Machine learning technique combined with data fusion strategies: A tea grade discrimination platform

Abstract

It is desirable to give a full-scaled evaluation of vine tea by incorporating both the quality related compounds in high content and the volatile compounds in trace level. The NIR and GC-MS technologies were performed for vine tea grade discrimination through data fusion approaches. Two machine learning methods of random forest (RF) and partial least squares-discrimination analysis (PLS-DA) were carried out to construct the tea grade discrimination platform with eight data driven models. Besides, the Monte-Carlo technology was implemented to acquire more representative results from thirty sub-models. As a result, the mid-level fusion combined with RF (92.38% ± 0.0446%) gave more impressive performance owing to the overall analysis with more balanced matrix, efficient features, and remarkable discriminant ability. The results revealed that the mid-level fusion coupled with RF is a promising method for tea grade identification and have great potential to guarantee the food quality.