No abstract

To solve the problems existing in traditional biochemical methods, such as complex sample pretreatment requirements, tedious detection processes and low detection accuracies with respect to rice species and adulteration, the volatile flavor substances of five kinds of rice are detected using headspace-gas chromatography-ion mobility spectrometry (HGC-IMS) to effectively identify the quality of rice and adulterated rice. The ion migration fingerprint spectra of five kinds of rice are identified using a semi-supervised generative adversarial network (SSGAN). We replace the output layer of the discriminator in a GAN with a softmax classifier, thus extending the GAN to a semi-supervised GAN. We define additional category tags for generated samples to guide the training process. Semi-supervised training is used to optimize the network parameters, and the trained discriminant network is used for classifying HGC-IMS images. The experimental results show that the prediction accuracy of the model reaches 98.00%, which is significantly higher than the rates achieved by other models, such as a decision tree, a support vector machine (SVM), improved SVM models (LS-SVM and PCA-SVM) and local geometric structure Fisher analysis (LGSFA); 98.00% is also higher than the prediction accuracies of the VGGNet, ResNet and Fast RCNN deep learning models. The experimental results also show that the accuracy of HGC-IMS image classification for identifying adulterated rice reaches 97.30%, which is higher than those of traditional chromatographic or spectral methods. The proposed method overcomes the shortcomings of some intelligent algorithms regarding the application of ion migration spectra and is feasible for accurately predicting rice varieties and adulterated rice.

The terahertz (THz) spectrum of 0.2–1.6 THz (6.6–52.8 cm−1) was used to identify the existence of transgenic rice Bt63 contents in non-GMO rice using a THz time-domain spectroscopy system. Principal component analysis (PCA) was used to extract the feature data based on the cumulative rate of information contribution ( > 90%); the top four principal components were selected and a radial basis function neural network (RBFNN) method was then trained and used. Three selection radial basis functions including a Gaussian function were used to identify the three types (strong positive, weak positive, and negative). The results show that the samples were identified with an accuracy of nearly 90%; additionally, the positive identification rate was > 87.5% and the negative identification rate reached 100% using the proposed method (PCA-RBF). The proposed approach was then compared with other methods, including back propagation (BP) neural networks and support vector machine (SVM). The results of the comparison show that the accuracy of PCA-RBF method reaches 92% in total and all the rest are < 90% using 100 samples. Obviously, the proposed approach outperforms the other methods and also indicates that the proposed method, in combination with THz spectroscopy, is efficient and practical for transgenic ingredient identification in rice.