A Robust Random Forest-Based Approach for Heart Rate Monitoring Using Photoplethysmography Signal Contaminated by Intense Motion Artifacts
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 a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/17/2/385 |
| _version_ | 1811185922811625472 |
|---|---|
| author | Yalan Ye Wenwen He Yunfei Cheng Wenxia Huang Zhilin Zhang |
| author_facet | Yalan Ye Wenwen He Yunfei Cheng Wenxia Huang Zhilin Zhang |
| author_sort | Yalan Ye |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-11T13:38:44Z |
| format | Article |
| id | doaj.art-6d41b25b1a9f48bba749d3de389d0906 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T13:38:44Z |
| publishDate | 2017-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6d41b25b1a9f48bba749d3de389d09062022-12-22T04:21:23ZengMDPI AGSensors1424-82202017-02-0117238510.3390/s17020385s17020385A Robust Random Forest-Based Approach for Heart Rate Monitoring Using Photoplethysmography Signal Contaminated by Intense Motion ArtifactsYalan Ye0Wenwen He1Yunfei Cheng2Wenxia Huang3Zhilin Zhang4School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaWest China Hospital of Sichuan University, Chengdu 610041, ChinaSamsung Research America—Dallas, Richardson, TX 75082, USAThe 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.http://www.mdpi.com/1424-8220/17/2/385heart rate (HR)photoplethysmography (PPG)motion artifacts (MA)random forest |
| spellingShingle | Yalan Ye Wenwen He Yunfei Cheng Wenxia Huang Zhilin Zhang A Robust Random Forest-Based Approach for Heart Rate Monitoring Using Photoplethysmography Signal Contaminated by Intense Motion Artifacts Sensors heart rate (HR) photoplethysmography (PPG) motion artifacts (MA) random forest |
| title | A Robust Random Forest-Based Approach for Heart Rate Monitoring Using Photoplethysmography Signal Contaminated by Intense Motion Artifacts |
| title_full | A Robust Random Forest-Based Approach for Heart Rate Monitoring Using Photoplethysmography Signal Contaminated by Intense Motion Artifacts |
| title_fullStr | A Robust Random Forest-Based Approach for Heart Rate Monitoring Using Photoplethysmography Signal Contaminated by Intense Motion Artifacts |
| title_full_unstemmed | A Robust Random Forest-Based Approach for Heart Rate Monitoring Using Photoplethysmography Signal Contaminated by Intense Motion Artifacts |
| title_short | A Robust Random Forest-Based Approach for Heart Rate Monitoring Using Photoplethysmography Signal Contaminated by Intense Motion Artifacts |
| title_sort | robust random forest based approach for heart rate monitoring using photoplethysmography signal contaminated by intense motion artifacts |
| topic | heart rate (HR) photoplethysmography (PPG) motion artifacts (MA) random forest |
| url | http://www.mdpi.com/1424-8220/17/2/385 |
| work_keys_str_mv | AT yalanye arobustrandomforestbasedapproachforheartratemonitoringusingphotoplethysmographysignalcontaminatedbyintensemotionartifacts AT wenwenhe arobustrandomforestbasedapproachforheartratemonitoringusingphotoplethysmographysignalcontaminatedbyintensemotionartifacts AT yunfeicheng arobustrandomforestbasedapproachforheartratemonitoringusingphotoplethysmographysignalcontaminatedbyintensemotionartifacts AT wenxiahuang arobustrandomforestbasedapproachforheartratemonitoringusingphotoplethysmographysignalcontaminatedbyintensemotionartifacts AT zhilinzhang arobustrandomforestbasedapproachforheartratemonitoringusingphotoplethysmographysignalcontaminatedbyintensemotionartifacts AT yalanye robustrandomforestbasedapproachforheartratemonitoringusingphotoplethysmographysignalcontaminatedbyintensemotionartifacts AT wenwenhe robustrandomforestbasedapproachforheartratemonitoringusingphotoplethysmographysignalcontaminatedbyintensemotionartifacts AT yunfeicheng robustrandomforestbasedapproachforheartratemonitoringusingphotoplethysmographysignalcontaminatedbyintensemotionartifacts AT wenxiahuang robustrandomforestbasedapproachforheartratemonitoringusingphotoplethysmographysignalcontaminatedbyintensemotionartifacts AT zhilinzhang robustrandomforestbasedapproachforheartratemonitoringusingphotoplethysmographysignalcontaminatedbyintensemotionartifacts |