Classification of exhaled air IR spectra using combination support vector machine, decision tree, and k-nearest neighbor

V. V. Nikolaev; D. A. Kuzmin; V. S. Zasedatel

doi:10.1117/12.2581563

17 November 2020 Classification of exhaled air IR spectra using combination support vector machine, decision tree, and k-nearest neighbor

V. V. Nikolaev, D. A. Kuzmin, V. S. Zasedatel

Author Affiliations +

Proceedings Volume 11582, Fourth International Conference on Terahertz and Microwave Radiation: Generation, Detection, and Applications; 115821H (2020) https://doi.org/10.1117/12.2581563
Event: Fourth International Conference on Terahertz and Microwave Radiation: Generation, Detection, and Applications, 2020, Tomsk, Russian Federation

Abstract

Non-invasive diagnosis of diseases using analysis of exhaled air are actively developing in medical practice. The aim of work is to compare a specifics groups of patients with pulmonary diseases. As features of the participants' state, absorption spectra of exhaled air samples were used. The analyzed spectrum is a bar chart which describes the dependence of the absorption coefficient on the wavelength. The problem to be solved is the choice of informative sub-ranges of spectra to improve the classification of the studied groups and the subsequent classification of several spectra for one person by voting methods. An integrated approach was used to solve this problem using the principal component analysis, support vector machine with RBF core and the subsequent voting technique.

Citation Download Citation

V. V. Nikolaev, D. A. Kuzmin, and V. S. Zasedatel "Classification of exhaled air IR spectra using combination support vector machine, decision tree, and k-nearest neighbor", Proc. SPIE 11582, Fourth International Conference on Terahertz and Microwave Radiation: Generation, Detection, and Applications, 115821H (17 November 2020); https://doi.org/10.1117/12.2581563

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Chronic obstructive pulmonary disease

Principal component analysis

Gas lasers

Lung cancer

Machine learning

Absorption

Photoacoustic spectroscopy

Show All Keywords

Keywords/Phrases

Search In:

Publication Years