Figure 1:
Architecture diagram for the proposed design of BQN-based decisive supporting system and Hopfield Symmetric CNN-GPOR. BQN, Bayesian Q-Network.
Figure 2:
Process flow for decisive logistic associative rule-based BQN. BQN, Bayesian Q-Network.
Figure 3:
Process flow for Hopfield Symmetric CNN-GPOR.
Figure 4:
Hopfield Symmetric CNN architecture.
Figure 5:
Flowchart for the proposed design BQN-based decisive logistic transformation and Hopfield symmetric CNN-GPOR. BQN, Bayesian Q-Network.
Figure 6:
Performance of MAE in the proposed system. MAE, mean absolute error.
Figure 7:
Performance of RMSE in the proposed system. RMSE, root mean square error.
Figure 8:
Performance of accuracy in the proposed system.
Figure 9:
Performance of loss in the proposed system.
Figure 10:
Performance of detection time in the proposed system.
Figure 11:
Performance of detection rate in the proposed system.
Figure 12:
Performance R2 in the proposed model.
Figure 13:
Performance of precision in the proposed model.
Figure 14:
Performance of recall in the proposed model.
Figure 15:
Comparison of MAE. MAE, mean absolute error.
Figure 16:
Comparison of RMSE. RMSE, root mean square error.
Figure 17:
Comparison of accuracy.
Figure 18:
Comparison of loss.
Figure 19:
Comparison of detection time.
Figure 20:
Comparison of detection rate.