Journal
IEEE SENSORS JOURNAL
Volume 16, Issue 19, Pages 7133-7141Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSEN.2016.2597265
Keywords
Heart rate (HR); photoplethysmography (PPG); motion artifacts (MA); recursive least squares (RLS); nonlinear adaptive filtering; signal decomposition
Funding
- National Natural Science Foundation of China [61501096, 61472067]
- Chengdu Research Institute of UESTC [RWS-CYHKF-02-20150005]
- International Science and Technology Cooperation and Exchange Program of Sichuan Province, China [2016HH0020]
- Fundamental Research Funds for the Central Universities
Ask authors/readers for more resources
Heart rate (HR) estimation using photoplethysmography (PPG) has drawn increasing attention in the field of wearable technology due to its advantages with higher degree of usability and lower cost than Electrocardiograph. It has been widely used in wearable devices, such as smart-watches for fitness tracking and vital sign monitoring. However, motion artifact is a strong interference, preventing accurate estimation of HR. Signal decomposition and adaptive filtering are two popular approaches for motion artifact removal, but each of them has inherent drawbacks. In this paper, a hybrid motion artifact removal method is proposed, which combines nonlinear adaptive filtering and signal decomposition, getting the best of both approaches. The method was evaluated on the PPG database used in the 2015 IEEE Signal Processing Cup. The experimental results showed that the method achieved the average absolute error of 1.16 beat per minutes (BPM) on the 12 training data sets, and 2.98 BPM on the ten testing data sets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available