Assessment of Soft Computing Techniques for the Prediction of Compressive Strength of Bacterial Concrete

Abstract

In this investigation, the potential of M5P, Random Tree (RT), Reduced Error Pruning Tree (REP Tree), Random Forest (RF), and Support Vector Regression (SVR) techniques have been evaluated and compared with the multiple linear regression-based model (MLR) to be used for prediction of the compressive strength of bacterial concrete. For this purpose, 128 experimental observations have been collected. The total data set has been divided into two segments such as training (87 observations) and testing (41 observations). The process of data set separation was arbitrary. Cement, Aggregate, Sand, Water to Cement Ratio, Curing time, Percentage of Bacteria, and type of sand were the input variables, whereas the compressive strength of bacterial concrete has been considered as the final target. Seven performance evaluation indices such as Correlation Coefficient (CC), Coefficient of determination (R2), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Bias, Nash-Sutcliffe Efficiency (NSE), and Scatter Index (SI) have been used to evaluate the performance of the developed models. Outcomes of performance evaluation indices recommend that the Polynomial kernel function based SVR model works better than other developed models with CC values as 0.9919, 0.9901, R2 values as 0.9839, 0.9803, NSE values as 0.9832, 0.9800, and lower values of RMSE are 1.5680, 1.9384, MAE is 0.7854, 1.5155, Bias are 0.2353, 0.1350 and SI are 0.0347, 0.0414 for training and testing stages, respectively. The sensitivity investigation shows that the curing time (T) is the vital input variable affecting the prediction of the compressive strength of bacterial concrete, using this data set.

Studies on Compressive Strength Microstructural Analysis of Self-Compacting Mortar with Bacteria

“…Cracks in concrete surfaces are often a new predicted mathematical formula for compressive strength of bacterial concrete was established using 69 experimental tests with various amounts of calcium nitrate tetra-hydrate, yeast extract, urea, bacterial cells and time. Almohammed et al [29] utilized M5P, Random Tree (RT), Reduced Error Pruning Tree (REPT), Random Forest (RF) and Support Vector Regression (SVR) techniques were evaluated and compared to Multiple Linear Regression (MLR) -based models for predicting the compressive strength of concrete (with bacteria). Ramagiri et al [30] disclosed that since the primary goal of creating these blends is to reduce environmental impact, a full Life Cycle Analysis (LCA) is required.…”

Using Random Forest and Random Tree model to Predict the splitting tensile strength for the concrete with basalt fiber reinforced concrete

“…One of the alternate tree models that RT developed was chosen based on a set of criteria. To determine the optimum pruning tree from a selection of alternate trees, various techniques have been utilised (Almohammed et al 2022).…”

A Review on Stabilizing Clayey Soil Using Waste Materials

“…It is a by-product of both out-of-date and modern rice mills, which can be found in metropolitan or rural areas [25]. Rice hush (RH) is formed every year, and around 100,000,000 (tons) are available each year for use in developing countries alone, as 50% of said amount are rice produced there each year [40]. Nearly twenty percent of RH is particularly high in ash, which is 92-95% silica, very porous, lightweight, and has a very large exterior surface area.…”