Next Article in Journal
Collective Memory: Transposing Pavlov’s Experiment to Robot Swarms
Next Article in Special Issue
A Heterogeneous Learning Framework for Over-the-Top Consumer Analysis Reflecting the Actual Market Environment
Previous Article in Journal
Rapid Nondestructive Postharvest Potato Freshness and Cultivar Discrimination Assessment
Article

Dynamic Segmentation for Physical Activity Recognition Using a Single Wearable Sensor

College of Computer and Information Sciences, King Saud University, Riyadh 11584, Saudi Arabia
*
Author to whom correspondence should be addressed.
Academic Editor: Grzegorz Dudek
Appl. Sci. 2021, 11(6), 2633; https://doi.org/10.3390/app11062633
Received: 24 February 2021 / Revised: 10 March 2021 / Accepted: 12 March 2021 / Published: 16 March 2021
(This article belongs to the Special Issue Applied Machine Learning Ⅱ)
Data segmentation is an essential process in activity recognition when using machine learning techniques. Previous studies on physical activity recognition have mostly relied on the sliding window approach for segmentation. However, choosing a fixed window size for multiple activities with different durations may affect recognition accuracy, especially when the activities belong to the same category (i.e., dynamic or static). This paper presents and verifies a new method for dynamic segmentation of physical activities performed during the rehabilitation of individuals with spinal cord injuries. To adaptively segment the raw data, signal characteristics are analyzed to determine the suitable type of boundaries. Then, the algorithm identifies the time boundaries to represent the start- and endpoints of each activity. To verify the method and build a predictive model, an experiment was conducted in which data were collected using a single wrist-worn accelerometer sensor. The experimental results were compared with the sliding window approach, indicating that the proposed method outperformed the sliding window approach in terms of overall accuracy, which exceeded 5%, as well as model robustness. The results also demonstrated efficient physical activity segmentation using the proposed method, resulting in high classification performance for all activities considered. View Full-Text
Keywords: activity recognition; machine learning; wearable sensors; spinal cord injury; telerehabilitation activity recognition; machine learning; wearable sensors; spinal cord injury; telerehabilitation
Show Figures

Figure 1

MDPI and ACS Style

Alhammad, N.; Al-Dossari, H. Dynamic Segmentation for Physical Activity Recognition Using a Single Wearable Sensor. Appl. Sci. 2021, 11, 2633. https://doi.org/10.3390/app11062633

AMA Style

Alhammad N, Al-Dossari H. Dynamic Segmentation for Physical Activity Recognition Using a Single Wearable Sensor. Applied Sciences. 2021; 11(6):2633. https://doi.org/10.3390/app11062633

Chicago/Turabian Style

Alhammad, Nora, and Hmood Al-Dossari. 2021. "Dynamic Segmentation for Physical Activity Recognition Using a Single Wearable Sensor" Applied Sciences 11, no. 6: 2633. https://doi.org/10.3390/app11062633

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