The background differences in water content of different samples have a very strong influence on the robustness of near-infrared spectroscopy (NIRS). For this reason, this study simulated typical biological water matrix samples with formulated hemoglobin (Hb), glucose (Glc), and distilled water, and attempted to use four different intelligent spectral variable selection algorithms [Competitive Adaptive Reweighted Sampling (CARS), Randomized Frog Hopping Algorithm (RF), Genetic Algorithm (GA), and Variable Projection Importance Algorithm (VIP)] to perform the Hb water interference-resistant feature band preferences, while combining partial least squares (PLS) in parallel to build a robust quantitative model of Hb. In addition, the applicability and validity of the model were validated using three prediction sets P1, P2, P3 with different water backgrounds (the formulation method and composition were kept the same, and only the water content increased sequentially). The results showed that RF, GA, and VIP could effectively screen out the characteristic wavelengths of Hb with low sensitivity to water changes and successfully correct the water effect, but due to the large number of characteristic variables they screened out and the existence of a large number of redundant and water interference variables, this ultimately made the model's robustness less than ideal. The CARS algorithm performed the best, and the RMSEP of the three prediction sets were 0.016, 0.017, and 0.038, which is closer to the RMSECV of the calibration set. Therefore, NIRS combined with the variable selection can reduce the effect of water on model robustness and improve the prediction accuracy of the model by the method of selecting effective wave number intervals, and CARS may be one of the ideal algorithms to solve such problems.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
D. Moorthy, R. Merrill, S. Namaste, and L. Iannotti, Adv. Nutr., 11, No. 6, 1631–1645 (2020).
D. Lelli, R. A. Incalzi, and C. Pedone, J. Am. Geriat. Soc., 65, No. 11, 2369–2373 (2017).
J. T. Kuenstner, K. H. Norris, and W. F. Mc Carthy, Appl. Spectrosc., 48, No. 4, 484–488 (1994).
K. Y. Wang, X. H. Bian, M. Zheng, P. Liu, L. G. Lin, and X. Y. Tan, Spectrochim. Acta A, 263, Article ID 120138 (2021).
H. Tian, L. N. Zhang, M. Li, Y. Wang, D. G. Sheng, J. Liu, and C. M. Wang, Infrared Phys. Technol., 102, Article ID 103003 (2019).
H. Y. Yang, S. N. Yang, J. L. Kong, A. C. Dong, and S. N. Yu, Nat. Protoc., 10, No. 3, 382–396 (2015).
M. L. Fan, W. C. Cai, and X. S. Shao, Appl. Spectrosc., 71, No. 3, 472–479 (2017).
K. I. Izutsu, Y. Fujimaki, A. Kusabara, Y. Hiyama, C. Yomota, and N. Aogagi, J. Pharm. Sci-Us., 95, No. 4, 781–789 (2006).
J. A. Hageman, J. A. Westerhuis, and A. K. Smilde, J. Near Infrared Spectrosc., 13, 53–62 (2005).
N. K. Wijewardane, Y. Ge, and C. L. S. Morgan, Eur. J. Soil Sci., 67, No. 5, 605–615 (2016).
Y. P. Du, Y. Z. Liang, and Y. Ozaki, Anal. Sci., 20, No. 9, 1339–1345 (2004).
S. Chakraborty, B. Li, D. C. Weindorfc, and C. L. S. Morgan, Geoderma, 337, 65–75 (2019).
H. Swierenga, P. J. de Groot, A. P. de Weijer, M. W. J. Derksen, and L. M. C. Buydens, Chemometr. Intell. Lab., 41, No. 2, 237–248 (1998).
B. Nadler and R. R. Coifman, J. Chemometrics, 19, No. 2, 107–118 (2005).
Y. H. Yun, Li, B. C. Deng, and D. S. Cao, Tract. Trend. Anal. Chem., 113, 102–115 (2019).
K. Rahlow and W. Hubner, Appl. Spectrosc., 51, No. 2, 160–170 (1997).
S. S. Bai, H. Wang, Y. J. Chen, and H. S. Wang, Spectrosc. Spectral. Anal., 35, No. 4, 894–898 (2015).
B. Yuan, K. Murayama, Y. Q. Wu, R. Tsenkova, X. M. Dou, S. Era, and Y. Ozaki, Appl. Spectrosc., 57, No. 10, 1223–1229 (2003).
H. D. Li, Y. Z. Liang, Q. S. Xu, and D. S. Cao, Anal. Chim. Acta, 648, 77–84 (2009).
H. D. Li, Q. S. Xu, and Y. Z. Liang, Anal. Chim. Acta, 740, 20–26 (2012).
R. M. Jarvis and R. Goodacre, Bioinformatics, 21, No. 7, 860–868 (2005).
I. G. Chong and C. H. Jun, Chemometr. Intell. Lab., 41, No. 2, 103–112 (2005).
Author information
Authors and Affiliations
Corresponding author
Additional information
Abstract of article is published in Zhurnal Prikladnoi Spektroskopii, Vol. 91, No. 4, p. 613, July–August, 2024.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Fang, R., Han, X., Li, X. et al. Variable Selection in Near-Infrared Spectra for Modeling of Hemoglobin Content in Bio-Water Solutions. J Appl Spectrosc (2024). https://doi.org/10.1007/s10812-024-01801-0
Published:
DOI: https://doi.org/10.1007/s10812-024-01801-0