Fig. 2

Comparison of Confusion Matrixs among machine learning models under full feature set (A) and selected feature set (B). The confusion matrix is a 2 × 2 matrix that contains the following four elements: True Positive (top left of the matrix); False Positive (bottom left of the matrix); True Negative (bottom right of the matrix); False Negative (top right of the matrix). Through the analysis of the confusion matrix, we can calculate many performance indicators such as accuracy, recall, precision, and F1 score to evaluate the classification performance of the model on different categories