Predicting the strength of waste aggregate concrete blocks using novel hybrid machine learning models and graphical user interface deployment.

14 e) shows a positive trend, with SHAP values rising from about − 2 at low binder levels to + 1.5 at higher binder contents, although the mean is slightly negative (–0.312) due to the prevalence of low-binder samples.

also in 6,846 other papers

14 f) shows a negative trend line falling from about + 0.2 at RA = 0 kg/m 3 to − 1.1 at RA = 400 kg/m 3 , yet its mean SHAP remains near zero (− 0.036, SD = 0.636) with 299 positives vs. 245 negative points, indicating a comparatively weak overall influence.

also in 2,510 other papers