Prediction of Peak Particle Velocity Caused by Blasting through the Combinations of Boosted-CHAID and SVM Models with Various Kernels

This research examines the feasibility of hybridizing boosted Chi-Squared Automatic Interaction Detection (CHAID) with different kernels support vector machine (SVM) techniques for prediction peak particle velocity (PPV) induced by quarry blasting. To achieve this objective, a boosting-CHAID technique was applied to big experimental database comprising six input variables. The identified four parameters (distance from blast-face, stemming length, powder factor, and maximum charge per delay) as most significant affecting accuracy utilized them propose SVM models various kernels. kernel types used in study include radial basis function, polynomial, sigmoid, linear. Several criteria, including mean absolute error (MAE), correlation coefficient (R), gains, were calculated evaluate developed models’ applicability. In addition, simple ranking system performance systematically. R MAE index function training testing phases, respectively, confirm high capability predicting PPV values. successfully demonstrates that combination can identify predict level effective