Application of soft computing techniques for shallow foundation reliability in geotechnical engineering

This research focuses on the application of three soft computing techniques including Minimax Probability Machine Regression (MPMR), Particle Swarm Optimization based Artificial Neural Network (ANN-PSO) and Adaptive Fuzzy Inference System (ANFIS-PSO) to study shallow foundation reliability settlement criteria. Soil is a heterogeneous medium involvement its attributes for geotechnical behaviour in soil-foundation system makes prediction complex engineering problem. explores feasibility against deterministic approach. The depends parameters γ (unit weight), e0 (void ratio) CC (compression index). These soil are taken as input variables while output. To assess performance models, different indices i.e. RMSE, VAF, R2, Bias Factor, MAPE, LMI, U95, RSR, NS, RPD, etc. were used. From analysis results, it was found that MPMR model outperformed PSO-ANFIS PSO-ANN. Therefore, can be used reliable technique non-linear problems foundations soils.