RADIOELECTRONIC AND COMPUTER SYSTEMS

The article’s subject matter is the processing of abdominal EMG recordings and finding breathing patterns. The goal is to automatically classify respiratory patterns into two classes, or clusters, by two breathing patterns, regular and irregular, using machine learning (ML) methods. The object of the study was to obtain a dataset of 40 randomly picked abdominal EMG recordings (sampling rate equal to 200 Hz) borrowed from the complete dataset published by the Computational Clinical Neurophysiology Laboratory and the Clinical Data Animation Laboratory of Massachusetts General Hospital. The tasks to be solved are as follows: finding ETS (errors-trend-seasonality) model for the EMG series using the exponential smoothing method; obtaining denoised and detrended signals; obtaining the Hurst exponents for EMGs using the power-law decaying of correlograms for the denoised and detrended signals; describing the variabilities, SNR, the outlier fractions, and Hurst exponents by robust statistics, performing correlation analysis, and Principal Components Analysis (PCA); analyzing the structure of the distant matrix by a graph-based technique; obtaining the periodograms in the frequency domain using the known Wiener-Khinchin theorem; and finding the best models and methods of classification and clusterization and evaluating them within modern Machine Learning methods. The methods used are exponential smoothing, the Wiener-Khinchin theorem, the graph theory method, principal component analysis, programing within MAPLE 2020, and data processing by Weka. The authors obtained the following results: 1) wide data variability has been rated with the median absolute deviations, which is the most robust statistic in this case; 2) most of the signals (38 of 40) showed frequent outliers: from a few percent up to 24.6 % of emissions; 3) these four variables: outliers' percentage, variability, SNR, and persistency factors – form the attributes of input vectors of the subjects for further Machine Learning with Weka software; 4) Manhattan distances matrix among subjects' vectors in 4D attributes space allows imaging the data set as a weighted graph, the vertices of which are subjects; 5) the weights of the graph's edges reflect distances between any pair of them. "Closeness centralities" of vertices allowed us to cluster the data set on two clusters with 11 and 29 subjects, and Weka clustering algorithms confirmed this result. 6) The learning curve shows that a sufficiently small data set (from 25 subjects) might be suitable for classification purposes. Conclusions. The scientific novelty of the results obtained is as follows: 1) the Error-Trend-Seasonality model was the same for all data sets. Abdominal EMG of sleeping patients had additive errors and undamped trends without any seasonality; 2) the correlograms' decaying according to power law had been set, and Hurst exponents were in the range (of 0.776–0.887). This testifies to "long memory" (high persistence) of abdominal EMGs; 3) the modified Z-scores and robust statistics with the highest breakdown values were used for the EMG parameters because of many outliers; 4) breathing patterns were set using the periodograms in the frequency domain using the Wiener-Khinchin theorem; 5) the new graph-based method was successfully exploited to cluster the dataset. Parallel clustering with Weka algorithms confirmed the graph-based clustering results.

Abdominal Electromyogram; Breathing Patterns; Machine Learning; Variability; Outliers; Persistency

Goldberger, A. L., Amaral, L. A. N., Glass, L., Hausdorff, J. M., Ivanov, P. Ch., Mark, R. G., Mietus, J. E., Moody, G. B., Peng, C.-K., & Stanley, H. E. PhysioBank, PhysioToolkit, and PhysioNet. Components of a New Research Resource for Complex Physiologic Signals. Circulation, 2000, vol. 101, iss. 23, pp. e215-e220. DOI: 10.1161/01.cir.101.23.e215.

PhysioNet /Computing in Cardiology Challenge 2018: Training/Test Sets. Available at: https://archive.physionet.org/physiobank/database/challenge/2018. (accessed 10.02.2023).

Ghassemi, M. M., Moody, B. E., Lehman, L. H., Song, C., Li, Q., Sun, H., Mark, R. G., Westover, M. B., & Clifford, G. D. You Snooze, You Win: The PhysioNet/Computing in Cardiology Challenge 2018. Computing in Cardiology, 2018, vol. 45. 4 p. DOI: 10.22489/cinc.2018.049.

Bhat, S., & Chokroverty, S. Sleep disorders and COVID-19. Sleep Medicine, 2022, vol. 91, pp. 253-261. DOI: 10.1016/j.sleep.2021.07.021.

Jahrami, H., BaHammam, A. S., Bragazzi, N. L., Saif, Z., Faris, M. A., & Vitiello, M. V. Sleep problems during COVID-19 pandemic by population: a systematic review and meta-analysis. Journal of Clinical Sleep Medicine, 2020, vol.17, iss. 2, pp. 299-313. DOI: 10.5664/jcsm.8930.

Chuiko, G., & Darnapuk, Ye. Fractal nature of arterial blood oxygen saturation data. Radioelektronni i komp'uterni sistemi – Radioelectronic and computer systems, 2022, no. 1, pp. 206–215. DOI: 10.32620/reks.2022.1.16.

Capodilupo, E. What is the Respiratory Rate? Available at: https://www.whoop.com/thelocker/what-is-respiratory-rate-normal/. (accessed 5.02.2023).

Lovell, K., & Liszewski, C. Normal Sleep Patterns. Available at: https://learn.chm.msu.edu/neuroed/neurobiology_disease/content/otheresources/sleepdisorders.pdf. (accessed 5.02.2023).

Chuiko, G., Dvornik, O., Darnapuk, Y., & Baganov, Y. Devising a new filtration method and proof of self-similarity of electromyograms. Eastern-European Journal of Enterprise Technologies, 2021, vol. 4, no. 9(112), pp. 15–22. DOI: 10.15587/1729-4061.2021.239165.

Rose, W. KAAP686 Mathematics and Signal Processing for Biomechanics. Electromyogram analysis. Available at: http://www1.udel.edu/biology/rosewc/kaap686/notes/EMG%20analysis.pdf. (accessed 5.02.2023).

Chuiko, G., Darnapuk, Ye., Dvornik, O., & Krainyk, Ya. Improved robust handling of electromyograms with mining of new diagnostic signs. Proceedings of the 1st International Workshop on Information Technologies: Theoretical and Applied Problems 2021, Ternopil, 16 November 2021, pp. 55–62. Available at: https://ceur-ws.org/Vol-3039/short6.pdf. (accessed 5.02.2023).

De Livera, A. M., & Hyndman, R. J. Forecasting time series with complex seasonal patterns using exponential smoothing. Monash University, Working Paper 15/09, 2009. 28 p. Available at: https://www.monash.edu/business/econometrics-and-business-statistics/research/publications/ebs/wp15-09.pdf. (accessed 5.02.2023).

Bishop, C. M. Pattern Recognition and Machine Learning. Springer Publ., 2016. 758 p.

Machine learning tasks in ML.NET. Available at: https://learn.microsoft.com/en-us/dotnet/machine-learning/resources/tasks. (accessed 5.02.2023).

Publications from You Snooze, You Win: the PhysioNet/Computing in Cardiology Challenge 2018. Available at: https://archive.physionet.org/challenge/2018/papers/. (accessed 5.02.2023).

Schertel, A., Funke-Chambour, M., Geiser, T., & Brill, A.-K. P231 Respiratory breathing patterns and cough in idiopathic pulmonary fibrosis: awake, asleep and over time. Chest, 2017, vol. 151, iss. 5, article no. A131. DOI: /10.1016/j.chest.2017.04.138.

Frank, J. I., & Hanley, D. F. Abnormal Breathing Patterns. In: Hacke, W., Hanley, D. F., Einhäupl, K. M., Bleck, T. P., Diringer, M. N., Ropper, A.H. (eds) Neurocritical Care. Springer, Berlin, Heidelberg, 1994, pp. 366-373. DOI: 10.1007/978-3-642-87602-8

Massaroni, C., Lopes, D. S., Lo Presti, D., Schena, E., & Silvestri, S. Contactless Monitoring of Breathing Patterns and Respiratory Rate at the Pit of the Neck: A Single Camera Approach. Journal of Sensors, 2018, vol. 2018, article id 4567213, pp. 1–13. DOI: 10.1155/2018/4567213.

Lan, T.-H., Gao, Z.-Y., Abdalla, A. N., Cheng, B., & Wang, S. Detrended fluctuation analysis as a statistical method to study ion single channel signal. Cell Biology International, 2008, vol. 32, iss. 2, pp. 247–252. DOI: 10.1016/j.cellbi.2007.09.001.

Veenstra, J. Q. Persistence and Anti-persistence: Theory and Software. Electronic Thesis and Dissertation Repository. Western University, 2013. 131 p. Available at: https://ir.lib.uwo.ca/cgi/viewcontent.cgi?article=2414&context=etd. (accessed 5.02.2023).

Wiener-Khinchin Theorem - from Wolfram MathWorld. Available at: https://mathworld.wolfram.com/Wiener-KhinchinTheorem.html. – Title from screen. (accessed 27.11.2022).

Bernardin, L., Chin, P., DeMarco, P., Geddes, K. O., Hare, D. E. G., Heal, K. M., Labahn, G., May, J. P., McCarron, J., Monagan, M. B., Ohashi, D., & Vorkoetter, S. M. Maple Programming Guide. Springer-Verlag Berlin and Heidelberg GmbH & Co. K, 2011. 678 p. Available at: https://www.maplesoft.com/view.aspx?SF=103828/337201/ProgrammingGuide.pdf. (accessed 27.11.2022).

Perlich, C. Learning Curves in Machine Learning. In: Sammut, C., Webb, G. I. (eds) Encyclopedia of Machine Learning. Springer, Boston, MA., 2011, pp. 577-580. DOI: 10.1007/978-0-387-30164-8_452.

Exponential Smoothing for Time Series Forecasting. Statistics By Jim. Available at: https://statisticsbyjim.com/time-series/exponential-smoothing-time-series-forecasting/. (accessed 5.02.2023).

Shastri, S., Sharma, A., Mansotra, V., Sharma, A., Bhadwal, A. S., & Kumari, M. A Study on Exponential Smoothing Method for Forecasting. International Journal of Computer Sciences and Engineering, 2018, vol. 6, iss. 4, pp. 482–485. DOI: 10.26438/ijcse/v6i4.482485.

Wilcox, R. Chapter 1 – Introduction. In Statistical Modeling and Decision Science, Introduction to Robust Estimation and Hypothesis Testing (Third Edition). Academic Press, 2012, pp. 1–22. DOI: 10.1016/b978-0-12-386983-8.00001-9

Scott, D. W. Averaged shifted histogram. Wiley Interdisciplinary Reviews: Computational Statistics, 2010, vol. 2, iss. 2, pp. 160–164. DOI: 10.1002/wics.54.

Węglarczyk, S. Kernel density estimation and its application. ITM Web of Conferences, 2018, vol. 23, article no. 00037. DOI: 10.1051/itmconf/20182300037.

Vathy-Fogarassy, Á., & Abonyi, J. Graph-Based Clustering Algorithms. In: Graph-Based Clustering and Data Visualization Algorithms. Springer Briefs in Computer Science. Springer, London, 2013, pp. 17–41. DOI: 10.1007/978-1-4471-5158-6_2.

Murphy, A., & Feger, J. Signal-to-noise ratio (radiography). Radiopaedia.org, 2020. DOI: 10.53347/rID-75580.

Movahed, M. S., Jafari, G. R., Ghasemi, F., Rahvar, S., & Tabar, M. R. R. Multifractal detrended fluctuation analysis of sunspot time series. Journal of Statistical Mechanics: Theory and Experiment, 2006, vol. 2006, no. 02, article no. P02003. DOI: 10.1088/1742-5468/2006/02/P02003.

Chapter 152. Box Plots. NCSS Statistical Software. 10 p. Available at: https://www.ncss.com/wp-content/themes/ncss/pdf/Procedures/NCSS/Box_Plots.pdf. (accessed 5.02.2023).

Rousseeuw, P. J., & Hubert, M. Robust statistics for outlier detection. WIREs Data Mining and Knowledge Discovery, 2011, vol. 1, iss. 1, pp. 73–79. DOI: 10.1002/widm.2.

Kamble, B., & Doke, K. Outlier Detection Approaches in Data Mining. International Research Journal of Engineering and Technology, 2017, vol. 04, iss. 3, pp. 634-638. Available at: https://www.irjet.net/archives/V4/i3/IRJET-V4I3171.pdf. (accessed 5.02.2023).

Seo, S. A Review and Comparison of Methods for Detecting Outliers in Univariate Data Sets. Univariate Data Sets. Master's Thesis, University of Pittsburgh, 2006. 53 p. Available at: http://d-scholarship.pitt.edu/7948/1/Seo.pdf. (accessed 5.02.2023).

Hansen, D. L., Shneiderman, B., Smith, M. A., & Himelboim, I. Chapter 6 - Calculating and visualizing network metrics. Calculating and visualizing network metrics. Analyzing Social Media Networks with NodeXL (Second Edition), 2020, pp. 79–94. DOI: 10.1016/b978-0-12-817756-3.00006-6.

Weka - Machine Learning Software in Java. WEKA Manual for Version 3-9-5, 2020. Available at: https://osdn.net/projects/sfnet_weka/downloads/documentation/3.9.x/WekaManual-3-9-5.pdf. (accessed 5.02.2023).

Grant, M. J., Button, C. M., & Snook, B. An Evaluation of Interrater Reliability Measures on Binary Tasks Using d-Prime. Applied Psychological Measurement, 2016, vol. 41, iss. 4, pp. 264–276. DOI: 10.1177/0146621616684584.

Yang, X., Fan, D., Ren, A., Zhao, N., & Alam, M. 5G-Based User-Centric Sensing at C-Band. IEEE Transactions on Industrial Informatics, 2019, vol. 15, iss. 5, pp. 3040–3047. DOI: 10.1109/tii.2019.2891738.