Machine learning applications for spectral analysis of human exhaled air for early diagnosis of diseasesMachine learning applications for spectral analysis of human exhaled air for early diagnosis of diseases
In this work, the possibility of using machine learning in the spectral analysis of exhaled breath for early diagnosis of diseases is considered. A quantum cascade laser with a tuning range of 5.4– 12.8 μm and an average power of 10 mW is used as an excitation source. Spectral analysis is based on the exhaled breath biomarkers. A trained CNN is used to identify biomarkers. The recognition is carried out using the example of Acetone and Ethanol. A minimum detectable concentration of 2 ppm is obtained with an SNR of less than 4.
File with abstract
Golyak Igor Semenovich
Bauman Moscow State Technical University, Moscow, Russia
File with report