Predicting Rock Brittleness Using a Robust Evolutionary Programming Paradigm and Regression-Based Feature Selection Model

Brittleness plays an important role in assessing the stability of surrounding rock mass deep underground projects. To this end, present study deals with developing a robust evolutionary programming paradigm known as linear genetic (LGP) for estimating brittleness index (BI). In addition, bootstrap aggregate (Bagged) regression tree (BRT) and two efficient lazy machine learning approaches, namely local weighted (LWLR) KStar approach, were examined to validate LGP model. best our knowledge, is first attempt estimate BI through A tunneling project Pahang state, Malaysia, was investigated, requirement datasets measured construct proposed models. According results from testing phase, model yielded statistical indicators (R = 0.9529, RMSE 0.4838, IA 0.9744) modeling BI, followed by LWLR 0.9490, 0.6607, 0.9400), BRT 0.9433, 0.6875, 0.9324), 0.9310, 0.7933, 0.9095), respectively. sensitivity analysis demonstrated that dry density factor most effective prediction BI.