首页|Findings from School of Technology in the Area of Machine Learning Reported (Eff icient Predictive Modeling of Resilient Modulus In Stabilized Clayey Soil Using Automated Machine Learning)
Findings from School of Technology in the Area of Machine Learning Reported (Eff icient Predictive Modeling of Resilient Modulus In Stabilized Clayey Soil Using Automated Machine Learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Research findings on Machine Learning are discussed in a new report. According to news reporting out of Gujarat, India , by NewsRx editors, research stated, "Pavement subgrade design relies on the re silient modulus (Mr) r ) to analyze structural response to vehicle-like loading. Adding stabilizers to the soil subgrade makes estimating Mr r difficult and res ource-intensive." Our news journalists obtained a quote from the research from the School of Techn ology, "This study uses an automated machine learning (ML) strategy to predict t he Mr r of stabilized clayey soil using recycled plastic waste. The proposed met hod automates model selection and hyperparameter tuning, making it a feasible al ternative to tedious ML modeling and costly laboratory testing. From extensive l aboratory investigation involving 3285 experimental data points, the automated M L model using Bayesian optimization evaluates ensembles, support vector machine (SVM), neural network (NET), decision trees, (TREE), and Gaussian process (GP) r egression models, identifying the best model based on cross-validation mean squa red error (MSE). Bayesian optimization explores hyperparameter spaces to find op timal configurations, enhancing the accuracy, scalability, and reliability of th e prediction model. The optimization process yielded the best results for the en semble least square boost (LSBoost) model with a cross-validation mean squared e rror (MSE) value of 6.723x10–29. The optimized ML model's performance is measur ed using R2 2 and adjusted R2. 2. The LSboost model's R2 2 and adjusted R2 2 val ues of 0.9999 suggested overfitting, prompting further investigations using perf ormance metrics like root mean squared error (RMSE), mean absolute error (MSE), and probability density function (PDF) for normalized absolute error (NAE) for t raining and testing datasets for the predictive ML model. The small RMSE and MAE (0.0049 and 0.0005) values and symmetrical NAE distribution of the proposed ML model demonstrate its high accuracy and generalization capabilities. The propose d model was subsequently tested on the new, unseen data and achieved predictions with an error rate of 0.24%."
GujaratIndiaAsiaCyborgsEmerging TechnologiesMachine LearningSchool of Technology
NETL
NSTL
