Employability Of Unsupervised Machine Learning Techniques For Elimination Of Electrodermal Activity Artefacts During And Post Surgeries
Saksham Agarwal
Montfort Sr. Sec. School, Ashok Vihar, Delhi
46-55
Vol: 11, Issue: 1, 2021
Receiving Date:
2021-02-10
Acceptance Date:
2021-03-28
Publication Date:
2021-03-29
Download PDF
http://doi.org/10.37648/ijrst.v11i01.006
Abstract
Detecting and removing artefacts is crucial in data preprocessing pipelines for physiological time series data, mainly when collected outside controlled experimental settings. The fact that such artefacts are often easily identifiable visually suggests that unsupervised machine learning algorithms could be practical without requiring manually labelled training datasets. Current methods are often heuristic-based, not generalizable, or designed for controlled experimental settings with fewer artefacts. In this study, we evaluate the effectiveness of three unsupervised learning algorithms—Isolation Forests, One-Class Support Vector Machine, and K-Nearest Neighbor Distance—in removing heavy cautery-related artefacts from electrodermal activity (EDA) data collected during surgeries involving six subjects. We defined 12 features for each half-second window as inputs to the unsupervised learning methods. We compared each subject's best-performing unsupervised learning method to four existing EDA artefact removal methods. The unsupervised learning method was the only approach that removed the artefacts across all six subjects. This approach can be easily extended to other types of physiological data in complex settings.
References
- G. Biagetti, P. Crippa, L. Falaschetti, G. Tanoni, C. Turchetti, “A comparative study of machine learning algorithms for physiological signal classification,” Procedia Computer Science, vol. 126, pp. 1977- 1984, 2018.
- M. Goldstein, S. Uchida, “A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data,” PLoS ONE, vol. 11, no. 4, pp. e0152173, Apr 2016.
- W. Boucsein, Electrodermal Activity. New York, NY: Springer, 2012.
- C. Qi, R.T. Faghih, “Detection of Autonomic Sympathetic Arousal from Electrodermal Activity,” PowerPoint presentation (unpublished).
- K. Dragomiretskiy, D. Zosso, “Variational Mode Decomposition,” IEEE Trans. Sig. Proc., vol. 62, no. 3, pp. 531-544, Feb. 2014.
- W. Chen, N. Jacques, S. Taylor, A. Sano, S. Fedor, R. W. Picard, “Wavelet-Based Motion Artifact Removal for Electrodermal Activity,” in Conf. Proc. IEEE Eng. Med. Biol. Soc., pp. 6223-6226, Aug 2015.
- S. Taylor, N. Jacques, W. Chen, S. Fedor, A. Sano, R. Picard, “Automatic Identification of Artifacts in Electrodermal Activity Data,” in Conf. Proc. IEEE Eng. Med. Biol. Soc., pp. 1934-1937, Aug 2015.
- Y. Zhang, “Unsupervised Motion Artifact Detection in Wrist-Measured Electrodermal Activity Data,” M.S. thesis, Dept. Electric. Eng., Univ. of Toledo, Toledo, Ohio, 2017.
- F. T. Liu, K. M. Ting, Z-H. Zhou, “Isolation Forest,” in Proc. 8th IEEE Int. Conf. Data Mining, pp. 413-422, 2008.
- L-Y. Hu, M-W. Huang, S-W. Ke, C-F. Tsai, “The distance function effect on k-nearest neighbor classification for medical datasets,” SpringerPlus, vol. 5, no. 1304, Aug 2016.
- L. M. Manevitz, M. Yousef, “One-Class SVMs for Document Classification,” Journal of Machine Learning Research, vol. 2, pp. 139- 154, 2001.
- “Neurofeedback Expert System”, Thought Technology Ltd, https://thoughttechnology.com/neurofeedback-expert-system/, accessed 1/6/21.
- R. Barbieri, E. C. Matten, A. A. Alabi, E. N. Brown, “A point-process model of human heartbeat intervals: new definitions of heart rate and heart rate variability,” Am. J. Physiol. Heart Circ. Physiol., vol. 288, no. 1, pp. H424–435, Jan 2005.
Back