Abstract
Taking different grades of strong-flavor raw liquor as the research object, gas chromatography-mass spectrometry (GC-MS) technology was used to obtain the volatile components mapping data of raw liquor, and Spearman correlation coefficient (Spearman) combined with principal component analysis (PCA) and kernel principal component analysis (KPCA) was used to realize the secondary feature extraction of the GC-MS data, and then combined with the support vector machine (SVM), extreme gradient boosting (XGBoost), and BP neural network to establish the raw liquor grades identification model, respectively. The results show that the prediction accuracy of the grade identification model based on Spearman-KPCA dimensionality reduction data is better, in which the Spearman-KPCA-BP neural network model has the best classification effect, and the accuracy of the correction set and prediction set reaches 99.44% and 96.10%, respectively. Research shows that the principal components extracted based on Spearman-KPCA secondary features can better characterize the characteristic information of different grades of raw liquor. Combined with the BP neural network model, it can effectively realize the identification of different grades of raw liquor. It is an effective method for identifying the grade of raw liquor.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.