In the current research, a newly developed ensemble intelligent predictive model called Bagging Regression (BGR) is proposed to predict the compressive strength of a hollow concrete masonry prism ($f_p$). A matrix of input combinations is constructed based on several predictive variables, including mortar compressive strength (f_m), concrete block compressive strength (f_b), and height to thickness ratio (h/t). Three modeling scenarios based on the different data divisions (i.e., 80–20%, 75–25%, and 70–30%) for training-testing phases are evaluated. The proposed model is validated against classical support vector regression (SVR) and decision tree regression (DTR) models using statistical indicators and graphical presentations. Results indicate the superiority of the BGR over the other models. In quantitative terms, BGR attains minimum root mean square error (RMSE = 1.51 MPa) using the data division scenario of 80–20% in the testing phase, while DTR and standalone SVR models offer RMSE = 2.55 and 2.33 MPa, respectively.

在目前的研究中，提出了一种新开发的集成智能预测模型，称为袋装回归（BGR），用于预测空心混凝土砌体棱柱的抗压强度。$F_p$）。基于多个预测变量构建输入组合矩阵，包括砂浆抗压强度 ( f _m )、混凝土砌块抗压强度 ( f _b ) 和高厚比 ( h/t）。评估了基于不同数据划分（即 80-20%、75-25% 和 70-30%）的三种建模场景，用于训练-测试阶段。所提出的模型使用统计指标和图形表示针对经典支持向量回归 (SVR) 和决策树回归 (DTR) 模型进行了验证。结果表明 BGR 优于其他模型。在定量方面，BGR 在测试阶段使用 80-20% 的数据划分场景获得最小均方根误差 (RMSE = 1.51 MPa)，而 DTR 和独立 SVR 模型分别提供 RMSE = 2.55 和 2.33 MPa。