Research of classifiers’ work to optimize diagnoses bronchopulmonary diseases
Main Article Content
Abstract
This article considers the possibility of using classifiers, which are the basis of machine learning to diagnoses bronchopulmonary diseases optimization. The work of a few qualifiers was considered and as a result of the research the nearest neighbor method was chosen for the task classifier. As the parameters of this method numerical characteristics of breathing sounds signals were chosen. This characteristics was calculated on the basis of poyspectral analysis. It was found that this classifier is simple to implement and to operate with the data base of breathing sounds. The resulting accuracy of the classifier is high enough. The algorithm is designed to greatly simplify the work of the doctor-pulmonologist for setting a timely diagnosis.
Referense 8, Figures 3.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Zolotih N.U. Machine Learning and Data Mining // URL: http://www.uic.unn.ru/~zny/ml/
Vorontsov K.V. Mathematical methods of training on precedents (machine learning theory)// http://www.ccas.ru/voron (Rus)
Mitchell T. Machine Learning. — McGraw-Hill Science/Engineering/Math, 1997. ISBN 0-07-042807-7.
Data classification by support vector method- URL: https://habrahabr.ru/post/105220/ (Rus)
Poreva G.S, Karplyuk Y.S., Makarenkova А.А., Makarenkov А.P. Detection of specific acoustic characteristics of patients with COPD based on spectral analysis of respiratory sounds // Electronics and Communications. – 2014. - Volume 19, №6(83) – Karplyuk Y.S., сс. 82-86 (Ukr)
Poreva G.S, Makarenkova А.А., Karplyuk Y.S., Goncharenko A.A. Application of polyspectral analysis to determine the diagnostic signs in the breathing sounds in patients with COPD - Proceedings of the National Technical University "KhPI" - technologies. Series: New solutions in modern technologies. – Kh.: NTU "KhPІ" - 2014. - , №36(1079)2014 - 200с., с. 49-55
Anna Poreva Yevgeniy Karplyuk, Anastasiia Makarenkova, Anatoliy Makarenkov Detection of COPD's Diagnostic Signs Based on Polyspectral Lung Sounds Analysis of Respiratory Phases 2015 IEEE 35th International Scientific Conference Electronics and Nanotechnology (ELNANO), pp.351-355
