Key result
Classification of human activity using wrist PPG data via an ensemble method achieved a test accuracy of 88.91%, compared to 94.28% for ECG data.
Why the study?
PPG is cheaper and widely available in smart devices compared to ECG, making it a desired alternative for human activity recognition despite being more prone to disturbance and artifacts.
Absolute Event Rate: 88.91% vs 94.28%
Wrist PPG combined with ensemble machine learning models provides a promising, widely available alternative to ECG for human activity recognition, achieving nearly 89% accuracy.
May support wearable PPG for activity monitoring; leaves open prospective validation in clinical cohorts.
Human activity recognition via Electrocardiography (ECG) and Photoplethysmography (PPG) is extensively researched. While ECG requires less filtering and is less prone to disturbance and artifacts, nonetheless, PPG is cheaper and widely available in smart devices, making it a desired alternative. In this study, we explore the employment of the ensemble method with several pre-trained machine learning models namely Resnet50V2, MobileNetV2, and Xception for the classification of wrist PPG data of human activity, in comparison to its ECG counterpart. The study produced promising results with a test classification accuracy of 88.91% and 94.28% for PPG and ECG, respectively.
No takes yet. Share an insight, caveat, or question.
Almanifi et al. (2022) studied Human activity recognition. Ensemble method with pre-trained machine learning models using wrist PPG data vs. ECG data was evaluated on Test classification accuracy. Classification of human activity using wrist PPG data via an ensemble method achieved a test accuracy of 88.91%, compared to 94.28% for ECG data.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: