Research Article
Computer-Aided Diagnosis Research of a Lung Tumor Based on a Deep Convolutional Neural Network and Global Features
Table 6
Experimental results of different sampling methods.
| Feature maps | Convolution kernels | Activation function | Pooling | Iterations/accuracy (%) | Time (s) | 5 | 10 | 12 | 15 | 20 | 30 | 50 | 100 |
| 6-16-120 | 5-10-10 | Sigmoid | Max | 60.08 | 65.37 | 79.94 | 73.75 | 71.76 | 70.26 | 69.86 | 63.67 | 2738.62 | Avg | 50.00 | 68.66 | 76.65 | 68.06 | 65.37 | 61.58 | 57.49 | 58.48 | 2718.68 |
|
|