Skip to main content

Table 7 Comparing the results of preceding research

From: Robust algorithm for arrhythmia classification in ECG using extreme learning machine

Method

Number of beat types

Training Data Set/Test Data Set

Accuracy (%)

ICA-BPNN[2]

8

(4900/4900)

98.37

DWT-NN[4]

13

(30293/75130)

96.79

FTNN [5]

3

(540/250)

98.0

Wavelet-PNN[6]

6

(11600/11600)

99.65

MOE [21]

4

about (10000/49260)

94.0

Fhyb-HOSA[22]

7

(4035/3150)

96.06

BSS-Fourier[23]

5

(320/160)*

85.04

PCA-ELM[24]

7

(3450/3450)

97.45

Proposed Algorithm

6

(10000/75853)

98.72

  1. * [23] did not use with MIT-BIH arrhythmia DB as the training and test data set.