Bituminous Mixtures Experimental Data Modeling Using a Hyperparameters-Optimized Machine Learning Approach

Abstract

This study introduces a machine learning approach based on Artificial Neural Networks (ANNs) for the prediction of Marshall test results, stiffness modulus and air voids data of different bituminous mixtures for road pavements. A novel approach for an objective and semi-automatic identification of the optimal ANN’s structure, defined by the so-called hyperparameters, has been introduced and discussed. Mechanical and volumetric data were obtained by conducting laboratory tests on 320 Marshall specimens, and the results were used to train the neural network. The k-fold Cross Validation method has been used for partitioning the available data set, to obtain an unbiased evaluation of the model predictive error. The ANN’s hyperparameters have been optimized using the Bayesian optimization, that overcame efficiently the more costly trial-and-error procedure and automated the hyperparameters tuning. The proposed ANN model is characterized by a Pearson coefficient value of 0.868.

Artificial Neural Network Hyperparameters Optimization: A Survey

“…13. Matteo Miani, et al [76] Used a Bayesian optimization algorithm for optimizing hyperparameters for prediction of Marshall test results, stiffness modulus, and air voids data regarding various bituminous mixtures for road pavements, with the use of an ML approach based on (ANNs). 14.…”

“…In [37], [72], [76], [77], [79], [82] overfitting problem is showed, in [37], [82] dropout rate is most important hyperparameter to prevent this issue, which the dropout and number of epochs enable model to reduce overfitting, while in [76], [79] L2 regularization is used to reduce the chance of model overfitting in this case the learning rate hyperparameter is affected . Lastly in [77] [72] they overcome the overfitting without relying on the hyperparameter in [77] use early stopping technique and in another one fit the neuron number manually.…”

Stiffness Data of High-Modulus Asphalt Concretes for Road Pavements: Predictive Modeling by Machine-Learning

“…However, there are many optimization algorithms available nowadays that can reduce the time spent in searching for the best model hyperparameters. Among them, the Bayesian optimization (BO) algorithm [44] has found considerable success mainly due to the work of Snoek et al [45]. The goal of the optimization process is to minimize a given objective function f (z) for z = z p , p ∈ {0, .…”

Road Pavement Asphalt Concretes for Thin Wearing Layers: A Machine Learning Approach towards Stiffness Modulus and Volumetric Properties Prediction

“…The standard practice of splitting the available data set into two random subsets of training and testing may result in biased performance evaluations due to the different distribution of data within such splits, along with the risk of missing some relevant trends in training data [40]. These effects are particularly marked when the data set is relatively small.…”