nguphysСибирский физический журналSIBERIAN JOURNAL OF PHYSICS2541-9447Новосибирский государственный университет10.25205/2541-9447-2018-13-3-101-109nguphys-56Research ArticleКОМБИНАЦИОННОЕ РАССЕЯНИЕ - 90 ЛЕТ ИССЛЕДОВАНИЙРЕШЕНИЕ ОБРАТНЫХ ЗАДАЧ СПЕКТРОСКОПИИ КОМБИНАЦИОННОГО РАССЕЯНИЯ ВОДНЫХ РАСТВОРОВ СОЛЕЙ С ПРИМЕНЕНИЕМ ВЕЙВЛЕТ-НЕЙРОННЫХ СЕТЕЙSOLUTION OF INVERSE PROBLEMS OF RAMAN SPECTROSCOPY OF AQUEOUS SALT SOLUTIONS WITH THE APPLICATION OF WAVELET NEURAL NETWORKSБуриковС. А.BurikovS. A.sergey.burikov@gmail.comЕфиторовА. О.EfitorovA. O.noemail@neicon.ruДоленкоТ. А.DolenkoT. A.noemail@neicon.ruШирокийВ. Р.ShirokiyV. R.noemail@neicon.ruДоленкоС. А.DolenkoS. A.noemail@neicon.ruМосковский государственный университет им. М. В. ЛомоносоваРоссияLomonosov Moscow State UniversityRussian Federation201826102020133101109Copyright © Буриков С.А., Ефиторов А.О., Доленко Т.А., Широкий В.Р., Доленко С.А., 20202020Буриков С.А., Ефиторов А.О., Доленко Т.А., Широкий В.Р., Доленко С.А.Burikov S.A., Efitorov A.O., Dolenko T.A., Shirokiy V.R., Dolenko S.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://nguphys.elpub.ru/jour/article/view/56

Представлены результаты решения задачи по определению солевого состава многокомпонентных водных растворов по их спектрам комбинационного рассеяния света с использованием искусственных нейронных сетей и метода проекций на латентные структуры. Сравниваются три метода извлечения признаков из спектральных кривых: агрегация каналов, дискретное и непрерывное вейвлет-преобразования. Показано, что для нейросетевого решения обратной задачи определения солевого состава наилучшие результаты обеспечивает непрерывное вейвлет-преобразование входных данных.

This paper presents the results of solving the problem of determining the salt composition of multicomponent aqueous solutions by their Raman spectra using artificial neural networks and the method of projections on latent structures. Three methods of input feature transformation are considered: aggregation of adjacent spectral channels, discrete and continuous wavelet transforms. It is shown that all of them can reduce both the dimension of the input data and the error of determination of the salt concentrations in the problem under consideration. The most effective method for the solution of the considered problem was a continuous wavelet transform. The multilayer perceptron trained on the transformed by this method input features provided the average error of determination of concentration for all 5 salts 0.023 M that is 38 % less than the error obtained by artificial neural network used without data compression. Thus, Raman spectroscopy combined with the use of artificial neural networks trained on transformed input features demonstrated high efficiency in solving the problem of identification and determination of concentrations of 5 inorganic salts dissolved in water.

спектроскопия комбинационного рассеянияводные растворы солейпроекции на латентные структурыискусственные нейронные сетивейвлет-анализRaman spectroscopyaqueous solutions of saltsprojections on latent structuresartificial neural networkswavelet analysisReferencesШевцов М. Н. Водно-экологические проблемы и использование водных ресурсов. Хабаровск: Изд-во Тихоокеан. гос. ун-та, 2015. 197 с. ISBN 978-5-7389-1817-9.Шевцов М. Н. Водно-экологические проблемы и использование водных ресурсов. Хабаровск: Изд-во Тихоокеан. гос. ун-та, 2015. 197 с. ISBN 978-5-7389-1817-9.Andersson M., Edner H., Johansson J., Svanberg S., Wallinder E., Weibring P. Remote sensing of the environment using laser radar techniques // Atomic Physics Methods in Modern Research. 1997. Vol. 499. P. 257-269. Springer. DOI: 10.1007/BFb0104329.Andersson M., Edner H., Johansson J., Svanberg S., Wallinder E., Weibring P. Remote sensing of the environment using laser radar techniques // Atomic Physics Methods in Modern Research. 1997. Vol. 499. P. 257-269. Springer. DOI: 10.1007/BFb0104329.Harsdorf S., Janssen M., Reuter R., Toeneboen S., Wachowicz B., Willkomm R. Submarine lidar for seafloor inspection // Meas Sci Tech. 1999. Vol. 10. No. 12. P. 1178-1184.Harsdorf S., Janssen M., Reuter R., Toeneboen S., Wachowicz B., Willkomm R. Submarine lidar for seafloor inspection // Meas Sci Tech. 1999. Vol. 10. No. 12. P. 1178-1184.Dolenko T. A., Churina I. V., Fadeev V. V., Glushkov S. M. Valence band of liquid water Raman scattering: some peculiarities and applications in the diagnostics of water media // J. Raman Spectroscopy. 2000. Vol. 31. P. 863- 870.Dolenko T. A., Churina I. V., Fadeev V. V., Glushkov S. M. Valence band of liquid water Raman scattering: some peculiarities and applications in the diagnostics of water media // J. Raman Spectroscopy. 2000. Vol. 31. P. 863- 870.Kauffmann T. H., Fontana M. D. Inorganic salts diluted in water probed by Raman spectrometry: Data processing and performance evaluation // Sensors and Actuators B. 2015. Vol. 209. P. 154-161.Kauffmann T. H., Fontana M. D. Inorganic salts diluted in water probed by Raman spectrometry: Data processing and performance evaluation // Sensors and Actuators B. 2015. Vol. 209. P. 154-161.Rudolph W. W., Irmer G. Raman and Infrared Spectroscopic Investigation on Aqueous Alkali Metal Phosphate Solutions and Density Functional Theory Calculations of Phosphate-Water Clusters // Appl. Spectroscopy. 2007. Vol. 61. No. 12. P. 274A-292A.Rudolph W. W., Irmer G. Raman and Infrared Spectroscopic Investigation on Aqueous Alkali Metal Phosphate Solutions and Density Functional Theory Calculations of Phosphate-Water Clusters // Appl. Spectroscopy. 2007. Vol. 61. No. 12. P. 274A-292A.Rull F., De Saja J. A. Effect of electrolyte concentration on the Raman spectra of water in aqueous solutions // J. Raman Spectroscopy. 1986. Vol. 17. No. 2. P. 167-172.Rull F., De Saja J. A. Effect of electrolyte concentration on the Raman spectra of water in aqueous solutions // J. Raman Spectroscopy. 1986. Vol. 17. No. 2. P. 167-172.Sadate S., Kassu A., Farley C. W., Sharma A., Hardisty J., Lifson Miles T. K. Standoff Raman measurement of nitrates in water // Proc. SPIE Remote Sensing and Modeling of Ecosystems for Sustainability VIII. 2011. P. 81560D-1-6.Sadate S., Kassu A., Farley C. W., Sharma A., Hardisty J., Lifson Miles T. K. Standoff Raman measurement of nitrates in water // Proc. SPIE Remote Sensing and Modeling of Ecosystems for Sustainability VIII. 2011. P. 81560D-1-6.Somekawa T., Tani A., Fujita M. Remote Detection and Identification of CO2 Dissolved in Water Using a Raman Lidar System // Applied Physics Express. 2011. Vol. 4. P. 1124011-3.Somekawa T., Tani A., Fujita M. Remote Detection and Identification of CO2 Dissolved in Water Using a Raman Lidar System // Applied Physics Express. 2011. Vol. 4. P. 1124011-3.Mernagh T. P., Wilde A. R. The use of the laser Raman microprobe for the determination of salinity in fluid inclusions // Geochimica et Cosmochimica Acta. 1989. Vol. 53. P. 765- 771.Mernagh T. P., Wilde A. R. The use of the laser Raman microprobe for the determination of salinity in fluid inclusions // Geochimica et Cosmochimica Acta. 1989. Vol. 53. P. 765- 771.Burikov S. A., Dolenko S. A., Dolenko T. A., Persiantsev I. G. Application of Artificial Neural Networks to Solve Problems of Identification and Determination of Concentration of Salts in Multi-Component Water Solutions by Raman Spectra // Optical Memory and Neural Networks (Information Optics). 2010. Vol. 19. No. 2. P. 140-148.Burikov S. A., Dolenko S. A., Dolenko T. A., Persiantsev I. G. Application of Artificial Neural Networks to Solve Problems of Identification and Determination of Concentration of Salts in Multi-Component Water Solutions by Raman Spectra // Optical Memory and Neural Networks (Information Optics). 2010. Vol. 19. No. 2. P. 140-148.Efitorov A., Burikov S., Dolenko T., Laptinskiy K., Dolenko S. Significant Feature Selection in Neural Network Solution of an Inverse Problem in Spectroscopy // Procedia Computer Science. 2015. Vol. 66. P. 93-102.Efitorov A., Burikov S., Dolenko T., Laptinskiy K., Dolenko S. Significant Feature Selection in Neural Network Solution of an Inverse Problem in Spectroscopy // Procedia Computer Science. 2015. Vol. 66. P. 93-102.Haykin S. S. Neural networks and learning machines. 3rd ed. Upper Saddle River. NJ. USA: Pearson, 2009.Haykin S. S. Neural networks and learning machines. 3rd ed. Upper Saddle River. NJ. USA: Pearson, 2009.Esbensen K. H. Multivariate Data Analysis // Practice, an Introduction to Multivariate Data Analysis and Experimental Design. 5th ed., CAMO Software AS. 2006, 599 p.Esbensen K. H. Multivariate Data Analysis // Practice, an Introduction to Multivariate Data Analysis and Experimental Design. 5th ed., CAMO Software AS. 2006, 599 p.Rumondor A. C., Taylor L. S. Application of partial least-squares (PLS) modeling in quantifying drug crystallinity in amorphous solid dispersions // Int. J. Pharm. 2010. Vol. 398. Is. 1-2. P. 155-160.Rumondor A. C., Taylor L. S. Application of partial least-squares (PLS) modeling in quantifying drug crystallinity in amorphous solid dispersions // Int. J. Pharm. 2010. Vol. 398. Is. 1-2. P. 155-160.Gushchin K. A., Burikov S. A., Dolen- ko T. A., Persiantsev I. G., Dolenko S. A. Data dimensionality reduction and evaluation of clusterization quality in the problems of analysis of composition of multi-component solutions // Optical Memory and Neural Networks. 2015. Vol. 24. Is. 3. P. 218-224.Gushchin K. A., Burikov S. A., Dolen- ko T. A., Persiantsev I. G., Dolenko S. A. Data dimensionality reduction and evaluation of clusterization quality in the problems of analysis of composition of multi-component solutions // Optical Memory and Neural Networks. 2015. Vol. 24. Is. 3. P. 218-224.Kamruzzaman S. M., Ahmed Ryadh Hasan. Pattern Classification using Simplified Neural Networks. arXiv:1009.4983v1 [cs.NE]Kamruzzaman S. M., Ahmed Ryadh Hasan. Pattern Classification using Simplified Neural Networks. arXiv:1009.4983v1 [cs.NE]Peng H., Ding C., Long F. Minimum redundancy maximum relevance feature selection // IEEE Intelligent Systems. 2005. Vol. 20. No. 6. P. 70-71Peng H., Ding C., Long F. Minimum redundancy maximum relevance feature selection // IEEE Intelligent Systems. 2005. Vol. 20. No. 6. P. 70-71Dolenko S., Burikov S., Dolenko T., Efitorov A., Gushchin K., Persiantsev I. Neural Network Approaches to Solution of the Inverse Problem of Identification and Determination of Partial Concentrations of Salts in Multiсomponent Water Solutions // Lecture Notes in Computer Science. 2014. Vol. 8681. P. 805-Dolenko S., Burikov S., Dolenko T., Efitorov A., Gushchin K., Persiantsev I. Neural Network Approaches to Solution of the Inverse Problem of Identification and Determination of Partial Concentrations of Salts in Multiсomponent Water Solutions // Lecture Notes in Computer Science. 2014. Vol. 8681. P. 805-Efitorov A., Dolenko T., Burikov S., Laptinskiy K., Dolenko S. Solution of an Inverse Problem in Raman Spectroscopy of Multi-component Solutions of Inorganic Salts by Artificial Neural Networks // Lecture Notes in Computer Science. 2016. Vol. 9887. P. 355Efitorov A., Dolenko T., Burikov S., Laptinskiy K., Dolenko S. Solution of an Inverse Problem in Raman Spectroscopy of Multi-component Solutions of Inorganic Salts by Artificial Neural Networks // Lecture Notes in Computer Science. 2016. Vol. 9887. P. 355Strang G., Nguyen T. Wavelets and filter banks. 2nd ed. Wellesley-Cambridge Press, 1996. 520 p.Strang G., Nguyen T. Wavelets and filter banks. 2nd ed. Wellesley-Cambridge Press, 1996. 520 p.Mallat S. G. A theory for multiresolution signal decomposition: the wavelet representation // IEEE Transactions on Pattern Recognition and Machine Intelligence. 1989. Vol. 11. No. 7. P. 674-693.Mallat S. G. A theory for multiresolution signal decomposition: the wavelet representation // IEEE Transactions on Pattern Recognition and Machine Intelligence. 1989. Vol. 11. No. 7. P. 674-693.Daubechies I. Orthonormal bases of compactly supported wavelets // Comm. Pure & Appl. Math. 1988. Vol. 41. No. 7. P. 909- 996.Daubechies I. Orthonormal bases of compactly supported wavelets // Comm. Pure & Appl. Math. 1988. Vol. 41. No. 7. P. 909- 996.Jean-Philippe Lachaux, Antoine Lutz, David Rudrauf, Diego Cosmelli, Michel Le Van Quyen, Jacques Martinerie, Francisco Varela. Estimating the time-course of coherence between single-trial brain signals: an introduction to wavelet coherence // Neurophysiol Clin. Elsevier. 2002. Vol. 32. P. 157-174.Jean-Philippe Lachaux, Antoine Lutz, David Rudrauf, Diego Cosmelli, Michel Le Van Quyen, Jacques Martinerie, Francisco Varela. Estimating the time-course of coherence between single-trial brain signals: an introduction to wavelet coherence // Neurophysiol Clin. Elsevier. 2002. Vol. 32. P. 157-174.Daubechies I. Ten Lectures on Wavelets // SIAM. 1992. 356 p.Daubechies I. Ten Lectures on Wavelets // SIAM. 1992. 356 p.Efitorov A., Dolenko T., Burikov S., Laptinskiy K., Dolenko S. Neural Network Solution of an Inverse Problem in Raman Spectroscopy of Multi-component Solutions of Inorganic Salts // Advances in Intelligent Systems and Computing. 2016. Vol. 449. P. 273-279.Efitorov A., Dolenko T., Burikov S., Laptinskiy K., Dolenko S. Neural Network Solution of an Inverse Problem in Raman Spectroscopy of Multi-component Solutions of Inorganic Salts // Advances in Intelligent Systems and Computing. 2016. Vol. 449. P. 273-279.

The authors declare that there are no conflicts of interest present.