Abstract
The estimation of heart rate (HR) based on wearable devices is of interest in fitness. Photoplethysmography (PPG) is a promising approach to estimate HR due to low cost; however, it is easily corrupted by motion artifacts (MA). In this work, a robust approach based on random forest is proposed for accurately estimating HR from the photoplethysmography signal contaminated by intense motion artifacts, consisting of two stages. Stage 1 proposes a hybrid method to effectively remove MA with a low computation complexity, where two MA removal algorithms are combined by an accurate binary decision algorithm whose aim is to decide whether or not to adopt the second MA removal algorithm. Stage 2 proposes a random forest-based spectral peak-tracking algorithm, whose aim is to locate the spectral peak corresponding to HR, formulating the problem of spectral peak tracking into a pattern classification problem. Experiments on the PPG datasets including 22 subjects used in the 2015 IEEE Signal Processing Cup showed that the proposed approach achieved the average absolute error of 1.65 beats per minute (BPM) on the 22 PPG datasets. Compared to state-of-the-art approaches, the proposed approach has better accuracy and robustness to intense motion artifacts, indicating its potential use in wearable sensors for health monitoring and fitness tracking.
Highlights
Heart rate (HR) estimation based on wearable devices is of vital importance due to its useful features in controlling the training load or monitoring physiologic conditions during daily activities.Photoplethysmography (PPG) [1,2,3,4,5] is a popular technique due to its simpler hardware implementation and lower cost than the conventional electrocardiography (ECG) method
The spectral peak tracking problem is formulated into a pattern classification task, and the random forest-based algorithm can locate the spectral peak corresponding to HR with a better generalization and robustness
We can see that heuristic algorithms achieved a good performance on the 12 recordings, but a poor performance under the more challenging 10 recordings
Summary
Yalan Ye 1 , Wenwen He 1 , Yunfei Cheng 1 , Wenxia Huang 2, * and Zhilin Zhang 3, *. Academic Editors: Octavian Adrian Postolache, Alex Casson and Subhas Chandra Mukhopadhyay. Received: 23 December 2016; Accepted: 12 February 2017; Published: 16 February 2017
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.