Comparative analysis of machine learning algorithms for optimizing variable step-size least mean square in motion artifact reduction

Authors

  • Zailan KABM Computer and Information Sciences Department, Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia
  • Hasan MHB Computer and Information Sciences Department, Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia
  • Witjaksono G Electrical and Electronic Engineering Department, Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia

Keywords:

Variable step-size least mean square, support vector machine, artificial neural network, random forest, motion artifact reduction

Abstract

Optical sensor like Photoplethysmographs (PPG), is widely used in generating real time information such as current heart rate. Existing studies on PPG demonstrated that the weakness of this technology is the sensor will capture the motion artifact reading when there is excessive motion exerts on the sensor. Numerous algorithms had been developed to reduce the motion artifact on PPG and increase the accuracy of the health monitoring device reading. However, these existing solutions using least mean square (LMS) algorithm failed to achieve high accuracy of heart rate reading. This paper presents and compares three types of machine learning algorithms that are widely used in classification of wearable signals, which are support vector machine (SVM), artificial neural network (ANN) and random forest (RF). The machine learning algorithms optimize variable step-size LMS (VSSLMS) accuracy by classifying the speed of the motion and giving suitable step size values based on the classification. The result shows that SVM is the best machine learning algorithm in classifying the speed category of the heart rate to eventually get the suitable step size value for VSSLMS.

References

“Redesigned Apple Watch Series 4 revolutionizes communication, fitness and health,” Apple (Canada), 24- Sep-2018. [Online]. Available: https://www.apple.com/newsroom/2018/09/redesignedapple-watch-series-4-revolutionizes-communication-fitnessand-health/. [Accessed: 30-Sep-2018].

Neha, R. Kanawade, S. Tewary, and H. K. Sardana, “Photoplethysmography Based Arrhythmia Detection and Classification,” 2019 6th International Conference on Signal Processing and Integrated Networks (SPIN), 2019.

G. Zhang, T. Wu, Z. Wan, Z. Song, M. Yu, D. Wang, L. Li, F. Chen, and X. Xu, “A method to differentiate between ventricular fibrillation and asystole during chest compressions using artifact-corrupted ECG alone,” Computer Methods and Programs in Biomedicine, vol. 141,

pp. 111–117, 2017.

Wijshoff, R., Mischi, M. and Aarts, R. “Reduction of Periodic Motion Artifacts in Photoplethysmography”. IEEE Transactions on Biomedical Engineering, 64(1), pp.196-207,2017.

F. Peng, Z. Zhang, X. Gou, H. Liu, and W. Wang, “Motion artifact removal from photoplethysmographic signals by combining temporally constrained independent component analysis and adaptive filter,” BioMedical Engineering OnLine, vol. 13, no. 1, p. 50, 2014.

R. Kelley, “Machine Learning Explained: Algorithms Are Your Friend,” Blog - Dataiku. [Online]. Available: https://blog.dataiku.com/machine-learning-explainedalgorithms-are-your-friend. [Accessed: 18-Oct-2018].

H. L. on S. Musings, “Which machine learning algorithm should I use?,” Subconscious Musings, 12-Apr-2017. [Online]. Available:

https://blogs.sas.com/content/subconsciousmusings/2017/04/12/machine-learning-algorithm-use/. [Accessed: 16-Oct-2018].

Pakalra, “Machine learning algorithm cheat sheet - Azure,”Machine learning algorithm cheat sheet - Azure | Microsoft Docs. [Online]. Available: https://docs.microsoft.com/enus/azure/machine-learning/studio/algorithm-cheat-sheet. [Accessed: 18-Oct-2018].

Liu, Weifeng, et al. Kernel Adaptive Filtering: a Comprehensive Introduction. John Wiley & Sons, Inc., Hoboken, New Jersey 2010.

S. Ray and Business Analytics, “7 Types of Regression Techniques you should know,” Analytics Vidhya, 06-Apr-2018. [Online]. Available: https://www.analyticsvidhya.com/blog/2015/08/comprehensive-guide-regression/. [Accessed: 04-Nov-2018].

“How to Improve Medical Diagnosis Using Machine Learning,” Romexsoft, 06-Oct-2017. [Online]. Available: https://www.romexsoft.com/blog/improve-medicaldiagnosis-using-machine-learning/. [Accessed: 24-Oct-2018].

M. S. Roy, R. Gupta, J. K. Chandra, K. D. Sharma, and A. Talukdar, “Improving Photoplethysmographic Measurements Under Motion Artifacts Using Artificial Neural Network for Personal Healthcare,” IEEE Transactions on Instrumentation and Measurement, vol. 67, no. 12, pp. 2820–2829, 2018.

Y. Ye, W. He, Y. Cheng, W. Huang, and Z. Zhang, “A Robust Random Forest-Based Approach for Heart Rate Monitoring Using Photoplethysmography Signal Contaminated by Intense Motion Artifacts,” Sensors, vol. 17, no. 2, p. 385, 2017.

Q. Zhang, X. Zeng, W. Hu, and D. Zhou, “A Machine Learning-Empowered System for Long-Term MotionTolerant Wearable Monitoring of Blood Pressure and Heart Rate With Ear-ECG/PPG,” IEEE Access, vol. 5, pp. 10547–10561, 2017.

Q. Zhang, D. Zhou, and X. Zeng, “A novel machine learning-enabled framework for instantaneous heart rate monitoring from motion-artifact-corrupted electrocardiogram signals,” Physiological Measurement, vol. 37, no. 11, pp. 1945–1967, 2016.

J.-G. Lee, S. Jun, Y.-W. Cho, H. Lee, G. B. Kim, J. B. Seo, and N. Kim, “Deep Learning in Medical Imaging: General Overview,” Korean Journal of Radiology, vol. 18, no. 4, p. 570, 2017.

"What Is a Neural Network?", Mathworks.com, 2019. [Online]. Available: https://www.mathworks.com/discovery/neuralnetwork.html?s_tid=srchtitle. [Accessed: 14- Sep- 2019].

Z. Zhang, “Undergraduate students compete in the IEEE signal Processing cup: Part 3,” IEEE Signal Process. Mag., vol. 32, no. 6, 2015.

Z. Yuan and X. Songtao, “New LMS Adaptive Filtering Algorithm with Variable Step Size,” 2017 International Conference on Vision, Image and Signal Processing (ICVISP), 2017.[20] N. M. M. Noor and S. H. A. Hamid, “Visualization of Crime Data Using Self-organizing Map (SOM) and Improvement in SOM: A Review and Available Tools,” Journal of Computer Science & Computational Mathematics, vol. 6, no. 2, pp. 37–43, 2016.

Downloads

Published

2024-02-26

How to Cite

Zailan, K. A. B. M., Hasan, M. H. B., & Witjaksono, G. (2024). Comparative analysis of machine learning algorithms for optimizing variable step-size least mean square in motion artifact reduction. COMPUSOFT: An International Journal of Advanced Computer Technology, 9(03), 3590–3595. Retrieved from https://ijact.in/index.php/j/article/view/557

Issue

Section

Review Article

Similar Articles

<< < 11 12 13 14 15 16 17 18 19 20 > >> 

You may also start an advanced similarity search for this article.