Assessing Waste Marble Powder Impact on Concrete Flexural Strength Using Gaussian Process, SVM, and ANFIS

The study’s goal is to assess the flexural strength of concrete that includes waste marble powder using machine learning methods, i.e., ANFIS, Support vector machines, and Gaussian processes approaches. Flexural has also been studied by most reliable approach sensitivity analysis in order determine influential independent variable predict dependent variable. entire dataset consists 202 observations, which 120 were experimental 82 readings from previous research projects. was then arbitrarily split into two subsets, referred as training testing dataset, each contained a weighted percentage total observations (70–30). Output mix strength, whereas inputs comprised cement, fine coarse aggregates, water, powder, curing days. Using statistical criteria, an evaluation efficacy approaches carried out. In comparison other algorithms, results demonstrate process technique lower error bandwidth, contributes its superior performance. capable producing more accurate predictions experiment due fact it higher coefficient correlation (0.7476), mean absolute value (1.0884), smaller root square (1.5621). number days identified significant predictor, addition factors, analysis.