Optimization the Initial Weights of Artificial Neural Networks via Genetic Algorithm Applied to Hip Bone Fracture Prediction : Figure 5

Figure 5: The ROC curves of the original BPNN and the GA-based BPNN for different ranges, (a1) and (a2) −0.5 to 0.5 range for the training and testing data, (b1) and (b2) −1 to 1 range for the training and testing data, (c1) and (c2) −5 to 5 range for the training and testing data.