Abstract:
In order to identify the moldy rice rapidly, an electronic nose system based on LabVIEW was developed. The volatiles of rice samples mixed with different proportions of moldy rice in different days were detected by the electronic nose system. Principal component analysis (PCA) and linear discriminant analysis (LDA) were performed on the collected data. Finally, back propagation (BP) neural network was used to establish the prediction model. The results showed that, there was significant difference in volatile matter between normal rice and moldy rice volatiles, and the LDA classification effect was better than PCA. The correlation between predicted value and actual value of the model was more than 0.953, the average relative error of training set and test set was 3.56% and 4.18%, and the recognition rate of training set and test set was 100% for normal rice samples. In conclusion, the electronic nose system could be used as an effective means of non-destructive detection of moldy rice, and had practical significance in rice quality identification.