://doi.org/10.3390/s19225026
Received: 1 October 2019 / Revised: 12 November 2019 / Accepted: 13 November 2019 / Published: 18 November 2019
(This article belongs to the Special Issue Mobile Sensing: Platforms, Technologies and Challenges)
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. View Full-Text
Keywords: activity recognition; inertial sensors; supervised classification activity recognition; inertial sensors; supervised classification
Show Figures

Figure 1

MDPI and ACS Style

Dehghani, A.; Sarbishei, O.; Glatard, T.; Shihab, E. A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors. Sensors 2019, 19, 5026. https://doi.org/10.3390/s19225026

AMA Style

Dehghani A, Sarbishei O, Glatard T, Shihab E. A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors. Sensors. 2019; 19(22):5026. https://doi.org/10.3390/s19225026

Chicago/Turabian Style

Dehghani, Akbar, Omid Sarbishei, Tristan Glatard, and Emad Shihab. 2019. "A Quantitative Comparison of Overlapping and Non-Overlapping Sliding Windows for Human Activity Recognition Using Inertial Sensors" Sensors 19, no. 22: 5026. https://doi.org/10.3390/s19225026

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop