Spectroscopy and Spectral Analysis, Volume. 45, Issue 2, 492(2025)
Establishment and Optimization of the Hyperspectral Detection Model for Soluble Solids Content in Fortunella Margarita
To develop a rapid measurement method of SSC in Fortunella margarita, the detection models based on hyperspectral imaging data were established and optimized by employing various preprocess and regression algorithms, and the pseudo-color distribution of SSC with storage time was analyzed. The 307 whole citrus and 227 hemisected citrus samples were involved in hyperspectral data collection and the SSC values. The effects of preprocessing, including standard normal variate (SNV), multiplicative scatter correction (MSC), Savitzky-Golay (SG) filtering, normalization (NM), first derivative (FD), standardization (SD), and wavelet transformation (WT), on the performance of the partial least squares regression (PLSR) model were compared to select the appropriate preprocessing method. Then, the detection models were established by using PLSR, least absolute shrinkage and selection operator (LASSO) regression, support vector machine regression (SVR), artificial neural networks (ANN), decision trees (DT), random forest (RF) and light gradient boosting machine (Light GBM) algorithms. Furthermore, the models were optimized using genetic algorithms (GA) to select characteristic spectral wavelengths. The results indicated that for the whole citrus samples, the FD preprocessing could extract more features, and the LASSO regression model performed better than other models with 0.925 7 and 0.976 5 as the prediction determination coefficient () and root mean square error of prediction (RMSEP), respectively. For the hemisected samples, the RF model based on the spectral after SD preprocessing had higher at 0.896 3 and lower RMSEP at 1.063 0. The GA could remove 53.85% and 50.58% wavelength variables to reduce the computational complexity for the whole and hemisected sample spectral, of which the SVR model has at 0.918 9. RMSEP at 1.017 3 RF model having at 0.895 3 and RMSEP at 1.084 3 performed better than other models. The results provided a feasible solution for high-throughput, non-destructive detection of SSC of Fortunella margarita.
Get Citation
Copy Citation Text
LI Wei-qi, WANG Yi-fan, YU Yue, LIU Jie. Establishment and Optimization of the Hyperspectral Detection Model for Soluble Solids Content in Fortunella Margarita[J]. Spectroscopy and Spectral Analysis, 2025, 45(2): 492
Received: Feb. 3, 2024
Accepted: May. 21, 2025
Published Online: May. 21, 2025
The Author Email: LIU Jie (liujie@mail.hzau.edu.cn)