Assessment of Electrocardiogram Rhythms by GoogLeNet Deep Neural Network Architecture

Table 2

Components of the deep learning model using GoogLeNet inception architecture.

Deep learning list	Parameters
Input size	200∼600
CNN layer	Number of filters: 15
	Kernel size: 5
	Stride: 1
	Padding: 0
Max-pooling layer	Pooling size: 2
	Stride: 2
	Padding: 0
Inception layer	Number of filters: 3∼15
	Kernel size: 1, 3, 5
	Pooling size: 3 × 3
	Stride: 1
	Padding: 0
FC layer	2 layers, [100, 50] neurons
Output size	5 classes
Iteration	10
Weight optimization function	Adam
Optimization parameters	Learning rate: 0.001, beta1: 0.9, beta2: 0.999
Batch size	100
Batch normalization	Not used
Dropout	Not used