Issue 2 (192), article 1

DOI:https://doi.org/10.15407/kvt192.02.005

Kibern. vyčisl. teh., 2018, Issue 2 (192), pp.

Fainzilberg L.S.1, Dr (Engineering), Professor,
Chief Researcher of the Department of Intelligent Automatic Systems
e-mail: fainzilberg@gmail.com
Matushevych N.A.2, Master student,
Faculty of Biomedical Engineering
e-mail: natalie.matushevych@gmail.com
1International Research and Training Center for Information Technologies
and Systems of the National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine, Acad. Glushkova av., 40, Kiev, 03187, Ukraine
2The National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute», Peremohy av., 37, Kiev, 03056, Ukraine

COMPARATIVE EVALUATION OF CONVERGENCE’S SPEED OF LEARNING ALGORITHMS FOR LINEAR CLASSIFIERS BY STATISTICAL EXPERIMENTS METHOD

Introduction. One of the main tasks of artificial intelligence is pattern recognition, which is often reduced to determining the discriminant function parameters in the multidimensional feature space. When recognizable objects can be completely separated by a linear discriminant function, the task is reduced to the linear classifier learning. There are many algorithms for linear classifiers learning, two of which are the Rosenblatt learning algorithm and the Kozinets algorithm.
The purpose of the article is to investigate the properties of the Rosenblatt and Kozinets learning algorithms on the basis of statistical experiment by the Monte Carlo method.
Methods. Two algorithms for linear classifiers learning have been studied: Rosenblatt and Kozinets. A number of researches have been performed to compare the convergence rate of algorithms for a different number of points and for their different location. Variation of the iterations number of algorithms spent on samples of different sizes was analyzed.
Results. Statistical experiments have shown that for a small sample size in approximately 20% of cases the convergence rates of the Rosenblatt and Kozinets algorithms are the same, but with the increase of observations number, the Kozinets learning algorithm proved to be the absolute leader. Also, the convergence rate of the Kozinets learning algorithm is less sensitive to the location of points in the learning sample.
Conclusions. The higher convergence rate of the Kozinets algorithm compared to the Rosenblatt algorithm, confirmed by a series of statistical experiments, allows formulating a promising research line on the evolution of neural networks where the Kozinets algorithm will be used to adjust the basic elements — perceptrons.

Keywords: Linear classifier, Rosenblatt algorithm, Kozinets algorithm.

Download full text!

REFERENCES

  1. Hastie T., Tibshirani R., Friedman J. The elements of statistical learning. NYk: Springer; 2014. 739 p.
  2. Bishop C.M. Pattern recognition and machine learning. NY: Springer; 2006. 738 p.
  3. Merkov A.B. Image recognition: Introduction to statistical learning methods. Moscow: URSS; 2011. 256 p. (In Russian).
  4. Vapnik, V. The nature of statistical learning theory. NY: Springer-Verlag; 1995. 188 p.
  5. Gori M. Machine Learning: A constraint-based approach. Waltham: Morgan Kaufmann; 2017. 580 p.
  6. Kodratoff Y., Michalski R.S. Machine learning: an artificial intelligence approach, Vol. 3. Elsevier; 2014. 825 p.
  7. Camastra F., Vinciarelli A. Machine learning for audio, image and video analysis: Theory and Applications. Madrid: Springer; 2015. 561 p.
  8. Schlesinger M, Hlavac V. Ten lectures on statistical and structural pattern recognition. Dodrecht/Boston /London: Kluwer Academic Publishers; 2002. 519 p.
  9. Burstein F., Holsapple Cl.W. Handbook on decision support systems 2: variations. NY: Springer; 2008. 798 p.
  10. Kung S.Y. Kernel methods and machine learning. Cambridge: Cambridge University Press; 2014. 591 p.
  11. Rosenblatt F. The perceptron: a probabilistic model for information storage and organization in the brain, Psychological Review. 1958. N. 65(6), P. 386–408.
  12. Kozinets B.N. A recursive algorithm for dividing the convex hulls of two sets. “Computer Science and Programming”. 1966. N. 4. P. 43–50.
  13. Novikoff A.B. On convergence proofs on perceptrons. Symposium on the Mathematical Theory of Automata. 1962. N. 12, P. 615–622.
  14. Vapnik V.N., Chervonenkis A.J. Theory of pattern recognision. Moscow: Nauka; 1974. 416 p. (In Russian).
  15. Buslenko N.P. The method of statistical modeling. Moscow: Statistics; 1970. 113 p. (In Russian).
  16. Rubinstein R.Y., Kroese D.P. Simulation and the Monte Carlo method(3 ed.). NY: John Wiley & Sons; 2016. 432 p.
  17. Robert C.P., Casella G. Monte Carlo statistical methods(2nd ed.). NY: Springer; 2004. 649 p.
  18. Trickey K.A. Structural models of coefficient of variation matrices. Los Angeles: University of California; 2015. 233 p.
  19. Kussul E., Baidyk T., Wunsch D.C. Neural networks and micromechanics. NY: Springer Science & Business Media; 2009. 221 p.
  20. Misuno I.S., Rachkovskij D.A., Slipchenko S.V. Experimental investigation of handwritten digit classification // System Technologies. 2005. Issue 4(39). P. 110–133.

Received 15.03.2018

Issue 3 (189), article 1

DOI:https://doi.org/10.15407/kvt189.03.005

Kibern. vyčisl. teh., 2017, Issue 3 (189), pp.

Orikhovska K.B., Postgraduate student,
Junior Researcher of the Department of Intelligent Automatic Systems
e-mail: kseniaor@gmail.com
Fainzilberg L.S., Dr (Engineering), Associate Professor (Docent), Chief Researcher of Data Processing Department
e-mail: fainzilberg@gmail.com

International Research and Training Center for Information Technologies and Systems of the NAS of Ukraine and Ministry of Education and Science of Ukraine,
Acad. Glushkova av., 40, Kiev, 03680, Ukraine

COMPARATIVE ANALYSIS OF ESTIMATION METHODS OF THE PHYSIOLOGICAL SIGNALS VARIABILITY

Introduction. In the modern world, more attention is paid to the study of the behavior of complexly organized medical and biological systems. The fundamental concept of synergetics is the generalized entropy, which quantitatively characterizes the degree of the system chaoticness. Of special interest are studies of changes in the dynamic series chaotic parameters generated by various biological systems.
The purpose of the article is further development and experimental research of methods for analyzing the variability of physiological signals under external influences on the body.
Methods. Two alternative approaches of estimating the variability of dynamic series are investigated: based on the calculation of the sample variance relative changes and entropy estimates (in a sliding window with the specified parameters) in relation to the first window. The theoretical and experimental dependences between the Shannon entropy and the standard deviation for a normal distribution of a random variable that generates a dynamic series are studied. Comparison of these estimates with real and model data is carried out.
Results. To increase the sensitivity of entropy estimates to the variability of the dynamic series, it is proposed to move from a series of discrete entropy values at the -th point, calculated by the sliding window method, to its phase portrait on the plane , where is the estimate of the first derivative . For an integral assessment of the chaotic nature of physiological signals, it is suggested to estimate the area of the convex hull of the entropy phase portrait and the coordinates of the phase portrait gravity center , . Experimental studies have confirmed the diagnostic value of these parameters in the assessment of variability of the electrocardiograms and rhythmograms indices with external influences on the body (intravenous therapy, surgery and physical activity).
Conclusions. Deviations of the integral parameters of the entropy phase portrait under the effect of external influences on the organism were detected, which open new possibilities in the evaluation of the cardiac activity regulation in preventive and clinical medicine. These integral parameters require further study to confirm their statistical significance in representative samples of observations.

Keywords: variability of physiological signals, entropy estimates, diagnostic criteria.

Download full text!

REFERENCES

1 Klimontovich Yu.L. Introduction to physics of open systems. Moscow: Janus–K; 2002. 284 p.

2 Martin-Sanchez F., Iakovidis I., Norager S., Maojo V., de Groen P., Van der Lei J., Jones T., Abraham-Fuchs K., Apweiler R., Babic A., Baud R., Breton V. Synergy between medical informatics and bioinformatics: facilitating genomic medicine for future health care. Journal of Biomedical Informatics. 2004. Vol. 37. N 1. P. 30–42.
https://doi.org/10.1016/j.jbi.2003.09.003

3 Weippert M., Behrens M., Rieger A., Behrens K. Sample entropy and traditional measures of heart rate dynamics reveal different modes of cardiovascular control during low intensity exercise. Entropy. 2014. Vol. 16. P. 5698–5711.
https://doi.org/10.3390/e16115698

4 Durnova N.Yu., Dovgalevskiy Ya.P., Burlaka A.N., Kiselev A.R., Furman N.V. Interdependence of parameters of variational pulsometry, entropy of heart rate, temporal and spectral analyses of heart rate variability in normal state and in ischemic heart disease. Saratov journal of medical scientific research. 2011. Vol. 7. N 3. P. 607–611.

5 Ban A.S., Paramonova N.A., Zagorodnyy G.M., Ban D.S. Analysis of the relationship of heart rate variability indices. Voennaya Meditsina. 2010. N 4. P. 21–24.

6 Joshua S., Richman J., Moorman R. Physiological time-series analysis using approximate entropy and sample entropy. The American journal of physiology. 2000. Vol. 278. N 6. P. 2039–2049.

7 Peng C.K., Havlin S., Stanley H.E., Goldberger A.L. Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. Chaos. 1995. Vol. 5. P. 82–87.
https://doi.org/10.1063/1.166141

8 Iyengar N., Peng C.K., Morin R., Goldberger A.L., Lipsitz L.A. Age-related alterations in the fractal scaling of cardiac interbeat interval dynamics. Am. J. Physiol. 1996. Vol. 271. P. 1078–1084.
https://doi.org/10.1152/ajpregu.1996.271.4.R1078

9 Mayorov O.Yu., Fenchenko V.N. Calculation of the correlation dimestion and entropy of EEG signals in cluster computing systems. Clinical informatics and telemedicine. 2014. Vol. 10. N 11. P. 10–20.

10 Anishchenko V.S., Saparin P.I. Normalized entropy as a diagnostic criterion of human cardio-vascular system reaction on the external influence. Izvestia VUZ. Applied nonlinear dynamics. 1993. Vol. 1. N 3–4. P. 54–64.

11 Shapovalov V.I. About the fundamental laws of trend management. Control Science. 2005. Vol. 2. P. 2–11.

12 Yashin A.A. Living matter. Physics of the alive and evolutionary processes. Moscow: LKI, 2010. 264 p.

13 Zhukovska O.A., Glushauskene G.A., Fainzilberg L.S.Research of the modified estimation properties of random variable’s variance on sample of different observations. Naukovi Visti NTUU KPI. 2008. N 4. P. 139–145.

14 Fainzilberg L.S., Orikhovska K.B., Vakhovskyi I.V. Assessment of chaotic fragments’ shape of the single-channel electrocardiogram.Cybernetics and computer engineering. 2016. Vol. 183. P. 4–24.

15 Gorban I.I. Entropy of uncertainty. Mathematical Machines and Systems. 2013. N 2. P. 105–117.

16 Afanasyev V.V. Theory of Probability: a textbook for university students studying in the specialty “Mathematics”. M.: The Humanitarian publishing center VLADOS, 2007. 350 p.
https://doi.org/10.1137/S0040585X97982700

17 Kramarenko S.S. Method of use of the entropy-information analysis for quantitative attributes. Proceedings of the Samara Scientific Center of the RAS. 2005. Vol. 7. N 1. P. 242-247.

18 Fainzilberg L.S. Information technology for signal processing of complex shape. Theory and practice. Kiev: Naukova Dumka, 2008. 333 p.

19 Fainzilberg L.S. Fasegraphy basics. Kyiv: Osvita Ukrainy, 2017. 264 p.

20 Rosenbaum D.S., Jackson L.E., Smith J.M. Electrical alternans and vulnerability to ventricular arrhythmias. New England Journal of Medicine. 1994. Vol. 330. P. 235–241.
https://doi.org/10.1056/NEJM199401273300402

21 Fainzilberg L.S., Bekler T.Yu. T-Wave Alternats Modeling on artificial electrocardiogram with internal and external perturbation. Journal of Automation and Information Sciences. 2012. Vol. 44. N 7. P. 1–14.
https://doi.org/10.1615/JAutomatInfScien.v44.i7.10

22 Vlasova I.V. There are more and more side effects in drugs. Commercial biotechnology. 2007. Vol. 10. P. 14–19.

Received 5.06.2017

Issue 1 (187), article 2

DOI: https://doi.org/10.15407/kvt187.01.011

Kibern. vyčisl. teh., 2017, Issue 1 (187), pp.11-30

L.S. Fainzilberg, Doctor of Engineering, Associate Professor (Docent),
Chief Researcher of Data Processing Department

e-mail: fainzilberg@voliacable.com

International Research and Training Center for Information Technologies and Systems of the NAS of Ukraine and Ministry of Education and Science of Ukraine,
av. Acad. Glushkova, 40, Kiev, 03680, Ukraine

INTERACTIVE SYNTHESIS OF INFORMATION TECHNOLOGY SIGNALPROCESSING WITH LOCALIZED INFORMATION

Introduction. Current task that inevitably arises before the designer of information technology (IT) signal processing with localized information — selection and setup of intelligent computational procedures to ensure an effective transition from the signal distorted by internal and external perturbations to the information products targeted at specific user.

The purpose of the article is to summarize the experience in the development of IT applications for the analysis and interpretation of the signals with localized information using an open tool for the expansion of the instrumental system.

Methods. On the basis of the object-oriented approach and IT tasks analysis, focused
on the extraction of diagnostic information from the distorted signal with a locally-focused features, held decomposition of the general problem of applied IT synthesis in different
applications.

Results. Generalized model of IT analysis and signals of complex shape interpretation has been developed. The development system architecture is proposed, the core of which is based on two abstract classes — a data carrier generalized model (DCM) and the generalized data processing model (DPM). On the basis of the heirs of these classes set up a set of basic computational component, ensuring the recovery of the useful signal monitoring in terms of internal and external disturbances, detection of informative reconstructed signal fragments, analysis of amplitude-time parameters (diagnostic indicators), focusing on the detected fragments and implementation of diagnostic rules, provides an assessment of the state of the object by the calculated characteristics.

Methodology of the experiments evidence with elements of the deductive approach, which is demonstrated by the example of the original evaluation index electrocardiogram is proposed.

Conclusions. The developed instrumental system allows to accelerate the development of the new IT processing of complex shape signals and to improve its effectiveness. Examples of the successful synthesis of applied information technologies for processing signals with localized information created using the developed instrumental system are given.

Keywords: information technology, complex shape signals, instrumental system.

Download full text (ru)!

REFERENCE

1 Fainzilberg L.S. Information technology for signal processing of complex shape. Theory and practice. Kiev: Nauk. Dumka, 2008. 333 p (in Russian).

2 Gritsenko V.I., Fainzilberg L.S. Computer diagnostics using complex-form signals under conditions of internal and external disturbances. Reports of the NAS of Ukraine. 2013. No 12. P. 36–44 (in Russian).

3 Technology. Soviet Encyclopedic Dictionary. Moscow: Sovetskaya entsiklopediya, 1988. P. 1330 (in Russian).

4 Fainzilberg L.S. Intelligent features and development prospects of fazagraphy — information technology processing complex shape signals. Kibernetika i vycislitelnaa tehnika. 2016. Iss. 186. P. 56–77 (in Russian).

5 Fainzilberg L.S. Computer diagnostics by phase portrait of electrocardiogram. Kiev: Osvita Ukrainy, 2013.191 p. (in Russian).

6 Fainzilberg L.S. Tool system for experimental evaluation of the effectiveness of processing algorithms for signals of complex shape. Control systems and machines. 2008. Vol. 2. P. 3–12, 53 (in Russian).

7 Zenkin A.A. Cognitive Computer Graphics. Moscow: Nauka, 1991. 192 p. (in Russian).

8 Fainzilberg L.S. Nowa metoda interpretacji zapisu EKG w balaniach skriningowych oraz w opiece domowej. Zdrowie publiczne (Public Health). 2005. Vol. 115. No 4.P. 458–464.

9 Fainzilberg L.S., Glushauskene G.A. Narrow-band Rejection Filter for Suppression of Harmonic Concentrated Interference on the Basis of Discrete Fourier Transform . Journal of Automation and Information Sciences. 2009. Vol. 41. Iss. 8. P. 55–70.

10 Fainzilberg L.S. Adaptive smoothing of noise in information technology processing of physiological signals. Mathematical Machines and Systems. 2002. No 3. P. 96–104.(in Russian).

11 Fainzilberg L.S. Restoration of a standard sample of cyclic waveforms with the use of the Hausdorff metric in a phase space. Cybernetics and Systems Analysis. 2003. No 3. P. 20–28 (in Russian).

12 Minzer O.P. Theory and practice of evidence-based medicine. Diagnosis and treatment. 2004. No 3. P. 7–15 (in Russian).

13 Fainzilberg L.S. FASEGRAPH — efficient information technology of ECG processing in the problem of ischemic cardiac disease screening. Clinical Informatics and Telemedicine. 2010.Vol. 6. Iss. 7. P. 22–30 (in Russian).

14 Schijvenaars B.J.A, Van Herpen G., Kors J.A. Intraindividual variability in electrocardiograms. Journal of Electrocardiology. 2008. Vol. 41. Iss. 3. P. 190–196.
https://doi.org/10.1016/j.jelectrocard.2008.01.012

15 Fainzilberg L.S. Simulation models of generating artificial cardiograms in terms of internal and external disturbances. Journal of Qafgaz University — Mathematics and Computer Science. 2012. No 34. P. 92–104 (in Russian).

16 Method for verification of metrological characteristics of digital electrocardiographs: UA Patent 100330:MPK G01 D21/00. No a 2011 11909, Bul. No 23. P. 6. 2012 (in Ukrainian).

17 Gritsenko V.I., Fainzilberg L.S. Personified digital medicine tools — step to health. Herald of the NAS of Ukraine. 2012. No 8. P. 62–70 (in Ukrainian).

18 Gritsenko V.I., Fainzilberg L.S. FASEGRAPH — information technology for the integrated assessment of the cardiovascular system state of the electrocardiogram phase portrait. Information technologies for the Physician. 2013. No 3. P. 52–63 (in Russian).

19 Vasetsky Y.M., Fainzilberg L.S., Chaikovsky I.A.Methods of structure analysis of current distribution in conducting medium for magnetocardiography. Electronic modeling. 2004. No 3. P. 95–115 (in Russian).

20 Fainzilberg L.S. Diagnostics of object state by phase trajectories of observed signals with locally concentrated features. Problems of Control and Informatics. 2004. No 2. P. 56–67 (in Russian).

21 Fainzilberg L.S., Kondratyuk T.V., Semergey N.A. ANTISTRESS — A New Information Technology for the Management of Regulatory Systems of a Human Body Based on the Biofeedback. Control systems and machines. 2011. No 3. P. 62–72 (in Russian).

22 Fainzilberg L.S., Korchynska Z.A., Semerhey M.O.Program-technical complex for study of a new method for biometric identification by phase portrait of electrocardiogram. Forensic Herald. 2015. No 1(23). P. 63–71 (in Ukrainian).

Recieved 22.12.2016

Issue 186, article 6

DOI:https://doi.org/10.15407/kvt186.04.056

KVT, 2016, Issue 186, pp.56-78

UDC 681.3.06.14

INTELLECTUAL CAPABILITIES AND PERSPECTIVES FASEGRAPHY DEVELOPMENT — INFORMATION TECHNOLOGY OF COMPLEX FORM SIGNAL PROCESSING

Fainzilberg L.S.

International Research and Training Center for Information Technologies and Systems of the National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine, Kiev, Ukraine

fainzilberg@voliacable.com

Introduction. Recently, a new class of information technologies (IT) — intelligent IT is widespread which, unlike traditional, operate generalized concepts — images, and provide more complete information about the external environment. One of the tasks requiring the involvement of intelligent IT — analysis and interpretation of complex form signals with a locally-focused information.

The purpose of the article is — to formulate the basic properties of intelligent IT complex form signal processing, demonstrate the ability to implement these features on the example of the innovative method fasegraphy and outline prospects for further development of this technology.

Methods. Fasegraphy is a high IT which is processing different complex form signals of physical nature, which, basing on a chain of intelligent computational procedures, enables the transition from the observed signal with a locally-focused features (raw material for technology) to information which is focused on a particular user (technology product). The main task of the scientific method fasegraphy aims to detect general laws of indicated signals to identify and use in practice the most effective computational procedures that can ensure this transition.

Results. Basic properties of intelligent IT — adaptation, learning, generalization, invariance, forecasting, understanding, flexibility, interoperability, accessibility have been formulated. Analysis of computational procedures chain in fasegraphy method, that provide a transition from the actually observed signals to technology product, shows that the method has all of the above properties, and therefore fasegraphy can be referred to intelligent ITs. New results have been presented from fasegraphy usage in pediatric cardiology and outlined prospects for the development of this method in two ways — by increasing the reliability of decision making in single-channel ECG and realization of intelligent processing tasks of other signals with locally-focused features.

Conclusions. Fasegraphy intelligent capabilities are far from exhausted and can be used to solve actual scientific and applied problems not only in cardiology but also in other applications.

Keywords: fasegraphy, information technology, complex shape signals, electrocardiogram.

Download full text (ru)!

Reference

  1. Omelchenko V.O. Orthogonal expansions of random signals and fields. Кiev: UMKVO, 1991, 142 p. (in Ukrainian).
  2. Murashko V.V., Strutynsky A.V. Electrocardiography. Moscow, 1991, 288 p. (in Russian).
  3. Primin M.A., Nedajjvoda I.V., Vasilev V.E. New algorithms for magnitokardiosignal processing. Control systems and machines, 1998, № 2, pp.48–62. (in Russian).
  4. Ronkin М.А., Ivanov L.B. Rheography in clinical practice. Moscow: SMC MBN, 1997, 250 p. (in Russian).
  5. Piloian G.О. Introduction to Thermal Analysis. Moscow, 1964, 231 p. (in Russian).
  6. Gritsenko V.I., Fainzilberg L.S. FASEGRAPH® — information technology for the integrated assessment of the cardiovascular system state of the electrocardiogram phase portrait. Information technologies for the Physician, 2013, № 3, pp.52–63. (in Russian).
  7. Fainzilberg L.S. Computer diagnostics by phase portrait of electrocardiogram. Kiev, 2013, 191 p. (in Russian).
  8. Katerinchuk I.P., Borisenko N.B. Heart rate variability and autonomic dysfunction in patients with metabolic syndrome. Arrhythmology, 2012, № 3(3), pp. 6–13. (in Ukrainian).
  9. Pavlichencko P.P. The influence of the playing load on the functional status of professional football players. World of medicine and biology, 2015, № 1(48), pp. 49–54. (in Russian).
  10. Ozhegov vocabulary. Available at: URL: http://ozhegov-online.ru/slovar-ozhegova/texnologiya/34888/
  11. Fainzilberg L.S. Information technology for signal processing of complex shape. Theory and practice. Kiev, 2008, 333 p. (in Russian).
  12. Gritsenko V.I. Intellectualization of Information Technologies. Science & Technology. Kiev: V.M. Glushkov Institute of Cybernetics of NAS of Ukraine, 1992, pp. 4–9. (in Ukrainian).
  13. Hawkins D., Blakeslee S. On intelligence. Moscow, St. Petersburg, Kiev, 2007, 128 p. (in Russian).
  14. Preston J., Bishop M. Views Into the Chinese Room: New Essays on Searle and Artificial Intelligence. Oxford, 2002, 410 p.
  15. Fainzilberg L.S. Simulation models of generating artificial cardiograms in terms of internal and external disturbances. Journal of Qafgaz University Mаthеmаtics and Computer Science, 2012, № 34, pp. 92–104. (in Russian).
  16. Fainzilberg L.S., Glushauskene G.A. Narrow-band Rejection Filter for Suppression of Harmonic Concentrated Interference on the Basis of Discrete Fourier Transform. Journal of Automation and Information Sciences, 2009, Vol. 41, Iss. 8. pp. 55–70.
  17. Fainzilberg L.S. Adaptive smoothing of noise in information technology processing of physiological signals. Mathematical Machines and Systems, 2002, № 3, pp. 96–104. (in Russian).
  18. Zywienz C., Borovsky D., Goettsch G.& others Methodology of ECG Interpretation in the Hanover Program. Meth. Inf. Med, 1990, № 29, pp. 375.
  19. Gritsenko V.I., Fainzilberg L.S. Computer diagnostics using complex-form signals under conditions of internal and external disturbances. Reports of the National Academy of Sciences of Ukraine, 2013, № 12, pp. 36–44. (in Russian).
  20. http://fainzilberg.irtc.org.ua/files/adaptiv.pdfFrumin L.L., Shtarck M.B. About ECG phase portrait. Avtometriya, 1993, № 2, pp. 51–54. (in Russian).
  21. Fainzilberg L.S. A method of personalized assessment of functional state of human cardiovascular system. UA Patent112325. 2016. Bul. 16. (in Ukrainian).
  22. Fainzilberg L.S. The Performance Evaluation of Information Technology FASEGRAPH® According to the Independent Studies. Control systems and machines, 2014, № 2, pp. 84–92. (in Russian).
  23. Maydannik V.G., Khaitovych N.V., Fainzilberg L.S. & others The symmetry of the T-wave on the electrocardiogram as a marker of cardiometabolic risk in schoolchildren. International Journal of Pediatrics, Obstetrics and Gynecology, 2013, Vol. 4, № 3, pp. 35–39. (in Russian).
  24. Morozik А.А., Fainzilberg L.S. Diagnostic value of electrocardiosignal combined analysis on phase plane and heart rate variability in children with diabetic cardiomyopathy. International Journal of Pediatrics, Obstetrics and Gynecology, 2015, Iss. 7, № 1, pp. 11– 17. (in Russian).
  25. Kondratiuk A.S., Garkaviy S.I., Korshun M.M. & others.Evaluation of primary school pupil’s functional state in physical education classes and swimming lessons dynamics. Hygiene of settlements, 2014, № 64, pp. 302–308. (in Ukrainian).
  26. Fainzilberg L.S., Orikhovska K.B., Vakhovskyi I.V. Assessment of chaotic fragments shape of the single-channel electrocardiogram. Kibernetika i vyčislitelʹnaâ tehnika, 2016, № 183, pp. 4–24. (in Russian).http://fainzilberg.irtc.org.ua/files/KIVT_2016_1.pdf
  27. Fainzilberg L.S. Method of evaluating the adequacy of reaction to load UA Patent 103229. 2015. Bul. 23. (in Ukrainian).
  28. Fainzilberg L.S., Soroka Т.V. Development of telemedicine system for remote monitoring of heart activity based on fasegraphy method. East Europe Journal of Enterprise Technologies, 2015, № 6/9(78), pp. 37–46.
  29. Fainzilberg L.S. Method for person identification by electrocardiogram UA Patent 105273. 2014. Bul. 8. (in Ukrainian).

Received 27.09.16

Issue 184, article 2

DOI:https://doi.org/10.15407/kvt184.02.008

KVT, 2016, Issue 184, pp.8-25

UDC 681.3.06.14

MOBILE APPLICATIONS FOR VIRTUAL INTERACTION OF PHYSICIAN AND PATIENT DURING REMOTE MONITORING OF HEART ACTIVITY

Fainzilberg L.S.1, Soroka T.V.2

1International Research and Training Center for Information Technologies and Systems of National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine, Kiev, Ukraine

2National Technical University of Ukraine “Kiev Polytechnical Institute”, Kiev, Ukraine

fainzilberg@voliacable.com , grais.victory@gmail.com

Introduction. The diseases of cardiovascular system lead in the structure of morbidity. The absence of timely treatment leads to severe complications, invalidity and death of the patient. Only preserving medicine can radically change this situation. Fasegraphy is one of perspective directions in cardiology, that allows even by simplified way of ECG registration to detect early signs of disease development.

Purpose. The development of method of fasegraphy for building of complex telemedicine system for mass prophylactic examinations based on client-server architecture and realization of mobile applications for patients and physicians in Android environment is proposed.

Methods. The portable sensor is used for registration of ECG signal, that provides the transfer of digital data through Bluetooth to the patient’s application. The application provides preprocessing of signal, the control of dosed exercise, stress and transfer data to server. The client’s applications are developed in a java programming language version 7 together with Android sdk. The software of server is written in Java version 8 in conjunction with frameworks Spring 4.3 for REST API and Hibernate 5.1 as ORM. The database is based on MySql 5.5.

Results. The server software provides automatic selection of ECG with atypical cycles for which the physician must pay attention primarily. The algorithm of selection is based on the analysis of ordered Hausdorff distances between trajectories of cycles on the phase plane. When the information about detection of atypical cycles is received, the physician may view ECG, perform additional analysis those ECGs and send appropriate recommendations to patient.

Conclusions. Client-server organization of interaction of physician and patient increases the effectiveness of screening surveys and optimizing time spent by a doctor on the medical services to their patients.

Keywords: client-server system, fasegraphy, distant monitoring, atypical cycles of ECG.

Download full text (ru)!

References:

1 Cassar A., Holmes D.R., Rihal C.S. et al. Chronic coronary artery disease: diagnosis and management. Mayo Clin. Proc., 2009, Vol. 84, No 12, pp. 1130–1146. https://doi.org/10.4065/mcp.2009.0391

2 Basso C., Corrado D., Thiene G. Prevention of sudden cardiac death in the young and in athletes: dream or reality? Cardiovascular Pathology. 2010, Vol. 19, No 4, pp. 207–217. https://doi.org/10.1016/j.carpath.2009.04.001

3 Thaulow E., Erikssen J., Sandvik L. et al. Initial clinical presentation of cardiac disease in asymptomatic men with silent myocardial ischemia and angiographically documented coronary artery disease (the Oslo Ischemia Study). American Journal of Cardiology, 1993, Vol. 72, No 9, pp. 629–633. https://doi.org/10.1016/0002-9149(93)90875-D

4 Gozhenko A., Kulbida M., Kochetov A. Preventive medical science strategy — a way to improve the efficiency of health care. Journal of National Academy of Sciences of Ukraine, 2011, No 12, pp. 64–69 (in Ukrainian).

5 Solopov V., Sadykova A., Fedoseyeva T. Restrictions of automatic analysis of computer. Kazansky Medical Journal, 2012, T.93, No 4, pp. 687-691 (in Russian).

6 Lourenco A. Unveiling the Biometrical Potential of Finger-Based ECG Signals. Computational Intelligence and Neuroscience, 2011, Vol. 2011, pp. 1–8. https://doi.org/10.1155/2011/720971

7 Grier J.W. Comparison and review of portable, handheld, 1-lead/channel ECG / EKG recorders. Available at https://www.ndsu.edu/pubweb/~grier/Comparison-handheld-ECG-EKG.html

8 Fainzilberg L.S. Computer diagnosis of the phase portrait of the electrocardiogram. Kiev: Osvita Ukrainy, 2013, 191 p. (in Russian).

9 Fainzilberg L.S. ECG Averaging based on Hausdorff Metric. International Journal of Biomagnetism, 2003, Vol. 5, No 1, pp. 236–237.

10 Fainzilberg L.S. Nowa metoda interpretacji zapisu EKG w balaniach skriningowych oraz w opiece domowej. Zdrowie publiczne (Public Health), 2005, Vol. 115, No 4, pp.458–464.

11 Matjaz Perc. Nonlinear time series analysis of the human electrocardiogram. European Journal of Physics, 2005, No 26, pp. 757–768.

12 Minina E.H., Fainzilberg L.S. Analysis of the functional condition of the cardiovascular system of the combination of features of the phase portrait of single-channel ECG. Russian Cardiology Journal, 2015, No 12 (128), pp. 7–13 (in Russian).

13 Fainzilberg L.S. Information signal processing technology complex shape. Theory and practice. Kiev: Scientific Thought, 2008, 333 p. (in Russian).

14 Gritsenko V.Y., Fainzilberg L.S. Information technology of FAZAGRAF for the integrated estimation of the cardiovascular’s system condition on phase portrait of electrocardiogram. Doctor and Information Technology, 2013, No 3, pp.52–63 (in Russian).

15 Vishnevsky V.V. Grid-based system for mass storing and and processing of digital electrocardiograms. Ukrainian Journal of Telemedicine and Medical Telematics, 2013, E. 11, No 1, pp. 202–208 (in Russian).

16 Fainzilberg L.S., Soroka T.V. The development of telemedicine systems for remote monitoring heart activity based on the method of fasegraphy. East European Journal of advanced technologies, 2015, No 6/9(78), pp. 37–46 (in Russian).

17 Kaya Y., Pehlivan H. Classification of Premature Ventricular Contraction in ECG. International Journal of Advanced Computer Science and Applications, 2015, Vol. 6. No 7, pp. 34–40. https://doi.org/10.14569/IJACSA.2015.060706

18 Goldberger A.L. Fractal mechanisms in the electrophysiology of the heart. IEEE Eng. Med. Biol., 1992, No 11, pp. 47–52.

19 Genkin A.A. The new information technology of medical data analysis. SPB: Polytechnic, 1999, 192 p. (in Russian).

Received 28.04.16

Issue 183, article 1

DOI:https://doi.org/10.15407/kvt183.01.005
Fainzilberg Leonid S., Dr of Engineering, Chief Researcher of Data Processing Department of International Research and Training Center for Information Technologies and Systems National Academy of Sciences of Ukraine and of Ministry of Education and Science of Ukraine, av. Acad. Glushkova, 40, Kiev, 03680.
e-mail: fainzilberg@voliacable.com

Orikhovska Kseniya B.,Postgraduate (PG) of International Research and Training Center for Information Technologies and Systems National Academy of Sciences of Ukraine and of Ministry of Education and Science of Ukraine, av. Acad. Glushkova, 40, Kiev, 03680,
e-mail: kseniaor@gmail.com

Vakhovskyi Ivan V., Student of National Technical University of Ukraine “Kiev Polytechnical Institute”, av. Pobedy, 37, Kiev, 03056,
e-mail: evanvaha@gmail.com

ASSESSMENT OF CHAOTIC FRAGMENTS’ SHAPE OF THE SINGLE-CHANNEL ELECTROCARDIOGRAM. Kibernetika i vyčislitel’naâ tehnika, 2016, issue 183, pp.4-24.

Introduction. Building an effective information technology (IT), which provides chaotic assessment of the electrocardiogram (ECG) fragments’ shape, has both cognitive and practical importance. Therefore, the problem of developing methods and computer tools that provide assessment not only by the rhythm of the heart, but also on other parameters of ECG that have diagnostic value is relevant.

The purpose of the article is to propose instrumental system for the study of single-channel ECG elements shape chaoticity, based on the various entropy assessments and make a comparative analysis of these estimates in the model and the real data.

Methods. The proposed instrumental system based on the national portable electrocardiograph FAZEGRAF® with the original finger electrodes sensor, which can record the ECG from the first standard lead. In addition to determining the chaoticity of parameters, that characterize the shape of the main elements of the ECG, also estimating the diagnostic features chaoticity. Introduced a number of improvements in the considered methods which determine the signal chaoticity degree. In particular, an original evaluation algorithm for permutation entropy evaluating that can automatically identify 5 classes of patterns is proposed.

Results. Processing of model and real data showed that the computing algorithms implemented in IT allow to adequately assessing the degree of signals chaoticity. Based on the parameters chaotic assessment, that carry information about the ECG elements shape, diagnostically important subtle signal differences in healthy and sick patients, as well as significant differences in parameters of the ECG elements shape chaoticity in people with varying degrees of organism fitness were found.

Conclusions. Instrumental system provides the convenience of experimental studies with searching for new biomarkers of cardiac abnormalities and evaluation of organism adaptation capabilities.

Keywords: heart rate, the entropy of the process, synergy, shape of ECG fragments.

Download full text (ru)!

References

1 Tuzov V.V. Methods of synergetics. Bibliosphere, 2009, No. 4, pp. 8–14. (in Russian).

2 Bian C., Qin C., Ma Q.D. et. al. Modified permutation-entropy analysis of heartbeat dynamics. Physical Review E, 2012, No. 85.

3 Parlitz U., Beg S.L., Schirdewan S. et al. Classifying cardiac biosignals using ordinal pattern statistics and symbolic dynamics. Computers in Biology and Medicine, 2012, No. 42, pp. 319–327. https://doi.org/10.1016/j.compbiomed.2011.03.017

4 Frank B., Pompe B., Schneider U. et al. Permutation entropy improves fetal behavioural state classification based on heart rate analysis from biomagnetic recordings in near term fetuses. Medical & Biological Engineering & Computing, 2006, No. 44, pp. 179–187. https://doi.org/10.1007/s11517-005-0015-z

5 Durnova N.Y., Dovgalevskij Y.P., Burlaka A.N. et al.The study of relationships between parameters of variation pulsometry, entropy of heart rate, time and spectral analysis of heart rate variability in normal and ischemic heart disease. Saratov Medical Scientific Research Journal, 2011, Vol. 7, No. 3, pp. 608–611. (in Russian).

6 Wentsel E.S. Theory of probability. Moscow: Science, 1969, 575 p. (in Russian).

7 Kuznecov A.A. Methods of analysis and processing of ECG signals: new approaches to information extraction: monograph. Vladimir: Vladimir State University Publishing, 2008, 140 p. (in Russian).

8 Sotnikov P.I. Isolation of the characteristic features of a EEG signal by the entropy analyzing. Science and Education, 2014, No. 11, pp. 555–570. (in Russian).

9 Nermiko A.P., Manilo L.A., Kalinichenko A.N. et.al. Comparative analysis of the different estimates usage of the EEG signal entropy for recognizing the anesthesia stages. Biotechnosphere, 2010, No. 3, pp. 3–10. (in Russian).

10 Takens F. Detecting strange attractors in turbulence. Dynamical systems and turbulence: lecture notes in mathematics, 1981, Vol. 898, pp. 366–381.

11 Pincus S.M. Approximate entropy as a measure of system complexity. Proc. of the National Academy of Sciences, 1991, Vol. 88, pp. 2297–2301. https://doi.org/10.1073/pnas.88.6.2297

12 Danilchuk A.B. Using entropy parameters for simulating the dynamics of complex social and economic systems. Economics, 2014, No. 3, pp. 19–24. (in Russian).

13 Jushkovskaja O.G. A new approach to assessing the effectiveness of sanatorium rehabilitation of patients with coronary heart disease. Physical education in the prevention, treatment and rehabilitation, 2004, No. 1, pp. 22–26. (in Russian).

14 Costa M., Ary L., Goldberger A.L. Multiscale entropy analysis of biological signals. Physical Review E, 2005, No. 71.

15 Pincus S.M., Goldberger A.L. Physiological time-series analysis: what does regularity quantify? The American journal of physiology, 1994, Vol. 266, pp. 1643–1656. https://doi.org/10.1152/ajpheart.1994.266.4.H1643

16 Joshua S. Richman J., Moorman R. Physiological time-series analysis using approximate entropy and sample entropy. The American journal of physiology, 2000, Vol. 278, No. 6, pp. 2039–2049.

17 Bandt C., Pompe B. Permutation entropy — a natural complexity measure for time series. Chinese Physics B, 2001, Vol. 18, No. 7, pp. 2690–2696.

18 Antipov I.E., Zakharov A.V., Poverennova O.I. The possibilities of different methods of automatic recognition of sleep stages. Saratov Medical Scientific Research Journal, 2012, Vol. 8, No. 2, pp. 374–379. (in Russian).

19 Mun F. Chaotic oscillations: Introductory course for scientists and engineers: Trans. from English. Moscow: Mir, 1990, 312 p. (in Russian).

20 Mayorov O.Y., Feshchenko V.N. Improving the reliability of studies of deterministic chaos in the bioelectric activity (EEG, ECG and heart rate variability) methods of nonlinear analysis. Clinical Informatics and Telemedicine, 2009, Vol. 6, No 6, pp. 10–17. (in Russian).

21 Kiseleva O.G., Nastenko Ie.A., Gerasimchuk M.V. Method of estimation disadaptation states of the human body. East European Journal of advanced technologies, 2011, Vol. 3, No. 2, pp. 57–64. (in Russian).

22 Zinenko A.V. R/S analysis of the stock market. Business Informatics, 2012, No 3, pp. 24–30. (in Russian).

23 Apanasenko G.L., Chistyakova Yu. S. Athlete’s Health Criteria evaluation and prediction. Theory and Practice of Physical Culture, 2006, No 1, pp.19–22. (in Russian).

24 Fainzilberg L.S. Computer diagnostics by phase portrait of electrocardiogram. Kiev: Osvita Ukrainy, 2013, 191 p. (in Russian).

25 Zaguskin S.L., Borisov V.A. A method for diagnosing the functional state of human and animal. RU Patent 2254051, 2006, bul. 13. (in Russian).

Received 08.12.2015

 

ISSUE 181, article 1

DOI:https://doi.org/10.15407/kvt181.01.005

Kibern. vyčisl. teh., 2015, Issue 181, pp.

Fainzilberg L.S., Orikhovska K.B.

International Research and Training Center for Information Technologies and Systems of National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine

INFORMATION TECHNOLOGY OF THE ORGANISM ADAPTATION RESERVES ASSESSMENT IN FIELD CONDITIONS

Introduction. Building an effective IT that provides an assessment of the reserve capacity of the organism to physical and emotional overload has both cognitive and practical importance. The relevance of such IT is increasing in our time since it is necessary to provide reliable results in field conditions. This requires prompt, convenient and reliable tools for obtaining test results, which is to be clear not only the decision maker, but also to the examinee that has no medical education.
The purpose of the article is to propose a new information technology for assessing the adequacy the body’s reaction and recovery processes of the cardiovascular system of a human on a set of single-channel ECG parameters.
Methods. The proposed IT includes a set of interacting modules, in particular input module and ECG processing module, which realized on FAZAGRAF® complex. This complex provides recording of the ECG first standard lead and automatic detection of 32 ECG parameters and variability of the cardiac cycle in three states: at rest, immediately after dosage load and after 3 minutes of rest. A distinctive feature of the technology is that decisions on adequate or inadequate response of the organism to physical or emotional overload are realized by two methods — qualitative assessment and quantitative assessment.
Results. It is shown that a qualitative assessment of the reaction to the overload can be carried out on the basis of recognition of patterns’ classes generated by each triplet of measured parameters, and comparing the detected pattern with the dominant classes of each of the parameters. Quantitative assessment can be carried out based on the comparison of the generalized parameter with thresholds.
The algorithm for determining the dominant classes of parameters is proposed. Statistical analysis showed that the probability of appearance of patterns’ classes and generalized parameter values significantly different in the groups of trained and untrained persons. Examples of decision-making of the adequate and inadequate reaction of the organism on the overload are given.
Conclusions. The proposed IT satisfies the formulated requirements to field tools for testing the reserve capacity of the cardiovascular system during physical and emotional overloads.

Keywords: information technology, cardiovascular system, assessment of reserve capacity of the organism.

Download full text (ru)!

References

1 Heart rate variability. Standards of Measurement, Physiological interpretation and clinical use // Circulation. 1996, vol. 93. P. 1043–1065. https://doi.org/10.1161/01.CIR.93.5.1043

2 Korkushko O.V., Pisaruk A.V., Shatilo V.G., Lishnevskaya V.Y., Chebotarev N.D.,

3 Pohoretsky Y.N. Analysis of heart rate variability in clinical practice (age aspects). Kijv: Institut gerontologii AMN. 2002, 189 p. (in Russian).

4 Baevsky R.M., Berseneva A.P. Estimation of adaptation capabilities of the organism, and the risk of the disease development. Moskow: Medicine. 1997, 236 p. (in Russian).

5 Aronov D.M., Lupanov V.P. Functional tests in cardiology. Moskow: Medpress-inform. 2002, 296 p. (in Russian).

6 Halson S.L., Jeukendrup A.E. Does Overtraining Exist? An Analysis of Overreaching and Overtraining Research. Sports Medicine. 2004, vol. 34. No. 14. P. 967–981. https://doi.org/10.2165/00007256-200434140-00003

7 Chaykovsky I.A., Lapshin I.E., Fainzilberg L.S., Secretnyi V.A. ECG analysis in phase space as a way of monitoring the functional state of athletes who specialize in football. Sports Medicine. 2011. No 1–2. P. 63–68. (in Ukrainian).

8 Minina O.M., Bukov Y.O., Fainzilberg L.S. Rapid control method of myocardial functional reserve and physical activity adequacy. UA Patent 87096, 2014, bul. 2. (in Ukrainian).

9 Fainzilberg L.S. Computer diagnostics by phase portrait of electrocardiogram. Kiev: Osvita Ukrainy. 2013, 191 p. (in Russian).

10 Chaykovsky I.A., Budnik M.M. Method for physiological assessment psychoemotional or physical stress. UA Patent 54185, 2010, bul. 20. (in Ukrainian).

11 Di Bernardo D., Murray A. Computer model for study of cardiac repolarization.

12 J. Cardiovasc. Electrophysiol. 2000, vol. 11. P. 895–899. https://doi.org/10.1111/j.1540-8167.2000.tb00069.x

13 Wentsel E.S. Theory of probability. Moskow: Science. 1969. 575 p. (in Russian).

12 Fainzilberg LS, Zhuk T.N. Guaranteed efficiency estimation of diagnostic tests based on the amplified ROC-analysis. Control systems and machines. 2009. No 5. P. 3–13. (in Russian).

Received 28.05.2015