No abstract

Resistance value (R-value) is one of the basic subgrade stiffness characterizations that express a material’s resistance to deformation. In this paper, artificial intelligence (AI)-based models—especially M5P, support vector machine (SVM), and Gaussian process regression (GPR) algorithms—are built for R-value evaluation that meets the high precision and rapidity requirements in highway engineering. The dataset of this study comprises seven parameters: hydrated lime-activated rice husk ash, liquid limit, plastic limit, plasticity index, optimum moisture content, and maximum dry density. The available data are divided into three parts: training set (70%), test set (15%), and validation set (15%). The output (i.e., R-value) of the developed models is evaluated using the performance measures coefficient of determination (R2), mean absolute error (MAE), relative squared error (RSE), root mean square error (RMSE), relative root mean square error (RRMSE), performance indicator (ρ), and visual framework (Taylor diagram). GPR is concluded to be the best performing model (R2, MAE, RSE, RMSE, RRMSE, and ρ equal to 0.9996, 0.0258, 0.0032, 0.0012, 0.0012, and 0.0006, respectively, in the validation phase), very closely followed by SVM, and M5P. The application used for the aforementioned approaches for predicting the R-value is also compared with the recently developed artificial neural network model in the literature. The analysis of performance measures for the R-value dataset demonstrates that all the AI-based models achieved comparatively better and reliable results and thus should be encouraged in further research. Sensitivity analysis suggests that all the input parameters have a significant influence on the output, with maximum dry density being the highest.

Soil erodibility has been identified as one of the major factors that govern threshold of resistance to erosion. Accurate measurement of soil erodibility in the field is indeed important for the determination of critical shear stresses. Critical shear stress is the stress that initiates particle movement that promotes shifting of the bankline. An attempt to establish soil erodibility parameters was successfully carried out using a newly fabricated Jet Erosion Device (JEd) based on soil properties. Soil erodibility coefficients are introduced to represent the erodibility of the soils under study. Statistical test is used to confirm the validity and accuracy of the proposed technique. Field data measurements were carried out on 3 rivers. Empirical models were developed using data from Selangor River and validated using data from Bernam and Lui rivers and other secondary river data. Analyses have shown high correlations and the parameters were further examined and analysed for the development of a predictive relationship for J i . The most accurate model was selected based on the adjusted R 2 , standard error of the estimate and discrepancy ratio to illustrate its significance. Selection of the predictive variables was based on their ability to explain the variation of J i . The models established could significantly reduce the cost, time and usage of water supply for field data collection using JEd.

Erosion from riverbank is most properly represented by the erodibility factor. One of the methods that can be used for in situ soil erodibility testing is the submerged jet test called Jet Erosion Test (JET). In this study, a newly modified version of the JET device namely Jet Erosion Device (JEd) is fabricated, with improved features and design that facilitates testing in the field and the laboratory. Analysis and calibration of the JEd tests were conducted to check on the reliability and performance of the Jet Erosion Device (JEd). Some preliminary results were shown to give some insights on the capabilities of the JEd. An evaluation of the erosion performance index i.e. jet index was performed to characterize the erosion resistance. The estimation of erodibility coefficients were made using the results of jet index obtained.

No abstract