Radiotekhnika
Publishing house Radiotekhnika

"Publishing house Radiotekhnika":
scientific and technical literature.
Books and journals of publishing houses: IPRZHR, RS-PRESS, SCIENCE-PRESS


Тел.: +7 (495) 625-9241

 

Capabilities application of artificial neural networks for classification phonocardiogram signals

Keywords:

W.M. Ayedh – Post-graduate Student, Department «Biomedical and Electronic Systems and Technology», Vladimir State University named after A.&N. Stoletovs E-mail: walid_aed@mail.ru W.A. Al-Haidri – Post-graduate Student, Department «Biomedical and Electronic Systems and Technology», Vladimir State University named after A.&N. Stoletovs E-mail: fawaz_tariq@mail.ru R.V. Isakov – Ph. D. (Eng.), Associate Professor, Department «Biomedical and Electronic Systems and Technology», Vladimir State University named after A.&N. Stoletovs E-mail: Isakov-RV@mail.ru L.T. Sushkova – Dr. Sc. (Eng.), Professor, Head of Department «Biomedical and Electronic Systems and Technology», Vladimir State University named after A.&N. Stoletovs E-mail: ludm@vlsu.ru


The human body is a complex dynamic system, comprising a number of subsystems and processes. Several physiological processes can be active at the same. Each of them generates a plurality of signals of different types. The appearance of the signals from the processes and systems that are not currently objects of study can be regarded as a physiological disturbance. This raises the problem of improving the quality and reliability of the information content of functional diagnostics in medicine. Cardiovascular diseases (CVD) are in the first place among the causes of death in the world. Therefore, it is very highly topical scientific and practical justification and development of effective methods of treatment, rehabilitation and prevention and, above all, accurate early diagnosis of CVD in the presence of minimal symptoms (complaints or feeling sick). There are various methods of detecting CVD. The most common electrocardiography (ECG) and phonocardiography (PCG) in connection with high efficiency, safety and ease of hardware implementation of these methods. Method of PCG is based on the registration and analysis the sounds that arising during contraction and relaxation of the heart. This method is affordable and relatively easy way to diagnose the functional state of cardiovascular systems. This work is associated with the study of the possibility of capabilities application of artificial neural networks (ANN) for classification phonocardiogram signals. propose an algorithm for classification of functional status on the phonocardiogram (PCG) signal based on ANN. The proposed algorithm seems more promising due to its versatility, simplicity and clarity. Considered the issue of segmentation accuracy PCG and correctness the preparation of informative data for the ANN. Classification of functional states is held by the type of «Norma» or «pathology». The results obtained in this paper of classification PCG have shown high efficiency on this approach, which is confirmed by the values generally, accepted criteria: sensitivity (90.06%) and specificity (87.89%). It testifies high efficiency assessment of heart sounds by PCG. The algorithm provides a qualitative tool doctor for primary diagnosis using simple techniques phonocardiography.
References:

 

  1. Slepnev E.S. Primenenie iskusstvennykh nejjronnykh setejj dlja analiza predavarijjnykh situacijj turboagregatov ehlektrostancijj // Naukovedenie (Internet-zhurnal). Majj–ijun 2014. № 3.
  2. Al-KHajjdri V.A. Isakov R.V., Sushkova L.T. Metodika ocenki ehffektivnosti nejjrosetevojj sistemy analiza ehlektrokardiograficheskogo signala // Doklady 12‑jj mezhd. nauchn. konf. «Fizika i radioehlektronika v medicine i ehkologii». Vladimir. 2016. Kn. 1. S. 134−137.
  3. Rangajjan R.M. Analiz biomedicinskikh signalov. Prakticheskijj podkhod: Per. s angl. Pod red. A.P. Nemirko. M.: FIZMATLIT. 2007. 440 s.
  4. The relevance of the use of Holter monitoring of blood pressure and ECG. URL = http://www.incart.ru/text.jsp?id=10473.
  5. Krasnov L.A., Olejjnik V.P.KH. Fonokardiografija. Tekhnicheskie sredstva ehlektronnojj i kompjuternojj diagnostiki v medicine: Ucheb. posobie. KHarkov: KHarkovskijj aviacionnyjj institut. 2013. 64 s.
  6. Fonokardiografija. URL = http://www.serdechno.ru.
  7. Minkin R.B., Pavlov K.D. EHlektrokardiografija i fonokardiografija. L.: Medicina. 1980.
  8. Miloslavskijj JA.M., KHodzhaeva D.K. Osnovnye instrumentalnye metody issledovanija serdca. Kazan: Izd-vo KGU. 1983. 143 s.
  9. Kushakov V.I. Prakticheskaja fonokardiografija: Ucheb. posobie. M.: Centralnyjj institut usovershenstvovanija vrachejj. 1989. 48 s.
  10. Kao WC, Wei CC. Automatic phonocardiograph signal analysis for detecting heart valve disorders // Expert Systems with Applications. 2011. V. 38. № 6. P. 6458−68.
  11. Huiying L, Sakari L, Iiro H. A heart sound segmentation algorithm using wavelet // 19th International Conference IEEE/EMBS. Chicago. IL. 1997.
  12. Wang P., Lim C.S., Chauhan S., Foo J.Y., Anantharaman V. Phonocardiographic signal analysis method using a modified hidden markov model. // Annals of Biomedical Engineering. 2007. V. 35. P. 367−374.
  13. Tanachat Nilanon, Jiayu Yao, Junheng Hao, Sanjay Purushotham, Yan Liu. Normal /abnormal heart sound recordings classification using convolutional neural network department of computer science // University of Southern California Los Angeles. California. 2016. 90089 USA.
  14. Iga Grzegorczyk, Mateusz Soliński, Michał Łepek, Anna Perka, Jacek Rosiński, Joanna Rymko, Katarzyna Stępień, Jan Gierałtowski. PCG Classification Using a Neural Network Approach. Faculty of Physics, Warsaw University of Technology. Warsaw. Poland. 2016.
  15. Physionet/cinc Challenge 2016: Training Sets. URL = https://www.physionet.org/challenge/2016/.
  16. L. Hamza Cheri, S.M. Debbal. Algorithm for detection of the internal components of the heart sounds and their split using a Hilbert transform // Journal of medical engineering and technology. 2013. V. 37. № 3. P. 220−230.
  17. JAsnickijj L.N. Iskusstvennyjj intellekt: populjarnoe vvedenie dlja uchitelejj i shkolnikov.
  18. URL = http://inf.1september.ru/view_article.php?ID=200902304.
  19. Aed V.M., Isakov R.V., Sushkova L.T., Al-KHajjdri V.A. Algoritm postroenija kardiointervalogrammy na osnove fonokardiogrammy // Radiotekhnicheskie i telekommunikacionnye sistemy. 2016. № 2. S. 34−42.
  20. Aed V.M., Isakov R.V., Sushkova L.T. Obzor metodov obrabotki fonokardiogrammy // Doklady 12‑jj Mezhdunar. nauchnaja konf. «Fizika i radioehlektronika v medicine i ehkologii» (FREHMEH). 2016. Vladimir-Suzdal. Rossija. Kn. 1. S. 138−144.

 

© Издательство «РАДИОТЕХНИКА», 2004-2017            Тел.: (495) 625-9241                   Designed by [SWAP]Studio