A Method for Detecting the Adulteration Categories of Camellia Oil Based on Random Forest

To achieve rapid detection of camellia oil adulteration, this paper proposes a camellia oil adulteration detection method based on random forest. By analyzing the mass spectrometry data of pure camellia oil and samples of rapeseed oil, rice bran oil, peanut oil, and sesame oil with a 20% adulteration ratio, and extracting spectral peak features, and using analysis of variance for feature selection, a random forest classification model is established for training and adulteration classification testing. The experimental results show that the accuracy rate is 93.33 %, providing an effective solution for the detection of camellia oil adulteration through mass spectrometry data and machine learning.