Variational mode decomposition unfolded extreme learning machine for spectral quantitative analysis of complex samples.

Journal: Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy
Published Date: May 8, 2025

Abstract

Considering the advantages of variational mode decomposition (VMD) in mathematical decomposition and extreme learning machine (ELM) in data modeling, a new regression model named variational mode decomposition unfolded extreme learning machine (VMD-UELM) is introduced for spectral quantitative analysis of complex samples. Firstly, mode components (uk) are obtained by decomposing spectra in VMD. Then the mode components are unfolded into an extended matrix. Ultimately, a quantitative model is built between the matrix and the target values by ELM. Efficiency of VMD-UELM is validated by quantitative analysis of hemoglobin, diaromatics and Panax notoginseng (PN) in blood, fuel oil and adulterated herb datasets. Results show that VMD-UELM model demonstrates better or similar performance compared with partial least squares (PLS) and ELM. Therefore, VMD-UELM is an efficient approach for spectral quantitative analysis.

Authors

  • Liangliang Shen
    School of Chemical Engineering and Technology, Tiangong University, Tianjin 300387, PR China.
  • Jiajing Zhao
    Shanxi Laboratory of Energetic Materials, Xi'an Modern Chemistry Research Institute, Xi'an 710065, PR China.
  • Deyun Wu
    School of Chemical Engineering and Technology, Tiangong University, Tianjin 300387, PR China.
  • Xiaoyao Tan
    State Key Laboratory of Separation Membranes and Membrane Processes, Tiangong University, Tianjin 300387, People's Republic of China; School of Chemistry and Chemical Engineering, Tiangong University, Tianjin 300387, People's Republic of China. Electronic address: tanxiaoyao@tjpu.edu.cn.
  • Xihui Bian
    State Key Laboratory of Separation Membranes and Membrane Processes, Tiangong University, Tianjin 300387, People's Republic of China; School of Chemistry and Chemical Engineering, Tiangong University, Tianjin 300387, People's Republic of China. Electronic address: bianxihui@163.com.

Keywords

External Resources

Popular Topics
Recent Journals