High precision qualitative identification of yeast growth phases using molecular fusion spectra

Compared to a single molecule spectral analysis method, molecular fusion spectroscopy can obtain multi-dimensional information reflecting the target attributes more comprehensively, which makes this method have potential application value in online monitoring of microbial fermentation process. This study proposes a method based on near-infrared (NIR) and Raman molecular fusion spectroscopy for high precision identification of yeast growth phases. First, the original spectra of yeast broth were preprocessed using Savitzky-Golay (SG) convolution smoothing combined with standard normal variate (SNV). Then, a novel fusion algorithm, which was discriminant correlation analysis (DCA), was used to realize the effective fusion of the NIR and Raman spectra after preprocessing in the feature layer. Finally, a linear discriminant analysis (LDA) identification model was developed based on the DCA fusion feature vectors. The results showed that the prediction performance of the LDA identification model based on the eigenvectors by the DCA fusion is far better than the best LDA model based on the single molecule spectra, and its correct identification rate is 97.37% in the prediction set. The overall results demonstrate that molecular fusion spectroscopy can achieve high precision and rapid monitoring of yeast fermentation process, and the DCA is an effective tool for molecular spectral fusion.