Robust algorithm for arrhythmia classification in ECG using extreme learning machine

Table 4 Evaluation of the learning times and the testing accuracies among algorithms using BPNN with 10 principle components

Learning rate η	The number of hidden neurons	10	20	30	40	50	60	70	80	90	100
0.0005	Training time (seconds)	4092.19	4213.25	4276.55	4424.77	4455.69	4589.70	4553.02	4640.63	4745.16	4884.30
	Testing accuracy (%)	94.77	94.00	94.16	95.32	94.74	92.62	92.52	90.28	88.77	89.91
0.001	Training time (seconds)	4058.33	4157.41	4218.09	4354.41	4408.23	4500.06	5.75*	1532.38*	2.38*	32.61*
	Testing accuracy (%)	95.02	94.45	95.83	95.51	93.56	91.30	78.17	78.17	78.17	78.17
0.002	Training time (seconds)	4054.50	4212.85	4213.71	4385.40	1.11*	1.12*	1.12*	3.44*	1.17*	144.12*
	Testing accuracy (%)	96.42	95.72	89.37	86.15	78.17	78.17	78.17	78.17	78.17	78.17

The bold characters represent the structure of the network which shows the best accuracy. The asterisk refers the early termination of the learning process, because the decrement of the error is very small.

ISSN: 1475-925X