Reliable Fault Classification of Induction Motors Using Texture Feature Extraction and a Multiclass Support Vector Machine

Table 6

True positive and false positive of classification accuracy with noise (SNR = 20 dB).

Algorithm	Average classification accuracy in terms of true positive and false positive								Average
	AMF	BRBF	NO	RIF	BF	BSF	PMF	PIF
Algorithm 1 [11]
TP	91.54	88.08	84.04	90.96	95.96	99.04	95.96	79.81	90.67375
FP	1.92	0.49	2.58	0.99	0.14	0.58	0.41	3.38	1.31125
Algorithm 2 [10]
TP	98.27	86.92	72.31	99.23	99.42	100.00	93.84	100.0	93.74875
FP	0.00	3.65	1.32	0.14	0.00	0.14	0.91	1.02	0.8975
Algorithm 3 [4]
TP	97.31	87.88	84.42	100.00	100.00	100.00	100.00	100.0	96.20125
FP	0.00	0.00	1.43	2.61	0.30	0.00	0.00	0.00	0.5425
Proposed approach
TP	100.0	100.0	100.0	100.00	100.00	100.00	100.00	100.0	100.00
FP	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00