Next Article in Journal
Driving-Induced Neurological Biomarkers in an Advanced Driver-Assistance System
Previous Article in Journal
Sky and Ground Segmentation in the Navigation Visions of the Planetary Rovers
Previous Article in Special Issue
Using Social Signals to Predict Shoplifting: A Transparent Approach to a Sensitive Activity Analysis Problem
Article

Human Activity Recognition: A Comparative Study to Assess the Contribution Level of Accelerometer, ECG, and PPG Signals

Department of Computer Science and Software Engineering, Concordia University, Montreal, QC H3G 1M8, Canada
*
Author to whom correspondence should be addressed.
Academic Editors: Alain Pegatoquet and Benoît Miramond
Sensors 2021, 21(21), 6997; https://doi.org/10.3390/s21216997
Received: 12 August 2021 / Revised: 1 October 2021 / Accepted: 14 October 2021 / Published: 21 October 2021
Inertial sensors are widely used in the field of human activity recognition (HAR), since this source of information is the most informative time series among non-visual datasets. HAR researchers are actively exploring other approaches and different sources of signals to improve the performance of HAR systems. In this study, we investigate the impact of combining bio-signals with a dataset acquired from inertial sensors on recognizing human daily activities. To achieve this aim, we used the PPG-DaLiA dataset consisting of 3D-accelerometer (3D-ACC), electrocardiogram (ECG), photoplethysmogram (PPG) signals acquired from 15 individuals while performing daily activities. We extracted hand-crafted time and frequency domain features, then, we applied a correlation-based feature selection approach to reduce the feature-set dimensionality. After introducing early fusion scenarios, we trained and tested random forest models with subject-dependent and subject-independent setups. Our results indicate that combining features extracted from the 3D-ACC signal with the ECG signal improves the classifier’s performance F1-scores by 2.72% and 3.00% (from 94.07% to 96.80%, and 83.16% to 86.17%) for subject-dependent and subject-independent approaches, respectively. View Full-Text
Keywords: human activity recognition (HAR); early fusion; 3D-accelerometer (3D-ACC); electrocardiogram (ECG); photoplethysmogram (PPG) human activity recognition (HAR); early fusion; 3D-accelerometer (3D-ACC); electrocardiogram (ECG); photoplethysmogram (PPG)
Show Figures

Figure 1

MDPI and ACS Style

Afzali Arani, M.S.; Costa, D.E.; Shihab, E. Human Activity Recognition: A Comparative Study to Assess the Contribution Level of Accelerometer, ECG, and PPG Signals. Sensors 2021, 21, 6997. https://doi.org/10.3390/s21216997

AMA Style

Afzali Arani MS, Costa DE, Shihab E. Human Activity Recognition: A Comparative Study to Assess the Contribution Level of Accelerometer, ECG, and PPG Signals. Sensors. 2021; 21(21):6997. https://doi.org/10.3390/s21216997

Chicago/Turabian Style

Afzali Arani, Mahsa S., Diego E. Costa, and Emad Shihab. 2021. "Human Activity Recognition: A Comparative Study to Assess the Contribution Level of Accelerometer, ECG, and PPG Signals" Sensors 21, no. 21: 6997. https://doi.org/10.3390/s21216997

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