Correction to: Feasibility of computational intelligent techniques for the estimation of spring constant at joint of structural glass plates: a dome-shaped glass panel structure

While serving as a core modelling strategy for explaining physical processes, classical and physics-based modelling is nevertheless associated with weaknesses such as computational burden, time consumption, and the inability to represent chaotic and complicated processes in glass science and engineering. On the other hand, machine learning (ML) models have been known to overcome the preceding limitation, particularly when accurate and reliable estimation is required from experiments, including axial load. The data (2879 instances) obtained from the experiment, including axial load (N) and four different displacements (mm), were pre-processed, and partitioned into 70% calibration and 30% verification. Subsequently, sensitivity analysis was conducted in which model combinations (M1–4) were generated. The model complies with the latest machine learning industry standards and allows low-cost experimental performances on low-powered edge computing devices. Regarding RMSE, GRNN-M2 and NN-M3 emerged as the best models; however, the confidence interval values indicated that they were superior to the best model (95%). The outcomes based on three performance evaluation criteria (NSE, RMSE, and R) depicted that the ML model performed meritoriously and proved reliable for the estimation of K. In comparison, the NN-M4 model outperformed that of SVM-M1, GRNN-M4, and MLR-M4 by 6, 4, and 5%, respectively, with average increments of 5% by all the models.