Study the Effect of Hyperparameters on Performance of BEIA to Detect Corrosion in Reinforced Concrete

The purpose of this study was to determine the effect of hyperparameters on the performance of BEIA in detecting corrosion in reinforced concrete. BEIA was run with fifteen data of potential measurement values on concrete surfaces. Variations in geometry size, cognitive values (a1), and social parameters (a2) were performed in this study. Simulation result show the hyperparameters can affect the performance of BEIA in finding the location of corrosion in reinforced concrete. Due to the effect of hyperparameter values on BEIA performance in detecting corrosion on rebar, the recommended cognitive parameter value is < 0.4; meanwhile the recommended social parameter value is 0.6 < a2 ≤ 0.9.