Swelling Prediction in Compacted Soils Using Adaptive Neuro-Fuzzy Inference System

Swelling in compacted soils may lead to some damages structures and buildings. For the sake of reducing such damages, soil swelling should be determined, so as make exhibit adequate resistance against a phenomenon. most cases, fully non-linear relations have been observed between parameters contributing soil. As such, determined via either experimentations or prediction models. However, being extremely timely, tests require special expensive equipment. Accordingly, there is need for models which can use available data theoretically give estimations relatively high accuracy without getting busy with associated issues. Investigated evaluated this research are ability application an adaptive neuro-fuzzy interference system (ANFIS) developed by subtractive clustering fuzzy c-mean determine predict soils. The results along obtained values root mean squared error (RMSE), absolute (MAE) coefficient correlation (R) indicated that proposed ANFIS model succeeded at good level accuracy. Therefore, used KEYWORDS: soil, Subtractive clustering, Fuzzy ANFIS, Prediction.