Random Forest versus Support Vector Machine Models’ Applicability for Predicting Beam Shear Strength

Abstract

The shear and bending are the actions that are experienced in the beam owing to the fact that the beam is a flexural member due to the load in the transverse direction to their longitudinal axis. The shear strength (Vs) computation of reinforced concrete (RC) beams has been a major topic in the field of structural engineering. There have been several methodologies introduced for the Vs prediction; however, the modeling accuracy is relatively low owing to the complex characteristic of the resistance mechanism involving dowel effect of longitudinal reinforcement, concrete in the compression zone, contribution of the stirrups if existed, and the aggregate interlock. Hence, the current research proposed a new soft computing model called random forest (RF) to predict Vs. Experimental datasets were collected from the open-source literature including the related geometric properties and concrete characteristics of beam specimens. Nine input combinations were constructed based on the statistical correlation to be supplied for the proposed predictive model. The prediction accuracy of the RF model was validated against the Support Vector Machine (SVM), and several other empirical formulations have been adopted in the literature. The proposed RF model revealed better prediction accuracy in addition the model structure emphasis in the incorporation of seven predictors by excluding (beam flange thickness and coefficient). In the quantitative term, the minimal root mean square error value was attained (RMSE = 89.68 kN).

Quantifying soil organic matter for sustainable agricultural land management with soil color and machine learning technique

“…This suggests that the relationship between soil color and SOM can be more easily explained with the RF algorithm, which has the capacity to capture nonlinear relationship. A previous study yielded similar outcomes to our research, including the superior performance of the RF algorithm compared to the SVM algorithm and the observation that R 2 values decreased when applied to the test dataset as opposed to the training dataset (Mohammed & Ismail, 2021). Furthermore, several studies by Mahmoudzadeh et al.…”

“…This suggests that the relationship between soil color and SOM can be more easily explained with the RF algorithm, which has the capacity to capture nonlinear relationship. A previous study yielded similar outcomes to our research, including the superior performance of the RF algorithm compared to the SVM algorithm and the observation that R 2 values decreased when applied to the test dataset as opposed to the training dataset (Mohammed & Ismail, 2021). Furthermore, several studies by Mahmoudzadeh et al (2020), Tziachris et al (2019), andZhang et al (2021) have demonstrated that when predicting the SOM content, the RF algorithm consistently outperforms other algorithms such as SVM, cubist, ordinary kriging, regression kriging, gradient boosting, decision tree, and bagging decision tree.…”

A knowledge transfer enhanced ensemble approach to predict the shear capacity of reinforced concrete deep beams without stirrups

“…In total, 118 experimental observations were used, and the trained model could successfully simulate the effects of input variables on the shear capacity of RC beams without stirrups. Moving away from ANNs, Mohammed and Ismail (2021) predicted the shear capacity of RC beams using a random forest (RF). The data they used comprised 349 experimental samples, and they validated the prediction by comparing it to the results of a support vector machine (SVM) and other empirical equations.…”

Metaheuristic Optimization of Random Forest for Predicting Punch Shear Strength of FRP-Reinforced Concrete Beams

“…Owing to its exceptional performance, RF was extensively employed in predicting the mechanical properties of reinforced concrete (RC) in construction engineering [37][38][39][40][41]. Mohammed et al [42] compared the performance of support vector machines (SVM) and RF models for predicting the shear strength of RC beams and found that the RF model has a better prediction accuracy than the SVM model. Zhang et al [32] compared the prediction performance of the BPNN and RF models for estimating the shear strength of RC beams with and without stirrups.…”