Spectroscopic Method for Detection of Soluble Solid Content in Cherry Tomato Using Deep Convolutional Generative Adversarial Network-Based Data Augmentation

Considering insufficient sample numbers in the practical detection of soluble solid content (SSC) in cherry tomato, we proposed a deep convolutional generation adversarial network (DCGAN) model to expand spectral data and SSC label data, and established a one-dimensional convolutional neural network regression (1D-CNNR) model to improve the prediction accuracy and generalization capability of the DCGAN model. For comparison, a partial least squares regression (PLSR) model and a support vector regression (SVR) model were established. The original dataset of 80 samples, the DCGAN extended dataset of 1 000 samples and the combined dataset of 1 080 samples were separately used for modeling and prediction with 1D-CNNR, SVR and PLSR. To further verify the generalization capability of the models, a new batch of 40 cherry tomato samples was used as a new test set. The results showed that the 1D-CNNR model based on the calibration set separated from the combined dataset was the optimal regression model for SSC detection. The prediction accuracy of the model for the test set from the combined dataset was the highest, with correlation coefficient of prediction (rp) of 0.980 7, and root mean square error of prediction (RMSEp) of 0.192 9. The prediction accuracy of the 1D-CNNR model for the new test set of 40 samples was also the highest, with rp of 0.963 8 and RMSEp of 0.224 5. This study provides a new idea for the accurate determination of the SSC in cherry tomato.