(46-4) 17 * << * >> * Russian * English * Content * All Issues

Numerical methods of spectral analysis of multicomponent gas mixtures and human exhaled breath
I.S. Golyak 1, E.R. Kareva 1, I.L. Fufurin 1, D.R. Anfimov 1, A.V. Scherbakova 1, A.O. Nebritova 1, P.P. Demkin 1, A.N. Morozov 1

The Bauman Moscow State Technical University (BMSTU, Moscow)

 PDF, 986 kB

DOI: 10.18287/2412-6179-CO-1058

Pages: 650-658.

Full text of article: Russian language.

In this paper, the application of machine learning and deep learning in the spectral analysis of multicomponent gas mixtures is considered. The experimental setup consists of a quantum cascade laser with a tuning range of 5.3–12.8 µm, a peak power of up to 150 mW, and an astigmatic Herriott gas cell with an optical path length of up to 76 m. Acetone, ethanol, methanol, and their mixtures are used as test substances. For the detection and clustering of substances, including molecular biomarkers, methods of machine learning, such as stochastic embedding of neighbors with a t-distribution, principal component analysis and classification methods, such as random forest, gradient boosting, and logistic regression, are proposed. A shallow convolutional neural network based on TensorFlow (Google) and Keras is used for the spectral analysis of gas mixtures. Model spectra of substances are used as a training sample, and model and experimental spectra are used as a test sample. It is shown that neural networks trained on model spectra (NIST database) can recognize substances in experimental gas mixtures. We propose using machine learning methods for clustering and classification of pure substances and gas mixtures and neural networks for the identification of gas mixture components. Using the experimental setup described, the experimentally obtained concentration limits are 80 ppb for acetone and 100–120 ppb for ethanol and methanol. The possibility of using the proposed methods for analyzing spectra of human exhaled air is shown, which is significant for biomedical applications.

gas analysis, spectral analysis, biophotonics, infrared spectroscopy, quantum cascade laser, biomarker, machine learning, deep learning.

Golyak IS, Kareva ER, Fufurin IL, Anfimov DR, Scherbakova AV, Nebritova AO, Demkin PP, Morozov AN. Numerical methods of spectral analysis of multicomponent gas mixtures and human exhaled breath. Computer Optics 2022; 46(4): 650-658. DOI: 10.18287/2412-6179-CO-1058.

The work was carried out as part of the implementation of the program of strategic academic leadership "Priority-2030", approved by the Decree of the Government of the Russian Federation of May 13, 2021 No. 729.


  1. Selvaraj R, Vasa NJ, Nagendra SMS, Mizaikoff B. Advances in mid-infrared spectroscopy-based sensing techniques for exhaled breath diagnostics. Molecules 2020; 25: 2227. DOI: 10.3390/molecules25092227.
  2. Vaks VL, Domracheva EG, Sobakinskaya EA, Chernyaeva MB. Exhaled breath analysis: physical methods, instruments, and medical diagnostics. Physics-Uspekhi 2014; 57: 684-701. DOI: 10.3367/ufne.0184.201407d.0739.
  3. van Mastrigt E, Reyes-Reyes A, Brand K, et al. Exhaled breath profiling using broadband quantum cascade laser-based spectroscopy in healthy children and children with asthma and cystic fibrosis. J Breath Res 2016; 10: 026003. DOI: 10.1088/1752-7155/10/2/026003.
  4. Pauling L, Robinson AB, Teranishi R, Cary P. Quantitative analysis of urine vapor and breath by gas-liquid partition chromatography. Proc Natl Acad Sci USA 1971; 68: 2374-2376. DOI: 10.1073/pnas.68.10.2374.
  5. Wallace LA, Pellizzari ED, D.Hartwell T, Sparacino CM, Sheldon LS, Zelon H. Personal exposures, indoor-outdoor relationships, and breath levels of toxic air pollutants measured for 355 persons in New Jersey. Atmospheric Environ 1985; 19(10): 1651-1661. DOI: 10.1201/9780367810870-15.
  6. Matthews DE, Hayes JM. Isotope-ratio-monitoring gas chromatography-mass spectrometry. Anal Chem 1978; 50: 1465-1473. DOI: 10.1021/ac50033a022.
  7. Lu Z, Huang W, Wang L, Xu N. Exhaled nitric oxide in patients with chronic obstructive pulmonary disease: A systematic review and meta-analysis. Int J Chron Obstruct Pulmon Dis 2018; 13: 2695-2705. DOI: 10.2147/COPD.S165780.
  8. Nadeem F, Mandon J, Khodabakhsh A, Cristescu S, Harren F. Sensitive spectroscopy of acetone using a widely tunable external-cavity quantum cascade laser. Sensors 2018; 18: 2050. DOI: 10.3390/s18072050.
  9. Xia J, Zhu F, Kolomenskii AA, et al. Sensitive acetone detection with a mid-IR interband cascade laser and wavelength modulation spectroscopy. OSA Continuum 2019; 2: 640. DOI: 10.1364/OSAC.2.000640.
  10. Heinrich K, Fritsch T, Hering P, Mürtz M. Infrared laser-spectroscopic analysis of 14NO and 15NO in human breath. Appl Phys B 2009; 95: 281-286. DOI: 10.1007/s00340-009-3423-1.
  11. Jimenez R, Herndon S, Shorter JH, Nelson DD, McManus JB, Zahniser MS. Atmospheric trace gas measurements using a dual quantum-cascade laser mid-infrared absorption spectrometer. Proc SPIE 2005; 5738: 318. DOI: 10.1117/12.597130.
  12. McManus JB, Nelson DD, Herndon SC, et al. Comparison of cw and pulsed operation with a TE-cooled quantum cascade infrared laser for detection of nitric oxide at 1900 cm-1. Appl Phys B 2006; 85: 235-241. DOI: 10.1007/s00340-006-2407-7.
  13. Wysocki G, McCurdy M, So S, et al. Pulsed quantum-cascade laser-based sensor for trace-gas detection of carbonyl sulfide. Appl Opt 2004; 43(32): 6040-6046. DOI: 10.1364/AO.43.006040.
  14. Vasil'ev NS, Vintaykin IB, Golyak IgS, Golyak IlS, Kochikov IV, Fufurin IL. Recovery and analysis of raman spectra obtained using a static fourier transform spectrometer. Computer Optics 2017; 41(5): 626-635. DOI: 10.18287/2412-6179-2017-41-5-626-635.
  15. Kochikov IV, Morozov AN, Svetlichnyi SI, Fufurin IL. Substance recognition in the open atmosphere from a single Fourier transform spectroradiometer interferogram. Opt Spectrosc 2009; 106: 666-671. DOI: 10.1134/S0030400X09050075.
  16. Li J, Hibbert DB, Fuller S, Vaughn G. A comparative study of point-to-point algorithms for matching spectra. Chemom Intell Lab Syst 2006; 82: 50-58. DOI: 10.1016/j.chemolab.2005.05.015.
  17. Samsonov DA, Tabalina AS, Fufurin IL. QCL spectroscopy combined with the least squares method for substance analysis. J Phys Conf Ser 2017; 918: 012034. DOI: 10.1088/1742-6596/918/1/012034.
  18. Skarysz A, et al., Convolutional neural networks for automated targeted analysis of raw gas chromatography-mass spectrometry data. 2018 Int Joint Conf on Neural Networks (IJCNN) 2018: 1-8. DOI: 10.1109/IJCNN.2018.8489539.
  19. de Vries R, Brinkman P, van der Schee MP, et al. Integration of electronic nose technology with spirometry: validation of a new approach for exhaled breath analysis. J Breath Res 2015; 9: 046001. DOI: 10.1088/1752-7155/9/4/046001.
  20. López-Sánchez LM, Jurado-Gámez B, Feu-Collado N, et al. Exhaled breath condensate biomarkers for the early diagnosis of lung cancer using proteomics. Am J Physiol Lung Cell Mol Physiol 2017; 313: L664-L676. DOI: 10.1152/ajplung.00119.2017.
  21. Austria YD, Goh ML, Maria LBSta Jr, Lalata J-A, Goh JE, Vicente H. Comparison of machine learning algorithms in breast cancer prediction using the coimbra dataset. International Journal of Simulation: Systems, Science & Technology 2019 Suppl 2; 20: 23. DOI: 10.5013/ijssst.a.20.s2.23.
  22. Jagadev P, Giri LI. Non-contact monitoring of human respiration using infrared thermography and machine learning. Infrared Phys Technol 2020; 104: 103117. DOI: 10.1016/j.infrared.2019.103117.
  23. Zhang L, Ding X, Hou R. Classification modeling method for near-infrared spectroscopy of tobacco based on multimodal convolution neural networks. J Anal Methods Chem 2020; 2020: 9652470. DOI: 10.1155/2020/9652470.
  24. Weng S, Yuan H, Zhang X, et al. Deep learning networks for the recognition and quantitation of surface-enhanced Raman spectroscopy. Analyst 2020; 145: 4827-4835. DOI: 10.1039/D0AN00492H.
  25. Badirli S, Liu X, Xing Z, Bhowmik A, Doan K, Keerthi SS. Gradient boosting neural networks: GrowNet. arXiv Preprint 2020. Source: <https://arxiv.org/abs/2002.07971>.
  26. Fufurin IL, Golyak IS, Anfimov DR, et al. Machine learning applications for spectral analysis of human exhaled breath for early diagnosis of diseases. Proc SPIE 2020; 11553: 115531G. DOI: 10.1117/12.2584043.
  27. Tabalina AS, Anfimov DR, Fufurin IL, Golyak IS. Infrared quantum cascade laser spectroscopy as non-invasive diagnostic tests for human diseases. Proc SPIE 2020; 11359: 113591J. DOI: 10.1117/12.2555042.
  28. Fufurin IL, Anfimov DR, Kareva ER, et al. Numerical techniques for infrared spectra analysis of organic and inorganic volatile compounds for biomedical applications. Opt Eng 2021; 60(8): 082016. DOI: 10.1117/1.OE.60.8.082016.
  29. Breiman L. Random forests. Machine Learning 2001; 45: 5-32. DOI: 10.1023/A:1010933404324.
  30. Linstrom P. NIST Chemistry WebBook, NIST Standard Reference Database Number 69. Source: <https://webbook.nist.gov/chemistry/>.
  31. Bergstra J, Yoshua B. Random search for hyper-parameter optimization. J Mach Learn Res 2012; 13: 281-305.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20