“…In current practical applications, systematic clustering and K-means clustering are the two most widely used classes. It is to first treat each sample as a class, and then define the distance between classes systematic clustering, also known as hierarchical clustering, merges the smallest pair of distance between classes to form a new class, and then calculates the distance between the newly generated classes and other classes, merges the two closest classes, and repeats the merging, each time merging will Each time the merger is repeated, one class is reduced until finally all related classes are merged into one class [11]. K-mean clustering, on the other hand, views the data as points on a K-dimensional space, and uses distance as the criterion for cluster analysis, dividing the samples into specified K classes, i.e., the number of categories needs to be developed in advance.…”