Association Rule-Based Feature Mining for Automated Fault Diagnosis of Rolling Bearing

Table 2

Interval class-information entropy based on different discretization methods.

	fBPFO	fBSF	fBPFI	f	xMV	xSD	xRMS	xRA	xCF	xS	xK	xKC
Equal probability	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
	0.00	0.00	0.80	0.00	1.43	1.45	1.45	1.50	1.99	0.00	0.00	0.00
	2.26	2.16	2.00	2.58	0.92	1.49	1.49	2.21	1.50	2.62	2.39	2.09
	2.23	1.47	0.00	1.00	2.13	1.13	1.13	1.46	0.95	1.53	1.00	1.05
	0.00	1.75	0.97	0.00	1.89	0.00	0.00	0.00	1.73	0.00	0.00	1.28
Equal density	0.00	0.00	0.00	0.35	1.56	0.00	0.00	0.00	0.00	1.77	0.00	0.91
	0.91	1.24	1.51	1.78	1.23	0.92	0.92	1.00	0.00	1.80	0.35	1.37
	1.37	1.46	1.43	1.81	2.15	1.23	1.23	1.29	1.23	1.05	1.38	0.92
	1.57	2.07	1.81	2.18	1.97	1.05	1.05	1.46	1.52	1.04	0.35	0.91
	1.51	1.43	0.84	2.09	2.15	1.81	1.89	1.69	1.23	1.55	1.16	0.57
Equal width	2.86	2.52	2.32	2.58	0.00	1.94	1.94	1.65	2.21	2.71	2.81	2.92
	0.67	1.85	0.87	0.50	0.00	1.79	1.79	1.94	1.33	0.34	0.00	1.83
	0.00	1.29	1.00	0.88	1.52	1.16	1.16	0.92	1.73	0.00	1.00	1.00
	0.00	0.98	0.85	0.00	2.17	0.00	0.00	0.00	0.00	0.00	0.72	1.28
	0.00	0.00	0.00	0.00	2.28	0.00	0.00	0.00	0.99	0.00	0.92	0.00