location:Home > 2024 Vol.7 Apr.N02 > Quantitative analysis of polycyclic aromatic hydrocarbons based on ensemble learning

2024 Vol.7 Apr.N02

  • Title: Quantitative analysis of polycyclic aromatic hydrocarbons based on ensemble learning
  • Name: Jialing Sun, YuanboShi
  • Company: School of Artificial Intelligence and Software, Liaoning Petrochemical University,Fushun 113001,China
  • Abstract:

    Food safety is of great concern, and polycyclic aromatic hydrocarbons such as benzopyrene have strong carcinogenicity. Excessive presence in edible oil can harm health. Raman spectroscopy concentration prediction is a research hotspot, and combining it with computer intelligence is more popular. This article adopts an ensemble learning fusion deep learning model, using benzopyrene Raman spectroscopy data as the dataset and CNN, GRU, and MLP as the basic models, to conduct quantitative analysis through stacking regression strategy. The experimental results show that the method has strong generalization ability, improved performance, and higher prediction accuracy when applied to the detection of benzo (a) pyrene in edible oil.


  • Keyword: Raman spectra;Ensemble learning;quantitative analysis
  • DOI: 10.12250/jpciams2024090313
  • Citation form: Jialing Sun.Quantitative analysis of polycyclic aromatic hydrocarbons based on ensemble learning [J]. Computer Informatization and Mechanical System,2024,Vol.7,pp.58-60
Reference:

[1] Lawal A T. Polycyclic aromatic hydrocarbons. A review[J]. Cogent Environmental Science, 2017, 3(1): 1339841.

[2] Mastrangelo G, Fadda E, Marzia V. Polycyclic aromatic hydrocarbons and cancer in man[J]. Environmental health perspectives, 1996, 104(11): 1166-1170.

[3] Liu W, Sun S, Liu Y, et al. Determination of benzo (a) pyrene in peanut oil based on Raman spectroscopy and machine learning methods[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2023, 299: 122806.

[4] Afseth N K, Segtnan V H, Wold J P. Raman spectra of biological samples: A study of preprocessing methods[J]. Applied spectroscopy, 2006, 60(12): 1358-1367.

[5] Bocklitz T, Walter A, Hartmann K, et al. How to pre-process Raman spectra for reliable and stable models?[J]. Analytica chimica acta, 2011, 704(1-2): 47-56.


Tsuruta Institute of Medical Information Technology
Address:[502,5-47-6], Tsuyama, Tsukuba, Saitama, Japan TEL:008148-28809 fax:008148-28808 Japan,Email:jpciams@hotmail.com,2019-09-16