Research on DOM Component Detection Based on Multiple Classifiers
Optimized by Swarm Intelligence Algorithm
FU Li-hui1, DAI Jun-feng2*, WANG Xiao-yan2
1. Faculty of Automation，Huaiyin Institute of Technology，Huai'an 223003，China
2. Faculty of Electronic Information Engineering，Huaiyin Institute of Technology，Huai'an 223003，China
Abstract：Dissolved organic matter (DOM) is one of the important factors affecting the ecological environment and the safety of residents' lives. When the total amount of DOM reaches a certain level, it will lead to the explosive growth of algae through water eutrophication, which makes the DOM composition more complex and the impact more severe. Although the standard detection methods can qualitatively analyze DOM, there are always bottlenecks in determining DOM components, and it is difficult for a single sensor to complete the complicated test of the total amount and components of DOM in water. Therefore, a DOM test scheme is proposed based on the cross-sensitivity between SPR (Surface Plasmon Resonance, SPR) sensors. Three classifiers are constructed using the BP (Back Propagation, BP) neural network trained by the swarm intelligence algorithm (Particle Swarm Optimization, PSO). The multi-mode fibers are coated with seven kinds of gold films with different thicknesses of 55~85 nm to form the SPR sensing probes with different optimal refractive index measurements to ensure the best refractive index measurement value of each sensing probe is effectively distributed in the range of 1.33~1.43 RIU, and each sensing probe has good sensitivity and linearity in the best measurement range. In the measurement range corresponding to other sensing probes, there are cross-responses as sensitive as possible through the change of wavelength, spectral width and light intensity. Finally, combined with the intelligent algorithm based on three classifiers of PSO-BP, through the experimental steps of water sample preparation of DOM, determination of DOM composition, measurement of refractive index and SPR effect, training and verification of artificial intelligence network, to realize the comprehensive training of the resonance wavelength, spectral width and light intensity of SPR effect on the measured samples. Thus, five DOM components (tyrosine proteins, tryptophan proteins, fulvic acid, soluble microbial metabolites, humic acids) of the inner canal(A), Hongze Lake (B), Park Landscape Lake (C) and campus landscape Lake (D) and their concentrations are effectively tested. Among them, the highest prediction rate for the concentration of DOM components in four different water bodies (A, B, C, D) is 81.2% (tyrosine), 85% (Tryptophan), 82% (Tryptophan), and 82.6% (Tryptophan), respectively. At the same time, the influence of the response parameters and the number of classifiers on the prediction effect is investigated, and the results show that the three classifiers have the best prediction effect compared with the two classifiers and the single classifier. The prediction accuracy of five different DOM component concentrations in mixed water sample can reach 81.5%, 84%, 81%, 82%, and 68.3%, respectively, to verify the correctness and feasibility of the multi-classifiers based on PSO-BP and fiber SPR sensor in DOM components prediction.
付丽辉，戴峻峰，王晓燕. 基于群智能优化多分类器的DOM组分检测研究[J]. 光谱学与光谱分析, 2024, 44(08): 2349-2356.
FU Li-hui, DAI Jun-feng, WANG Xiao-yan. Research on DOM Component Detection Based on Multiple Classifiers
Optimized by Swarm Intelligence Algorithm. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(08): 2349-2356.
[1] Wang Y F，Li J N，Xu L，et al. Journal of Environmental Chemical Engineering，2023，11（5）：111115.
[2] Liang E H，Li J R，Li B，et al. Journal of Hazardous Materials，2023，460（15）：132410.
[3] Chen Q，Lü F，Zhang H，et al. Water Research，2023，244（1）：120536.
[4] Zha Y，Li X，Nan J. Environmental Research，2023，236（2）：116855.
[5] FAN Chun-hui，XIN Yi-bei，YUAN Wen-jing（范春辉，辛意贝，袁文静）. Spectroscopy and Spectral Analysis（光谱学与光谱分析），2022, 42（8）：2432.
[6] SUN Jing，ZHAO Ge-ge，ZHANG Yun-bo，et al（孙 婧，赵阁阁，张运波，等）. China Water & Wastewater（中国给水排水），2021，37（23）：21.
[7] He J，Zhi G Q，Yang Y，et al. Ecological Indicators，2022，142：109088.
[8] Qiu J J，Li T Q，Lü F，et al. Journal of Environmental Sciences，2023，126：174.
[9] Min J Y，Lee J W，Bae G S，et al. Food Chemistry: X，2023，20：100889.
[10] Xu J，Xu J J，Tong Z Y，et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy，2023，296（5）：122646.
[11] Mishra S K，Tripathi D C，Mishra A K. Plasmonics，2022，（2）：17.
[12] JIA Mei-hui，LI Li-juan, REN Jiao-jiao，et al（贾美慧，李丽娟，任姣姣，等）. Acta Photonica Sinica（光子学报），2021，50（9）：193.
[13] Yu Y S，Zhang H Y. Measurement，2023，218（15）：113197.
