The combination of virtual reality interactive systems and educational technologies have been used in the training of procedural tasks, but there is a lack of research with regard to providing specific assistance for acquiring motor skills. In this paper we present a novel approach to evaluating motor skills with an interactive intelligent learning system based on the ULISES framework. We describe the implementation of the different layers that ULISES is composed of in order to generate a diagnosis of trainees' motor skills. This diagnostic process takes into account the following characteristics of movement: coordination, poses, movement trajectories and the procedure followed in a sequence of movements. In order to validate our work we generated a model for the diagnosis of tennis-related motor skills and we conducted an experiment in which we interpreted and diagnosed tennis serves of several subjects and which shows promising results.

PEO constitutes a promising surface technology for the development of protective and functional ceramic coatings on lightweight alloys. Despite its interesting advantages, including enhanced wear and corrosion resistances and eco-friendliness, the industrial implementation of PEO technology is limited by its relatively high energy consumption. This study explores the development and optimization of novel PEO processes by means of machine learning (ML) to improve the coating thickness. For this purpose, ML models random forest and XGBoost were employed to predict the thickness of the developed PEO coatings based on the key process variables (frequency, current density, and electrolyte composition). The predictive performance was significantly improved by including the composition of the used electrolyte in the models. Furthermore, Shapley values identified the pulse frequency and the TiO₂ concentration in the electrolyte as the most influential variables, with higher values leading to increased coating thickness. The residual analysis revealed a certain heteroscedasticity, which suggests the need for additional samples with high thickness to improve the accuracy of the model. This study reveals the potential of artificial intelligence (AI)-driven optimization in PEO processes, which could pave the way for more efficient and cost-effective industrial applications. The findings achieved further emphasize the significance of integrating interactions between variables, such as frequency and TiO₂ concentration, into the design of processing operations.

This research addresses the complexities inherent in grinding operations, aiming to identify the most effective process parameters and predict the behavior of the workpiece surface condition. This task is particularly challenging due to the difficulty of achieving smooth surfaces and complex, nonlinear interactions between input factors such as grinding conditions and cooling system type, and output factors such as surface roughness. These challenges are further intensified when considering additional elements, such as grinding wheel wear and advanced cryogenic lubricants or coolants. To address these issues, this study advances beyond traditional modeling methods, such as General Linear Regression or Random Forest models, to explore novel distributional modeling techniques, including General Additive Models for Shape and Scale and Distributional Random Forest. These advanced models are designed to elucidate the intricate connections between input factors and their corresponding outputs, mainly focusing on predicting the distribution of surface roughness profiles. The enhanced accuracy of these models (predictive error decreasing at around 7% and 24%) is instrumental in determining the most effective process parameters. These models offer deeper insights into the interdependencies in grinding operations, enabling more precise process control. Additionally, these models shed light on the potential improvements in surface profile quality achieved by implementing cryogenic techniques, opening new paths for optimization in grinding operations.