Applying artificial rabbit optimisation-LSSVR analysis for HPC's compressive strength estimation

High-performance concrete (HPC) functions stronger because it contains more components than ordinary concrete. The compressive strength (CS) of HPC prepared with fly ash (FA) and blast furnace slag (BFS) was assessed using several artificially-based analytics. In this study, the artificial rabbit optimisation (ARO) technique, abbreviated as AROR and AROLS for the radial basis function (RBF) neural network and the least square support vector regression (LSSVR) analysis, accordingly, was employed to identify the optimal values for the parameters that could be adjusted to enhance performance. The CS was used as the predicting objective, and 1,030 experiments and eight input parameters were used to construct the suggested techniques. After that, the outcomes of the enhanced model were compared to those documented in the corpus of current scientific literature. The calculations suggest that combining AROLS with AROR research might be advantageous. The AROLS demonstrated much higher R2 (R2Train = 0.9853 and R2Test = 0.9912) and lower error metrics when compared to the AROR and previous papers. Finally, the offered technique for computing the CS of HPC increased by BFS and FA may be created using the recommended LSSVR analysis enhanced by ARO.