• Laser & Optoelectronics Progress
  • Vol. 58, Issue 1, 130002 (2021)
Wang Xiaobin1、2, Ma Xiao1, Yang Lei1、2, and Li Chunyu1、2、*
Author Affiliations
  • 1School of Forensic Science, People''s Public Security University of China, Beijing 100038, China
  • 2Forensic Science Experimental Teaching Center, People''s Public Security University of China, Beijing 100038, China
  • show less
    DOI: 10.3788/LOP202158.0130002 Cite this Article Set citation alerts
    Wang Xiaobin, Ma Xiao, Yang Lei, Li Chunyu. Multi-Layer Perceptron Pattern Recognition of Handwriting Ink Based on PLS-DA Raman Spectral Feature Extraction[J]. Laser & Optoelectronics Progress, 2021, 58(1): 130002 Copy Citation Text show less
    Raman spectra of samples after pre-processing
    Fig. 1. Raman spectra of samples after pre-processing
    PLS-DA score graph
    Fig. 2. PLS-DA score graph
    ROC curve and area under the curve AUC of 5 types of samples
    Fig. 3. ROC curve and area under the curve AUC of 5 types of samples
    VIP value of independent variables
    Fig. 4. VIP value of independent variables
    Structure of multi-layer perceptron
    Fig. 5. Structure of multi-layer perceptron
    Changes of cross-entropy in epoch
    Fig. 6. Changes of cross-entropy in epoch
    Actual classPredicted class
    12345
    1322040
    2117100
    3032000
    410070
    5000111
    Table 1. Classification results of multi-layer perceptron
    Wang Xiaobin, Ma Xiao, Yang Lei, Li Chunyu. Multi-Layer Perceptron Pattern Recognition of Handwriting Ink Based on PLS-DA Raman Spectral Feature Extraction[J]. Laser & Optoelectronics Progress, 2021, 58(1): 130002
    Download Citation