PPG2EMG: Estimating Upper-Arm Muscle Activities and EMG from Wrist PPG Values
Abstract
:1. Introduction
- Easy to wear: Compared to an EMG sensor, there is no need for multiple electrodes to be attached, and no gel or adhesive tape is used, resulting in less stress on the skin.
- Low cost: All you need is a rubber band (≤1 USD). Disposable conductive gel and adhesive tape are not used.
- No additional equipment: Only a smartwatch or activity meter equipped with a PPG sensor is needed. There is no need for wiring or communication ports for the muscle action potential sensing. Data size and power consumption do not increase.
2. Related Work
2.1. Human Activity Recognition Using EMG
2.2. Human Activity Recognition Using PPG
3. Proposed Method
3.1. Principle
3.2. Muscle Activity Recognition Method
3.3. EMG Estimation Method
4. Evaluation
4.1. Preliminary Experiment
4.1.1. Setup
4.1.2. Result
4.2. Evaluation for Muscle Activity Recognition
4.2.1. Setup
4.2.2. Result
4.3. Evaluation for EMG Estimation
4.3.1. Setup
4.3.2. Result
5. Discussion
5.1. User Dependency
5.2. Relation of Compression and Pulse Wave
5.3. Noise of PPG Measurement
5.4. Load on the Body
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Toda, M.; Akita, J.; Sakurazawa, S.; Yanagihara, K.; Kunita, M.; Iwata, K. Wearable biomedical monitoring system using textilenet. In Proceedings of the International Symposium on Wearable Computers (ISWC2006), Montreux, Switzerland, 11–14 October 2006; pp. 119–120. [Google Scholar] [CrossRef]
- Matsuhisa, N.; Kaltenbrunner, M.; Yokota, T.; Jinno, H.; Kuribara, K.; Sekitani, T.; Someya, T. Printable elastic conductors with a high conductivity for electronic textile applications. Nat. Commun. 2015, 6, 7461. [Google Scholar] [CrossRef] [PubMed]
- Lenzi, T.; De Rossi, S.M.M.; Vitiello, N.; Carrozza, M.C. Intention-based EMG control for powered exoskeletons. IEEE Trans. Biomed. Eng. 2012, 59, 2180–2190. [Google Scholar] [CrossRef] [PubMed]
- Huang, D.; Zhang, X.; Saponas, T.S.; Fogarty, J.; Gollakota, S. Leveraging Dual-Observable Input for Fine-Grained Thumb Interaction Using Forearm EMG. In Proceedings of the 28th Annual ACM Symposium on User Interface Software and Technology (UIST2015), Charlotte, NC, USA, 11–15 November 2015; pp. 523–528. [Google Scholar] [CrossRef]
- McIntosh, J.; McNeill, C.; Fraser, M.; Kerber, F.; Löchtefeld, M.; Krüger, A. EMPress: Practical Hand Gesture Classification with Wrist-Mounted EMG and Pressure Sensing. In Proceedings of the ACM SIGCHI International Conference on Human Factors in Computing Systems (CHI2016), San Jose, CA, USA, 7–12 May 2016; pp. 2332–2342. [Google Scholar] [CrossRef]
- Amma, C.; Krings, T.; Böer, J.; Schultz, T. Advancing Muscle-Computer Interfaces with High-Density Electromyography. In Proceedings of the 33rd Annual ACM SIGCHI International Conference on Human Factors in Computing Systems (CHI2015), Seoul, Republic of Korea, 18–23 April 2015; pp. 929–938. [Google Scholar] [CrossRef]
- Zhang, X.; Chen, X.; Li, Y.; Lantz, V.; Wang, K.; Yang, J. A Framework for Hand Gesture Recognition Based on Accelerometer and EMG Sensors. IEEE Trans. Syst. Man, Cybern. 2011, 41, 1064–1076. [Google Scholar] [CrossRef]
- Kurosawa, H.; Sakamoto, D.; Ono, T. MyoTilt: A target selection method for smartwatches using the tilting operation and electromyography. In Proceedings of the 20th International Conference on Human–Computer Interaction with Mobile Devices and Services (MobileHCI 2018), Barcelona, Spain, 3–6 September 2018; pp. 1–11. [Google Scholar] [CrossRef]
- Saponas, T.S.; Tan, D.S.; Morris, D.; Turner, J.; Landay, J.A. Making Muscle-computer Interfaces More Practical. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI2010), Atlanta, GA, USA, 10–15 April 2010; pp. 851–854. [Google Scholar] [CrossRef]
- Duente, T.; Schulte, J.; Pfeiffer, M.; Rohs, M. MuscleIO: Muscle-Based Input and Output for Casual Notifications. J. ACM Interact. Mob. Wearable Ubiquitous Technol. (IMWUT2018) 2018, 2, 1–21. [Google Scholar] [CrossRef]
- Javaid, H.; Tiwana, M.; Alsanad, A.; Iqbal, J.; Riaz, M.; Ahmad, S.; Almisned, F. Classification of Hand Movements Using MYO Armband on an Embedded Platform. Electronics 2021, 10, 1322. [Google Scholar] [CrossRef]
- Havriushenko, A.; Slyusarenko, K.; Fedorin, I. Smartwatch based respiratory rate estimation during sleep using CNN/LSTM neural network. In Proceedings of the IEEE 40th International Conference on Electronics and Nanotechnology (ELNANO 2020), Kyiv, Ukraine, 22–24 April 2020; pp. 584–587. [Google Scholar] [CrossRef]
- Jarchi, D.; Salvi, D.; Tarassenko, L.; Clifton, D.A. Validation of Instantaneous Respiratory Rate Using Reflectance PPG from Different Body Positions. Sensors 2018, 18, 3705. [Google Scholar] [CrossRef] [PubMed]
- Han, D.; Bashar, S.K.; Mohagheghian, F.; Ding, E.; Whitcomb, C.; McManus, D.D.; Chon, K.H. Premature Atrial and Ventricular Contraction Detection using Photoplethysmographic Data from a Smartwatch. Sensors 2020, 20, 5683. [Google Scholar] [CrossRef] [PubMed]
- Wang, W.F.; Yang, C.Y.; Wu, Y.F. SVM-Based Classification Method to Identify Alcohol Consumption Using ECG and PPG Monitoring. Pers. Ubiquitous Comput. 2018, 22, 275–287. [Google Scholar] [CrossRef]
- Longmore, S.K.; Lui, G.Y.; Naik, G.; Breen, P.P.; Jalaludin, B.; Gargiulo, G.D. A Comparison of Reflective Photoplethysmography for Detection of Heart Rate, Blood Oxygen Saturation, and Respiration Rate at Various Anatomical Locations. Sensors 2019, 19, 1874. [Google Scholar] [CrossRef]
- Goshvarpour, A.; Abbasi, A.; Goshvarpour, A. Fusion of heart rate variability and pulse rate variability for emotion recognition using lagged poincare plots. Australas. Phys. Eng. Sci. Med. 2017, 40, 617–629. [Google Scholar] [CrossRef]
- Kajiwara, Y.; Shimauchi, T.; Kimura, H. Predicting Emotion and Engagement of Workers in Order Picking Based on Behavior and Pulse Waves Acquired by Wearable Devices. Sensors 2019, 19, 165. [Google Scholar] [CrossRef] [PubMed]
- Lee, M.S.; Lee, Y.K.; Pae, D.S.; Lim, M.T.; Kim, D.W.; Kang, T.K. Fast Emotion Recognition Based on Single Pulse PPG Signal with Convolutional Neural Network. Appl. Sci. 2019, 9, 3355. [Google Scholar] [CrossRef]
- Udovičić, G.; Ðerek, J.; Russo, M.; Sikora, M. Wearable Emotion Recognition System Based on GSR and PPG Signals. In Proceedings of the MMHealth’17, 2nd International Workshop on Multimedia for Personal Health and Health Care, Mountain View, CA, USA, 23 October 2017; pp. 53–59. [Google Scholar] [CrossRef]
- Tong, Z.; Chen, X.; He, Z.; Tong, K.; Fang, Z.; Wang, X. Emotion Recognition Based on Photoplethysmogram and Electroencephalogram. In Proceedings of the 2018 IEEE 42nd Annual Computer Software and Applications Conference (COMPSAC), Tokyo, Japan, 23–27 July 2018; Volume 2, pp. 402–407. [Google Scholar] [CrossRef]
- Lee, M.; Cho, Y.; Lee, Y.; Pae, D.; Lim, M.; Kang, T. PPG and EMG Based Emotion Recognition using Convolutional Neural Network. In Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics (ICINCO 2019), Prague, Czech Republic, 29–31 July 2019; pp. 595–600. [Google Scholar] [CrossRef]
- Ayata, D.; Yaslan, Y.; Kamasak, M.E. Emotion Recognition from Multimodal Physiological Signals for Emotion Aware Healthcare Systems. J. Med. Biol. Eng. 2020, 40, 149–157. [Google Scholar] [CrossRef]
- Kotzen, K.; Charlton, P.H.; Salabi, S.; Amar, L.; Landesberg, A.; Behar, J.A. SleepPPG-Net: A deep learning algorithm for robust sleep staging from continuous photoplethysmography. IEEE J. Biomed. Health Inform. 2022. ahead of print. [Google Scholar] [CrossRef] [PubMed]
- Yoshida, K.; Murao, K. Estimating load positions of wearable devices based on difference in pulse wave arrival time. In Proceedings of the 23rd International Symposium on Wearable Computers (ISWC2019), London, UK, 9–13 September 2019; pp. 234–243. [Google Scholar]
- Akimoto, Y.; Murao, K. Design and Implementation of an Input Interface for Wearable Devices using Pulse Wave Control by Compressing the Upper Arm. In Proceedings of the AHs’21: Augmented Humans Conference, Rovaniemi, Finland, 22–24 February 2021; pp. 280–282. [Google Scholar] [CrossRef]
- Yamakoshi, K.; Shimazu, H.; Shibata, M.; Kamiya, A. New oscillometric method for indirect measurement of systolic and mean arterial pressure in the human finger (Part 1) Model experiment. Med. Biol. Eng. Comput. 1982, 20, 307–313. [Google Scholar] [CrossRef] [PubMed]
- Yamakoshi, K.; Shimazu, H.; Shibata, M.; Kamiya, A. New oscillometric method for indirect measurement of systolic and mean arterial pressure in the human finger (Part 2) Correlation study. Med. Biol. Eng. Comput. 1982, 20, 314–318. [Google Scholar] [CrossRef] [PubMed]
- Petrofsky, J. Frequency and amplitude analysis of the EMG during exercise on the bicycle ergometer. Eur. J. Appl. Physiol. Occup. Physiol. 1979, 41, 1–15. [Google Scholar] [CrossRef] [PubMed]
- Warren, G.L.; Hermann, K.M.; Ingalls, C.P.; Masselli, M.R.; Armstrong, R. Decreased EMG median frequency during a second bout of eccentric contractions. Med. Sci. Sport. Exerc. 2000, 32, 820–829. [Google Scholar] [CrossRef] [PubMed]
- Fratini, A.; La Gatta, A.; Bifulco, P.; Romano, M.; Cesarelli, M. Muscle motion and EMG activity in vibration treatment. Med. Eng. Phys. 2009, 31, 1166–1172. [Google Scholar] [CrossRef] [PubMed]
- Bayati, H.; Mill’an, J.D.R.; Chavarriaga, R. Unsupervised Adaptation to On-body Sensor Displacement In Acceleration-Based Activity Recognition. In Proceedings of the International Symposium on Wearable Computers (ISWC2011), San Francisco, CA, USA, 12–15 June 2011; pp. 71–78. [Google Scholar] [CrossRef]
Arm State | Subject | |||||
---|---|---|---|---|---|---|
A | B | C | D | E | Average | |
(1) Normal | 0.72 | 0.72 | 0.79 | 0.78 | 0.87 | 0.776 |
(2) Bend arm | 0.63 | 0.65 | 0.68 | 0.81 | 0.76 | 0.706 |
(3’) Put strength & hold dumbbell | 0.90 | 0.94 | 0.93 | 0.95 | 0.90 | 0.924 |
Average | 0.75 | 0.77 | 0.80 | 0.85 | 0.84 |
Arm State | Subject | |||||
---|---|---|---|---|---|---|
A | B | C | D | E | Average | |
(1) Normal | 0.49 | 0.31 | 0.00 | 0.07 | 0.18 | 0.21 |
(2) Bend arm | 0.27 | 0.34 | 0.00 | 0.15 | 0.04 | 0.16 |
(3’) Put strength & hold dumbbell | 0.78 | 0.72 | 0.67 | 0.69 | 0.69 | 0.71 |
Average | 0.51 | 0.46 | 0.22 | 0.30 | 0.30 |
Arm State | Subject | ||||
---|---|---|---|---|---|
A | B | C | D | E | |
(1) Normal | 961 | 422 | 159 | 342 | 59 |
(2) Bend arm | 443 | 848 | 247 | 348 | 223 |
(3) Put strength | 2246 | 1261 | 1129 | 2239 | 1394 |
(4) Hold dumbbell | 2716 | 2351 | 1924 | 3506 | 1422 |
Arm State | Subject | ||||
---|---|---|---|---|---|
A | B | C | D | E | |
(1) Normal | 20.1% | 22.2% | 22.5% | 13.6% | 32.2% |
(2) Bend arm | 18.7% | 20.2% | 27.0% | 14.1% | 37.0% |
(3) Put strength | 11.1% | 14.3% | 27.4% | 15.7% | 17.1% |
(4) Hold dumbbell | 17.8% | 67.5% | 46.7% | 20.0% | 16.4% |
Average | 17.1% | 23.8% | 27.7% | 15.5% | 24.8% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Okamoto, M.; Murao, K. PPG2EMG: Estimating Upper-Arm Muscle Activities and EMG from Wrist PPG Values. Sensors 2023, 23, 1782. https://doi.org/10.3390/s23041782
Okamoto M, Murao K. PPG2EMG: Estimating Upper-Arm Muscle Activities and EMG from Wrist PPG Values. Sensors. 2023; 23(4):1782. https://doi.org/10.3390/s23041782
Chicago/Turabian StyleOkamoto, Masahiro, and Kazuya Murao. 2023. "PPG2EMG: Estimating Upper-Arm Muscle Activities and EMG from Wrist PPG Values" Sensors 23, no. 4: 1782. https://doi.org/10.3390/s23041782
APA StyleOkamoto, M., & Murao, K. (2023). PPG2EMG: Estimating Upper-Arm Muscle Activities and EMG from Wrist PPG Values. Sensors, 23(4), 1782. https://doi.org/10.3390/s23041782