Методи машинного навчання для дослідження сигналівзвуківлегенів

Anna Serhiivna Poreva; Valentyn Ihorovych Vaityshyn; Yevgeniy Serhiiovych Karplyuk

doi:10.20535/2523-4455.2017.22.6.108829

Vol. 22 · Issue 6 · 2017 Dec 29, 2017 Biomedical devices and systems

Machine learning methods for the study of the lungsounds signals

Anna Serhiivna Poreva Corresponding National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” Ukraine

Valentyn Ihorovych Vaityshyn National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” Ukraine

Yevgeniy Serhiiovych Karplyuk National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” Ukraine

Pages41-47 PublishedDec 29, 2017

PDF (Ukrainian)

VOL 22 · ISS 6 · 2017 View issue

Abstract

The article considers the basic methods of machine learning for applying them to the task of the lungs sounds classifying. A number of signal parameters were obtained on the basis of the lungs sounds set. The task of the study was to classify sounds using five different machine learning methods. It was also necessary to determine from a number of signal parameters those that give the highest accuracy. Thus the seven most diagnostically valuable parameters of lung sounds were found. The results showed that two methods of machine learning - the method of reference vectors and the decision tree method - have the best accuracy. Thus this classification technique can serve as an auxiliary tool for a pulmonary physician to diagnosis. Ref. 18, tabl. 5.

Keywords

#lung sounds #machine learning #classifier #support vector method #decision tree method

References

T. Kaur and E. N. Gupta, “Classification of Lung Diseases Using Optimization Techniques,” Int. J. Sci. Res. Dev., vol. 3, no. 8, pp. 852–854, Nov. 2015. URL: http://ijsrd.com/Article.php?manuscript=IJSRDV3I80412
“Vsemirnaja organizacija zdravoohraneniya. 10 vedyshih smertej v mire [World Health Organization. 10 leading deaths in the world.],” WHO, 2017. [Online]. Available: http://www.who.int/mediacentre/factsheets/fs310/ru/ .
A. A. Grinchenko, V. T. Makarenkov, A. P. Makarenkova, “Kompjuternaya auskultaciya - novij metod objektivizacii harakterictik zvykov dihaniya [Computer auscultation is a new method of objectifying the lung sounds characteristics],” Klin. Inform. i telemeditsina, vol. 6, no. 7, pp. 31–36, 2010.
A. Jones, “A Brief Overview of the Analysis of Lung Sounds,” Physiotherapy, vol. 81, no. 1, pp. 37–42, Jan. 1995. DOI: 10.1016/S0031-9406(05)67034-4
R. L. H. Murphy et al., “Automated lung sound analysis in patients with pneumonia.,” Respir. Care, vol. 49, no. 12, pp. 1490–7, Dec. 2004. PMID: 15571639
D. Emmanouilidou, K. Patil, J. West, and M. Elhilali, “A multiresolution analysis for detection of abnormal lung sounds,” in 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2012, pp. 3139–3142. DOI: 10.1109/EMBC.2012.6346630
S. Ulukaya, G. Serbes, I. Sen, and Y. P. Kahya, “A lung sound classification system based on the rational dilation wavelet transform,” in 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2016, pp. 3745–3748. DOI: 10.1109/EMBC.2016.7591542
E. Shams, D. Karimi, and Z. Moussavi, “Bispectral analysis of tracheal breath sounds for Obstructive Sleep Apnea,” in 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2012, pp. 37–40. DOI: 10.1109/EMBC.2012.6345865
“Mashinnoe obychenie [Machine Learning].” [Online]. Available: http://www.machinelearning.ru/wiki/index.php?title=Machine_Learning .
T. Hastie, R. Tibshirani, and J. H. Friedman, The elements of statistical learning : data mining, inference, and prediction, Second. New York, NY, USA: Springer, 2009. ISBN: 978-0387848570
V. N. Vapnik, Vosstanovlenie zavisimostej po empiricheskim dannim [Recovery of dependencies according to empirical data]. Moskow, USSR: Nauka, 1979.
S. A. Ajvazyan, V. M. Byhshtaber, I. S. Jenyukov, and L. D. Meshalkin, Prikladnaya ststistika: klassifikasiya i snizheniye razmernosti [Applied statistics: classification and dimension reduction]. Moskow, USSR: Finansi a statistika, 1989.
U. I. Zhyravlev, V. V. Ryazanov, and O. V. Senko, Raspoznavaniye. Matematicheskie metody. Programmnaya sistema. Prakticheskie primeneniya [Recognition. Mathematical methods Software system. Practical applications]. Moskow, Russia: Fazis, 2006. ISBN: 5-7036-0108-8
D. M. W. Powers, “Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness & Correlation,” J. Mach. Learn. Technol., vol. 2, no. 1, pp. 37–63, 2011. URL: https://www.bioinfopublication.org/viewhtml.php?artid=BIA0001114
T. Fawcett, “An introduction to ROC analysis,” Pattern Recognit. Lett., vol. 27, no. 8, pp. 861–874, Jun. 2006. DOI: 10.1016/j.patrec.2005.10.010
A. S. Poreva, A. A. Makarenkova, Y. S. Karplyuk, and A. A. Goncharenko, “Primeneniye polispectral’nogo analiza dlya opredeleniya diagnosticheskih priznakov v zvykah dihanija bol’nih HOBL [The using of polyspectral analysis for determining diagnostic signs in the lung sounds in COPD patients],” Visn. Nac. Teh. Univ. “KhPI,” no. 36, pp. 49–55, 2014. URI: http://repository.kpi.kharkov.ua/handle/KhPI-Press/9386
A. Poreva, Y. Karplyuk, A. Makarenkova, and A. Makarenkov, “Detection of COPD’s diagnostic signs based on polyspectral lung sounds analysis of respiratory phases,” in 2015 IEEE 35th International Conference on Electronics and Nanotechnology (ELNANO), 2015, pp. 351–355. DOI: 10.1109/ELNANO.2015.7146908
H. S. Porieva and D. Honcharova, “Doslidzhennia roboty klasyfikatoriv dlia optymizatsii postanovky diahnoziv bronkholehenevykh zakhvoriuvan [Research of classifiers’ work to optimize diagnoses bronchopulmonary diseases],” Electron. Commun., vol. 21, no. 4, pp. 44–48, Nov. 2016. DOI: 10.20535/2312-1807.2016.21.4.81930

Previous in issue Improvement of parameters X-ray television systems on the basis of electronic converters Next in issue Subjective evaluation of quality and intelligibility of speech distorted by synthesized noise

§ 06 — Related

[1] T. Kaur and E. N. Gupta, “Classification of Lung Diseases Using Optimization Techniques,” Int. J. Sci. Res. Dev., vol. 3, no. 8, pp. 852–854, Nov. 2015. URL: http://ijsrd.com/Article.php?manuscript=IJSRDV3I80412

[2] “Vsemirnaja organizacija zdravoohraneniya. 10 vedyshih smertej v mire [World Health Organization. 10 leading deaths in the world.],” WHO, 2017. [Online]. Available: http://www.who.int/mediacentre/factsheets/fs310/ru/ .

[3] A. A. Grinchenko, V. T. Makarenkov, A. P. Makarenkova, “Kompjuternaya auskultaciya - novij metod objektivizacii harakterictik zvykov dihaniya [Computer auscultation is a new method of objectifying the lung sounds characteristics],” Klin. Inform. i telemeditsina, vol. 6, no. 7, pp. 31–36, 2010.

[4] A. Jones, “A Brief Overview of the Analysis of Lung Sounds,” Physiotherapy, vol. 81, no. 1, pp. 37–42, Jan. 1995. DOI: 10.1016/S0031-9406(05)67034-4

[5] R. L. H. Murphy et al., “Automated lung sound analysis in patients with pneumonia.,” Respir. Care, vol. 49, no. 12, pp. 1490–7, Dec. 2004. PMID: 15571639

[6] D. Emmanouilidou, K. Patil, J. West, and M. Elhilali, “A multiresolution analysis for detection of abnormal lung sounds,” in 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2012, pp. 3139–3142. DOI: 10.1109/EMBC.2012.6346630

[7] S. Ulukaya, G. Serbes, I. Sen, and Y. P. Kahya, “A lung sound classification system based on the rational dilation wavelet transform,” in 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2016, pp. 3745–3748. DOI: 10.1109/EMBC.2016.7591542

[8] E. Shams, D. Karimi, and Z. Moussavi, “Bispectral analysis of tracheal breath sounds for Obstructive Sleep Apnea,” in 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2012, pp. 37–40. DOI: 10.1109/EMBC.2012.6345865

[9] “Mashinnoe obychenie [Machine Learning].” [Online]. Available: http://www.machinelearning.ru/wiki/index.php?title=Machine_Learning .

[10] T. Hastie, R. Tibshirani, and J. H. Friedman, The elements of statistical learning : data mining, inference, and prediction, Second. New York, NY, USA: Springer, 2009. ISBN: 978-0387848570

[11] V. N. Vapnik, Vosstanovlenie zavisimostej po empiricheskim dannim [Recovery of dependencies according to empirical data]. Moskow, USSR: Nauka, 1979.

[12] S. A. Ajvazyan, V. M. Byhshtaber, I. S. Jenyukov, and L. D. Meshalkin, Prikladnaya ststistika: klassifikasiya i snizheniye razmernosti [Applied statistics: classification and dimension reduction]. Moskow, USSR: Finansi a statistika, 1989.

[13] U. I. Zhyravlev, V. V. Ryazanov, and O. V. Senko, Raspoznavaniye. Matematicheskie metody. Programmnaya sistema. Prakticheskie primeneniya [Recognition. Mathematical methods Software system. Practical applications]. Moskow, Russia: Fazis, 2006. ISBN: 5-7036-0108-8

[14] D. M. W. Powers, “Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness & Correlation,” J. Mach. Learn. Technol., vol. 2, no. 1, pp. 37–63, 2011. URL: https://www.bioinfopublication.org/viewhtml.php?artid=BIA0001114

[15] T. Fawcett, “An introduction to ROC analysis,” Pattern Recognit. Lett., vol. 27, no. 8, pp. 861–874, Jun. 2006. DOI: 10.1016/j.patrec.2005.10.010

[16] A. S. Poreva, A. A. Makarenkova, Y. S. Karplyuk, and A. A. Goncharenko, “Primeneniye polispectral’nogo analiza dlya opredeleniya diagnosticheskih priznakov v zvykah dihanija bol’nih HOBL [The using of polyspectral analysis for determining diagnostic signs in the lung sounds in COPD patients],” Visn. Nac. Teh. Univ. “KhPI,” no. 36, pp. 49–55, 2014. URI: http://repository.kpi.kharkov.ua/handle/KhPI-Press/9386

[17] A. Poreva, Y. Karplyuk, A. Makarenkova, and A. Makarenkov, “Detection of COPD’s diagnostic signs based on polyspectral lung sounds analysis of respiratory phases,” in 2015 IEEE 35th International Conference on Electronics and Nanotechnology (ELNANO), 2015, pp. 351–355. DOI: 10.1109/ELNANO.2015.7146908

[18] H. S. Porieva and D. Honcharova, “Doslidzhennia roboty klasyfikatoriv dlia optymizatsii postanovky diahnoziv bronkholehenevykh zakhvoriuvan [Research of classifiers’ work to optimize diagnoses bronchopulmonary diseases],” Electron. Commun., vol. 21, no. 4, pp. 44–48, Nov. 2016. DOI: 10.20535/2312-1807.2016.21.4.81930

Machine learning methods for the study of the lungsounds signals

Abstract

Keywords

References

Similar articles in this journal

Non-contact monitoring of ventilation function parameters using optical flow

Termohram quality stabilisation by the way of thermal defocus compensation

Quasistatic Identification of The Shading Structure of Solar Panels by The Method of Cardinal Number Vectors

Similar Articles

Similar Articles

A A Complex Method for Non-invasive Fetal Electrocardiogram Signal Extraction and Cardiac Arrhythmia Classification

Practical Method of Estimating Safe Sounds for a Person with PTSD

Siamеse Neural Network’s Models for Cardiac Arrhythmia Classification in the Conditions of Shortage of Training Ecg Signals

Quasistatic Identification of The Shading Structure of Solar Panels by The Method of Cardinal Number Vectors

Increase the Resistance of Digital Television to Interference

Planning Trajectory of Anthropomorphic Walking Robot (Biped Robot)

Influence of the Cerium Oxide Thin Film Produc-Tion Methods on the Capacitance-Voltage Charac-Teristics of the Mis Structures

Optical properties of nickel nanoparticles in systems with a statistically inhomogeneous structure

An active method application for the chromatic dispersion compensation aimed to increase the transmіssion capabilities of the fiber-optical linear path

Specific electric polarizability of copper nanoparticles in the optical range of the spectrum