Feature Extraction and Selection Scheme for Intelligent Engine Fault Diagnosis Based on 2DNMF, Mutual Information, and NSGA-II

Table 3

Engine faults classification performances of four feature subsets , and based on three classifiers.

Classifiers	Feature subsets	Dimension of the feature subset	Computation time (s)	Classification accuracy (%)
KNNC		100	—	92.5
		40	2.54	96.25
		25	102.3	100
		7	49.6	100
NBC		100	—	87.5
		40	2.54	88.75
		24	148.25	96.25
		9	86.5	97.5
SVM		100	—	96.25
		40	2.54	97.5
		27	496.4	100
		9	172.8	100