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

<table>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.</table>

Advances in Fuzzy Systems

fig5

Figure 5

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