Skip to main content

Table 3 The initial and training parameters

From: A particle swarm optimization improved BP neural network intelligent model for electrocardiogram classification

Parameters

Numerical value

Significance

indim

16

Number of input variables

hiddennum

5

Number of hidden unit

outdim

1

Number of output variables

vmax

1

Maximum velocity

minerr

0.0001

Minimum error

wmax

0.95

Maximum inertia weight

wmin

0.10

Minimum inertia weight

itermax

100

Maximum iteration number

c1

2.5

Local learning factor

c2

2.7

Global learning factor

k

0.37

Shrinkage factor

N

75

Number of particles

D2

116

Length of particle