Table 1 Performance evaluation indexes of the deep learning network models.
From: Mineral prospectivity prediction based on convolutional neural network and ensemble learning
Networks model | Classes (0-Non-ore-bearing; 1-Ore-bearing) | Precision (%) | Recall (%) | F1-score(%) | Accuracy (%) | Mean precision(%) | Mean recall(%) | Mean F1-score(%) | |
|---|---|---|---|---|---|---|---|---|---|
CNN | LeNet | 0 | 97.43 | 97.43 | 97.43 | 96.50 | 95.99 | 95.99 | 95.99 |
1 | 94.55 | 94.55 | 94.55 | ||||||
AlexNet | 0 | 97.85 | 97.71 | 97.78 | 96.99 | 96.51 | 96.58 | 96.55 | |
1 | 95.17 | 95.45 | 95.31 | ||||||
VGG 16 | 0 | 98.01 | 98.29 | 98.15 | 97.48 | 97.18 | 97.03 | 97.10 | |
1 | 96.34 | 95.76 | 96.04 | ||||||
ResNet 50 | 0 | 97.87 | 98.57 | 98.22 | 97.57 | 97.40 | 97.01 | 97.20 | |
1 | 96.92 | 95.45 | 96.18 | ||||||
Mobilenet V2 | 0 | 98.15 | 98.29 | 98.22 | 97.57 | 97.25 | 97.18 | 97.21 | |
1 | 96.35 | 96.06 | 96.20 | ||||||
VIT | 0 | 97.99 | 97.42 | 97.70 | 96.89 | 96.30 | 95.59 | 95.94 | |
1 | 94.61 | 93.76 | 94.18 | ||||||
