Information system based on a complex model using machine learning for spectral analysis
DOI:
https://doi.org/10.17721/1812-5409.2025/1.14Keywords:
information system, artificial intelligence, spectral analysis, modeling, machine learning, intelligent data analysisAbstract
The research is devoted to the design and development of an information system based on a complex model using machine learning methods to automate spectral analysis to increase the accuracy and speed of data processing. The history of the research is connected with the development of analytical methods in physics, chemistry and biology, where spectral analysis has traditionally played a key role. However, modern challenges, in particular the growth of data volumes and the need for automation, have stimulated the introduction of innovative methods based on artificial intelligence.
The relevance is due to the need to process large volumes of complex spectral data in real time, which is important for medicine, ecology, chemistry and other industries. Traditional analysis methods have limitations, so the use of machine learning is appropriate to increase the efficiency of the process.
The research focuses on the following issues: how to automate spectral data processing, how to ensure the integration of classical methods with machine learning, and how to increase the accuracy and scalability of the analysis. For this purpose, signal processing methods were applied, including noise filtering, smoothing, baseline correction, and peak analysis using derivatives and numerical integration. Machine learning was implemented through Random Forest models and neural networks adapted for predicting spectrum parameters.
The results showed that the developed system provides high accuracy and speed of spectral data analysis, interactive visualization of spectrum parameters, as well as the ability to integrate with other information platforms. This significantly simplifies analysis processes, reduces dependence on expert intervention, and increases productivity.
Research prospects include optimizing mathematical models for even greater accuracy, integration with IoT systems, and expanding the functionality for analyzing complex multidimensional spectra. This opens up opportunities for application in interdisciplinary projects, such as monitoring environmental changes or diagnosing medical conditions.
Pages of the article in the issue: 104 - 114
Language of the article: Ukrainian
References
Alsmeyer, F., & Marquardt, W. (2004). Automatic Generation of Peak-Shaped Models. Applied Spectroscopy, 58, 986–994. https://opg.optica.org/as/abstract.cfm?uri=as-58-8-986
Bilak, Yu., Kozubovskii, V., & Rol, M. (2023). Using the Fabry – Pérot interferometer as a spectral mask. Journal of Physical Studies, 27(1), 1402–1409. https://doi.org/10.30970/jps.27.1402
Butler, K. T., Davies, D. W., Cartwright, H., Isayev, O., & Walsh, A. (2018). Machine learning for molecular and materials science. Nature, 559, 547–555. https://doi.org/10.1038/s41586-018-0337-2
Butucea, C., Delmas, J.-F., Dutfoy, A., & Hardy, C. (2021). Modeling Infrared Spectra: An Algorithm for an Automatic and Simultaneous Analysis. In B. Castanier, M. Cepin, D. Bigaud, & C. Berenguer (Eds.), 31st European Safety and Reliability Conference (ESREL), Angers, France (pp. 3359–3366). https://doi.org/10.3850/978-981-18-2016-8_732-cd
Griffiths, P. (1983). Fourier Transform Infrared Spectrometry. Science, 222(4621), 297–302. https://doi.org/10.1126/science.6623077
Huang, L. (2014). Modeling and Simulation in Spectroscopic Study. Spectral Analysis Review, 2(3), 7–9. https://doi.org/10.4236/sar.2014.23023
Kozubovsky, V. R., & Bilak, Y. Y. (2022). Express Analysis of Gas Mixtures Using a Spectral Correlator Based on the Fabry – Perot Interferometer. Journal of Applied Spectroscopy, 89, 495–499. https://doi.org/10.1007/s10812-022-01385-7
Kriesten, E., Alsmeyer, F., Bardow, A., & Marquardt, W. (2008). Fully automated indirect hard modeling of mixture spectra. Chemometrics and Intelligent Laboratory Systems, 91(2), 181–193. https://doi.org/10.1016/j.chemolab.2007.11.004
Lavanya, A., Sindhuja, S., Gaurav, L., & Ali, W. (2023). Assessing the Performance of Python Data Visualization Libraries. International Journal of Computer Engineering in Research Trends, 10, 28–39. https://doi.org/10.22362/ijcert/2023/v10/i01/v10i0104
Mishra, P., Passos, D., Marini, F., Xu, J., Amigo, J. M., Gowen, A. A., Jansen, J. J., Biancolillo, A., Roger, J. M., Rutledge, D. N., & Nordon, A. (2022). Deep learning for near-infrared spectral data modelling: Hypes and benefits. TrAC Trends in Analytical Chemistry, 157(2), 116804. https://doi.org/10.1016/j.trac.2022.116804
Murray, S. (2013). Interactive Data Visualization for the Web. O'Reilly Media, Inc. https://www.oreilly.com/library/view/interactive-data-visualization/9781449340223/
Rodionova, O. Y., & Brereton, R. G. (2005). Chemometrics: Data Analysis for the Laboratory and Chemical Plant. Journal of Analytical Chemistry, 60, 994–996. https://doi.org/10.1007/s10809-005-0223-6
Shuaibov, O. K., Hrytsak, R. V., Minya, O. I., Malinina, A. A., Bilak, Yu. Yu., & Gomoki, Z. T. (2022). Spectroscopic diagnostics of overstressed nanosecond discharge plasma between zinc electrodes in air and nitrogen. Journal of physical studies, 26(2), 2501–2509. https://doi.org/10.30970/jps.26.2501
Tagliaferri, R., Ciaramella, A., Barone, F., Longo, G., & Milano, L. (2001). Neural Networks for Spectral Analysis of Unevenly Sampled Data. In A. J. Banday, S. Zaroubi, & M. Bartelmann (Eds.), Mining the Sky (pp. 386–390). Springer Nature. https://doi.org/10.1007/10849171_47
McKinney, W. (2017). Python for Data Analysis (2nd ed.). O'Reilly Media. https://www.oreilly.com/library/view/python-for-data/9781491957653/
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Yuriy Bilak
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).
