New State Identification Method for Rotating Machinery under Variable Load Conditions Based on Hybrid Entropy Features and Joint Distribution Adaptation

Table 4

Diagnosis results of Cases 1–5 by using JDA-KNN, KNN, SVM, and RF.

	JDA-KNN			KNN (%)	SVM (%)	RF (%)
		K	Accuracy (%)
Case 1	110	18	99.17	88.75	84.58	95.21
Case 2	50	20	98.12	92.50	91.25	97.50
Case 3	50	20	98.06	92.78	91.25	95.63
Case 4	120	20	99.58	94.06	98.85	98.54
Case 5	50	20	98.06	88.96	92.29	97.08