Scientific Journal

Herald of Advanced Information Technology

Current state and future perspectives of machine learning usage in the computer bioinformatics systems are analyzed in the article. It is shown that heterogeneousness of data and wide range of bioinformatics tasks influenced the development of the specialized solutions for each separate domain or application. This complicates the possibility to compare effectiveness of certain methods as well as usage of the best variants for the system design for the new tasks. Research results are presented, which are related to the development of principles for the design of the biosignal computer processing systems involving the machine learning. The expediency of separation the system levels within the process of biosignals processing is reasoned, and their functions are outlined. Innovativeness of the suggested approach lies in separation of the function of lower, middle and upper levels from methods with the help of which they are realized, as well as from the implementation variants for these methods based on the hardware and software components. It is highlighted that the middle system level is significantly invariable both in regards to the task to be solved and to the biosignal type. At the same time the upper level is specific as to the task, and the lower level is specific as to the type of biosignal. Distinct outlining of functions for each system level and the inter level interfaces opens prospectives for structuring information during the analysis of the known decisions, which simplifies the analysis and comparison of the effectiveness of these solutions. Design process of the computer system for the specific tasks gets simplified and potentially quickens due to the possibility of transferring the best results between the related tasks. On the basis of the developed three system levels concept the range of tasks related to machine learning application and biosignal processing on all the system levels was studied and analyzed.
1. Rangayyan, R. M. (2002). “Biomedical Signal Analysis: A Case-Study Approach”. John Willey and Sons Inc. 552 p. 
2. Jain, A. K., Flynn, P. & Ross, A. A. (2008). “Handbook of Biometrics”. Springer, 556 p. 
3. Luneski, A., Konstantinidis, E. & Bamidis, P. (2010). “Affective Medicine: a review of Affective Computing efforts in Medical Informatics”, Methods of Information in Medicine, 49 (3). pp. 207-218. 
4. Ramadan, R. A. & Vasilakos, A. V. (2017). “Brain Computer Interface: Control Signals Review”. Neurocomputing, Volume 223, (5) pp. 26-44. 
5. Reaz, M. B. I., Hussain, M. S. & MohdYasin, F. (2006). “Techniques of EMG signal analysis: detection, processing, classification and applications”. Biol. Proced. Online, 8(1), pp. 11-35. 
6. Lugovaya, T. S. (2005). “Biometric human identification based on electrocardiogram”. SaintPetersburg, Russian Federation, Publ. “LETI”. 
7. Khoma, Y. V., Stadnyk, B. I., Mykyichuk, M. M. & Frish, S. (2018). “Metody i zasoby vymiryuvannya ta komp’yuternoho opratsyuvannya biosyhnaliv”. [Methods and assets of biosignal measuring and computer processing]. Measuring Equipment and Metrology. Vol. 79(3), pp. 5-16 (in Ukrainian). 
8. Seonwoo, M., Byunghan, L. & Sungroh, Y. (2017). “Deep learning in bioinformatics”. Briefings in Bioinformatics, Vol. 18(5), pp. 851-869. 
9. Miotto, R., Wang, F., Wang, S., Jiang, X. & Dudley, J. T. (2018). “Deep learning for healthcare: review, opportunities and challenges”. Briefings in Bioinformatics, Vol. 19(6), pp. 1236-1246. 
10. Arsirii, O. O. & Manikaeva, O. S. (2019). “Models and methods of intellectual analysis for medical-sociological monitoring’s data based on the neural network with a competitive layer”. Applied Aspects of Information Technology. Vol. 2, No. 3, pp. 173-185. DOI: 10.15276/aait.03.2019.1. 
11. Jang, H. & Cho, K. (2019). “Applications of deep learning for the analysis of medical data”. Arch. Pharm. Res. 42, pp. 492-504. 
12. Duke, J., Ryan, P., Suchard, M., Hripcsak, G., Jin, P., Reich, C., Schwalm, M.-S., Khoma, Y., Wu, Y., Xu, H., Shah, N., Banda, J. & Schuemie, M. (2017). “Risk of Angioedema Associated with Levetiracetam Use: Findings of the Observational Health Data Sciences and Informatics”. Epilepsia Vol. 58(8), pр. e101-e106. 
13. Pinto, J. R., Cardoso J. S. & Lourenco, A. (2018). “Evolution, Current Challenges, and Future Possibilities in ECG Biometrics”. IEEE Access, Vol. 6, IEEE Access 6: pp. 34746-34776. 
14. Rajkomar, A., Dean, J. & Kohane, I. (2019). “Machine learning in medicine”. New England Journal of Medicine, 380(14), pp. 1347-1358. 
15. Zanini, R. A., Colombini E. L. & de Castro, M. C. F. (2019). “Parkinson’s Disease EMG Signal Prediction Using Neural Networks”. IEEE International Conference on Systems, Man and Cybernetics (SMC), Bari, Italy, pp. 2446-2453. 
16. Q. Gui, Z. Jin & W. Xu (2014). “Exploring EEG-based biometrics for user identification and authentication”. IEEE Signal Processing in Medicine and Biology Symposium (SPMB), pp. 1-6. 
17. Wieclaw, L., Khoma, Y., Falat, P., Sabodashko, D. & Herasymenko, V. (2017). “Biometric Identification from Raw ECG Signal Using Deep Learning Techniques”. The 9th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications. 21-23 September 2017, Bucharest, Romania, pp.129-133. 
18. (2012). Gacek, A., Pedrycz W. (Eds.). “ECG Signal Processing, Classification and Interpretation”. A Comprehensive Framework of Computational Intelligence. Verlag: Springer, London, 278 p. 
19. (2019). Hannun, A.Y., Rajpurkar, P., Haghpanahi, M. (et al.). “Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network”. Nat Med 25, pp. 65-69. 
20. Crone, B. (2011). “Multiphysiological Parameter Patient Monitoring”. Analog Devices, Inc. Technical Article, MS-2126. 
21. Von Luhmann, A., Wabnitz, H., Sander, T. & Muller, K.-R. (2017). “M3BA A Mobile, Modular, Multimodal Biosignal Acquisition Architecture for Miniaturized EEG-NIRS-Based Hybrid BCI and Monitoring”. IEEE Transactions on Biomedical Engineering, Vol. 64(6), pp. 1199-1210. 
22. Ahn, J. W.; Ku, Y. & Kim, H. C. (2019). “A Novel Wearable EEG and ECG Recording System for Stress Assessment”. Sensors 19, 1991, pp.1-14. 
23. Baby, B., Manikandan, M. S. & Soman, K. P. (2011). “Automated Cardiac Event Change Detection for Continuous Remote Patient Monitoring Devices”. In Proc.: 1st Int. Conf. on Wireless Techn. for Humanitarian Relief, pp. 225-232. 
24. Ng, K. A. & Chan, P. K. (2005). “A CMOS Analog Front-End IC for Portable EEG/ECG Monitoring Applications”. IEEE Transactions on Circuits and Systems, Vol. 52, (11), pp. 2335-2347. 
25. Celik, N., Manivannan, N. & Balachandran, W. (2016). “Evaluation of a Behind-the-Ear ECG Device for Smartphone based Integrated Multiple Smart Sensor System in Health Applications”. (IJACSA) Intern. J. of Advanced Comp. Sci&Appl., Vol. 7(7), pp. 409-418. 
26. Sasiadek, J. Z. (2002). “Sensor Fusion”. Annual Reviews in Contro, pp. 203-228. 
27. Khoma, V., Pelc, M., Khoma, Y. & Sabodashko, D. (2018). “Outlier Correction in ECGBased Human Identification”. In: Hunek W., Paszkiel S. (eds) (2018). “Biomedical Engineering and Neuroscience”. BCI Advances in Intelligent Systems and Computing, Vol. 720. pp. 11-22. Springer, Cham. 
28. Wrzuszczak, M. & Khoma, Y. (2016). “Wykorzystanie sztucznych sieci neuronowych do zmniejszenia błędów przetworników impedancji”. XLVIII Międzyuczelniana Konferencja Metrologów MKM`, AGH, Kraków, 5-7 września 2016 (in Polish). 
29. Khoma, V. V., Khoma, Y. V., Sabodashko, D. V. & Khoma, P. P. (2019). “Avtoenkodery dla opratsyuvannya promakhiv syhnaliv EKG u systemi biometrychnoyi avtentyfikatsiyi” [Autoencoder for ECG signal outlier processing in system of biometric authentication], Artificial Intelligence, No. 1-2, pp. 101-110 (in Ukrainian). 
30. Urigüen, J. A. & Garcia-Zapirain, B. (2015). “EEG artifact removal-state-of-the-art and guidelines”. J Neural Eng. 12 (3). pp. 2006-2015. 
31. Dudykevych, V. B., Khoma, V. V., Chekurin, V. F., Khoma, Y. V. & Sabodashko, D. V. (2019). “Normalizatsiya syhnaliv EKG dlya zastosuvannya v systemakh biometrychnoyi identyfikatsiyi”. [ECG signals normalization for systems of biometric identification]. Scientific notes of Taurida National V. I. Vernadsky University, Issue: Technical Science: Vol. 30 (69), Part 1, No. 4. pp. 49-56 (in Ukrainian). 
32. Khoma, Y. V. (2019). “Klasyfikatsiya vibroartrohrafichnykh syhnaliv z vykorystannyam khvylʹkovoho peretvorennya i tekhnolohiy mashynnoho navchannya”. [Classification of vibroartographic signals based on wavelet transformation and machine learning techniques]. Journal of Lviv Polytechnic National University “Information Systems and Networks”, Vol. 5, pp. 40-52 (in Ukrainian). 
33. Pelc, M., Khoma, Y. & Khoma, V. (2019). “ECG Signal as Robust and Reliable Biometric Marker: Datasets and Algorithms Comparison” Sensors, 19(10), 2350, pp. 1-8. 
34. (2018) “ADAS1000/ADAS1000- 1/ADAS1000-2 Low Power, Five Electrode Electrocardiogram”. Analog Front End. Data Sheet. Analog Devices. 85 p. 35. (2019). “ADS1299-x Low-Noise, 4-, 6-, 8- Channel, 24-Bit, Analog-to-Digital Converter for EEG and Biopotential Measurements”. Texas Instruments Incorporated. 83 p. 
36. Nikolayev, D. V., Smirnov, A. V., Bobrinskaya, I. G. & Rudnev, S. G. (2009). “Bioimpedansnyy analiz sostava tela cheloveka” [Bioelectric impedance analysis of human body composition]. Moscow, Russian Federation, Nauka, 392 p. (in Russian). 
37. Smajda, M., Khoma, V., Khoma, Y. & Otenko, V. (2019). “Zastosowanie technologii cyfrowego przetwarzania sygnałów w nowoczesnych układach reograficznych”. Przeglad Elektrotechniczny. R. 95, Nr. 11, pp. 231-237 (in Polish).

Received. 11.02.2020
Received after revision 14.02.2020
Accepted 19.02.2020
Last download:
29 June 2020

[ © KarelWintersky ] [ All articles ] [ All authors ]
[ © Odessa National Polytechnic University, 2018.]