Table 4 Evaluating CNN using 80–20 and 70–30 splitting methods without feature selection
From: Classification of lung cancer severity using gene expression data based on deep learning
Dataset | Training – testing method | Convolutional layers | Max-pooling layer | Max-pooling layer size | Dense layer | Learning rate | Batch size | Accuracy |
|---|---|---|---|---|---|---|---|---|
LUAD | 70–30 splitting | 1 | NA | NA | 1 | 0.01 | 128 | 61.49% |
80–20 splitting | 60.61% | |||||||
LUSC | 70–30 splitting | 1 | NA | NA | 1 | 0.01 | 128 | 55% |
80–20 splitting | 57% |