New prediction models for the compressive strength and dry-thermal conductivity of bio-composites using novel machine learning algorithms

Bio-composites have become the prime material selection for green concrete because of the increasing awareness of environmental issues. Due to their highly heterogenous nature, most of the existing studies have focused on the experimental investigation of thermal conductivity (TC) and compressive strength (CS) of hemp-based bio-composites (HBC). However, the tests to estimate the TC and CS may take long time and be costly. In this study, three different machine learning (ML) techniques known as artificial neural network (ANN), adaptive neuro-fuzzy interface system (ANFIS), and multi-gene expression programming (MEP) are used to predict and formulate a mathematical expression for determining the CS and TC of HBC. A total of 159 and 86 experimental records for CS and TC, respectively, were achieved from the past published literature and the ten most influential input variables were considered. The performance of the proposed models was tested using root squared error (RSE), mean absolute error (MAE), Nash-Sutcliffe efficiency (NSE), root mean square logarithmic error (RMSLE), root mean square error (RMSE), correlation coefficient (R), coefficient of determination (R²), performance index (PI), the objective function (OF), and other statistical measures recommended in the literature. Sensitivity and parametric studies were also conducted to assess the coherence of the developed MEP equations with the actual physical phenomenon. Based on R, R² and NSE, the increasing order is ANFIS > MEP > ANN for both CS and TC. The overall R-value for CS models are 0.9929 (ANFIS), 0.9848 (MEP) and 0.9691 (ANN) while 0.9997 (ANFIS) 0.9759 (MEP) and 0.9601 (ANN) for TC. The integrated measurements of statistical performance (PI and OF) of all models approach 0, stating the outburst performance and generalization capability of the developed models. MEP also provides a simple empirical mathematical equation for the prediction of CS and TC. The increasing trend of the importance of inputs variables for CS and TC was calculated. The parametric trend of each input for CS and TC is in strong agreement and consistent with the experimental results in the database. Thus, the projected equations for estimating the CS and TC of HBC are accurate and feasible and can be used by the designer and practitioners to save the total time required of hectic laboratory tests. However, it is suggested to validate the results of this research with the latest experimental data and other ML algorithms must be studied.