Computer-Aided Diagnosis Research of a Lung Tumor Based on a Deep Convolutional Neural Network and Global Features

Table 8

Experimental results of different activation functions.

Feature maps	Convolution kernels	Pooling	Activation function	Iterations	Accuracy (%)	Time (s)
6-16-120	5-10-10	Max pooling	Sigmoid	150	73.82	543.73
			ReLU	3	72.07	11.37
20-50-500	5-10-10	Max pooling	Sigmoid	8	80.00	4971.42
			ReLU	1	72.82	1043.57