Raman spectroscopy-based adversarial network combined with SVM for detection of foodborne pathogenic bacteria.

Raman spectroscopy combined with artificial intelligence algorithms have been widely explored and focused on in recent years for food safety testing. It is still a challenge to overcome the cumbersome culture process of bacteria and the need for a large number of samples, which hinder qualitative analysis, to obtain a high classification accuracy. In this paper, we propose a method based on Raman spectroscopy combined with generative adversarial network and multiclass support vector machine to classify foodborne pathogenic bacteria. 30,000 iterations of generative adversarial network are trained for three strains of bacteria, generative model G generates data similar to the actual samples, discriminant model D verifies the accuracy of the generated data, and 19 feature variables are obtained by selecting the feature bands according to the Raman spectroscopy pattern. Better classification results are obtained by optimising the parameters of the multi-class support vector machine, etc. Our detection and classification method not only solves the problem of needing a large number of samples as training set, but also improves the accuracy of the classification model. Therefore, this GAN-SVM classification model provides a new idea for the detection of bacteria based on Raman spectroscopy technology combined with artificial intelligence algorithms.