Monitoring of solid-state fermentation of protein feed by electronic nose and chemometric analysis

• E-nose technique was attempted to monitor the SSF process of protein feed.
• Application of linear and non-linear algorithms in calibrating discrimination model using e-nose data.
• Optimizing discrimination model by five-fold cross-validation.

To achieve the real-time smell monitoring of solid-state fermentation (SSF) of protein feed associated with its degree of fermentation. Electronic nose (e-nose) technique, with the help of chemometric analysis, was attempted in this study. Linear discriminant analysis (LDA), K-nearest neighbors (KNN), and support vector machines (SVM) were respectively used to calibrate discrimination models in order to evaluate the influences of different linear and non-linear classification algorithms on the identification results. Experimental results showed that the predictive precision of SVM model was superior to those of the others two, and the optimum SVM model was obtained when five PCs were included. The discrimination rates of the SVM model were 97.14% and 91.43% in the training and testing sets, respectively. The overall results sufficiently demonstrate excellent promise for the e-nose technique combined with an appropriate chemometric method to be applied in the SSF industry.