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.

The civil construction industry has a significant challenge in contributing to environmental protection by developing cement and natural aggregates alternatives. Because of global warming caused by the use of cement in concrete, it is essential to provide sustainable alternatives for producing waste-containing concrete. For the building’s time, cost and dependability, this chapter is being conducted. As a result of the use of artificial neural networks (ANN), the concrete component proportions of several grades of concrete have been corrected to include a different aggregate replacement with recycled one. The k-fold cross-validation method was also used in order to assess the model’s overall performance. According to the results, when one hidden layer and seven neurons were employed, the model produced an R-value of 0.95431, while the ANN model produced an R-value of 0.91 when one hidden layer and up to 50 neurons were used.

This study examines the compressive strength of two concrete mixes (M25 and M20) enhanced with basalt fiber and polypropylene fiber. The experiment investigates the impact of each fiber independently as well as their combined effect. Various combinations of the fibers were employed, including 100% basalt fiber (BF), 100% polypropylene fiber (PF), 50% BF 50% PF, 75% BF 25% PF, and 25% BF 75% PF. For M25, the results indicate a decrease in compressive strength with the application of all fibers both independently and in combination, except for the (75% BF 25% PF) combination, which resulted in a slight increase in compressive strength. Basalt fiber was found to be more effective than polypropylene when applied independently, whereas the hybrid effect yielded better results than individual fiber. For M20, fibers had a more positive impact on the compressive strength, and the hybrid effect yielded better results than individual fibers. The combination of 25% BF and 75% PF was found to be the most effective in improving compressive strength.