Using of the machine learning methods to identify bronchopulmonary system diseases with the use of lung sounds

Abstract

This study reviews the main approaches to the analyzing of modern methods of digital processing of lung sounds. It is shown that each of the existing methods gives a definite result in solving a particular problem. However, none of the methods that were reviewed, can’t be called universal and completely convenient for using in the real conditions of the hospital. Certain numerical parameters can be obtained, as a result of the work of each method. In this study it is showed that machine learning can serve as a unifying mechanism for the considered methods. A set of different parameters can be the input arguments of the classifier, which will be properly trained. As a result, the primary opinion in a convenient and accessible form can be presented to the doctor.

Authors and Affiliations

M. Chekhovych, A. Poreva, V. Timofeyev, P. Henaff

Keywords

Related Articles

Ganzenko Generation and properties of Gold’s sequence

The article shows principles generation of Gold's sequences, shown a block diagram of sequence generator, based on shift registers and step by step description of its work. We calculated the spectral characteristics of s...

Radiocontact with outland civilization

Possiblity appearance and development of the “clever” life on the planet.

The use of "Echo model" in the design of data communication system on power supply networks

Introduction. Analysis of power supply network and research parameters for possible use as an environment of data transfer which are considered in the broadband frequency range. The purpose of this work is the usage of "...

The electromagnetic ether, as a medium of the existence of electromagnetic waves

We propose a new approach to the problem, according to which the revision is subject to the very concept of ether, which should not be viewed as filling, as well as an integral part of the universe.

Mathematical model сoherent demodulation of synchronous mutually nonorthogonal digital signals with minimum frequency-shift keying

Introduction. The synthesis mathematical model procedure of coherent demodulation of synchronous mutually nonorthogonal digital signals with minimum frequency-shift keying is the basic and purpose of this article. Synthe...

Download PDF file
  • EP ID EP308245
  • DOI 10.20535/RADAP.2018.73.55-62
  • Views 41
  • Downloads 0

How To Cite

M. Chekhovych, A. Poreva, V. Timofeyev, P. Henaff (2018). Using of the machine learning methods to identify bronchopulmonary system diseases with the use of lung sounds. Вісник НТУУ КПІ. Серія Радіотехніка, Радіоапаратобудування, 0(73), 55-62. https://europub.co.uk/articles/-A-308245