Fig. 8 figure 8 Visual confusion matrix of three different Phone Number List modeling methods based on feature fusion, where R, S and X stand for “RF,” “SVM” and “XGBoost,” respectively Full size image Screening of characteristic wavelengths Compared Phone Number List with the previous models under single features, the accuracy of the model based on features fusion is not significantly improved. Still, the features fusion increases the data volume, and the Phone Number List redundant information is added.
Therefore, in order to simplify the model and Phone Number List mprove the accuracy of the model, CARS algorithm was used to screen the wavelength of the normalized spectral feature data in MATLAB. The process of CARS screening wavelength is Phone Number List shown in Fig. 9. Fig. 9 figure 9 The CARS screening wavelength process: (a) trend chart of the number of wavelengths; (b) trend chart of the RMSECV; (c) trend chart of the regression Phone Number List coefficients of the wavelength variables Full size image From Fig.
The number of sampling times is Phone Number List set to 100, and Fig. 9a shows the trend of the number of variables with the number of sampling Phone Number List runs, and the number of selected wavelengths gradually decreases as the number of the sampling runs increases. Figure 9b shows the trend of RMSECV with the number of sampling Phone Number List runs, and the RMSECV decreases slowly at the beginning, it indicates that some irrelevant variables are removed in the process of sampling. And then the RMSECV steps up, and some variables with high correlation are removed (Li et al. 2021b). Figure 9c shows that the RMSECV is the smallest when Phone Number List the sampling number is 29, at which time a total of 50 characteristic wavelengths are screened out, accounting for 28.41% of the full band.