This paper analyses mechanical property prediction through Machine Learning for continuous fiber-reinforced polymer matrix composites printed using the novel Material Extrusion Additive Manufacturing technique. The composite is formed by a nylon-based matrix and continuous fiber (carbon, Kevlar, or fiberglass). From the literature, the elastic modulus and tensile strength were taken along with printing parameters like fiber content, fiber fill type, matrix lattice, matrix fill density, matrix deposition angle, and fiber deposition angle. Such data were fed to several supervised learning algorithms: Ridge Regression, Bayesian Ridge Regression, Lasso Regression, K-Nearest Neighbor Regression, CatBoost Regression, Decision Tree Regression, Random Forest Regression, and Support Vector Regression. The Machine Learning analysis confirmed that fiber content is the most influential parameter in elasticity (E) and strength ($\sigma$). The results show that the K-Nearest Neighbors and CatBoost provided the closest predictions for E and $\sigma$ compared to the other models, and the tree-based model presented the narrowest error distribution. The computational metrics point to a size versus prediction time tradeoff between these two best predictors, and adopting the prediction time as the most relevant criterion leads to the conclusion that the CatBoost model can be considered, when compared to the others tested, the most appropriate solution to work as a predictor in the task at hand.

Shear Horizontal (SH) guided waves have been extensively used to estimate and detect defects in structures like plates and pipes. Depending on the frequency and plate thickness, more than one guided-wave mode propagates, which renders signal interpretation complicated due to mode mixing and complex behavior of each individual mode interacting with defects. This paper investigates the use of machine learning models to analyse the two lowest order SH guided modes, for quantitative size estimation and detection of corrosion-like defects in aluminium plates. The main contribution of the present work is to show that mode separation through machine learning improves the effectiveness of predictive models. Numerical simulations have been performed to generate time series for creating the estimators, while experimental data have been used to validate them. We show that a full mode separation scheme decreased the error rate of the final model by 30% and 67% in defect size estimation and detection respectively.

The purpose of the present study was to identify the performance determinant factors predicting 15-m backstroke-to-breaststroke turning performance using and comparing linear and tree-based machine-learning models. The temporal, kinematic, kinetic and hydrodynamic variables were collected from 18 age-group swimmers (12.08 ± 0.17 yrs) using 23 Qualisys cameras, two tri-axial underwater force plates and inverse dynamics approach. The best models were obtained: (i) with Lasso linear model of the leave-one-out cross-validation in open turn (MSE = 0.011; R² = 0.825) and in the somersault turn (MSE = 0.016; R² = 0.734); (ii) the Ridge of the leave-one-out cross-validation (MSE = 0.016; R² = 0.763) for the bucket turn; and (iii) the AdaBoost tree-based model of the leave-one-out cross-validation for the crossover turn (MSE = 0.016; R² = 0.644). Model’s selected features revealed that optimum turning performance was very similarly determined for the different techniques, with balanced contributions between turn-in and turn-out variables. As a result, the relevant feature’s contribution of each backstroke-to-breaststroke turning technique are specific; developing approaching speed in conjunction with proper gliding posture and pull-out strategy will result in improved turning performance, and may influence differently the development of specific training intervention programmes.