Grinding burn is a critical defect that compromises the integrity of high-precision components. While analytical models rely on rigorous physical formulations, they often lack the flexibility to adapt to real variability. In contrast, standard machine learning (ML) also fails by ignoring grinding process understanding. To bridge this gap, this study transfers expert knowledge to the model by extracting signal features from the distinct phases of the grinding cycle. Signals from Computer Numerical Control (CNC), accelerometers, and acoustic emissions were segmented into approach, roughing, and spark-out stages to enable independent phase learning. Additionally, a feature selection strategy was proposed, successfully reducing the 1425 initial features to a set of just 32. Machine learning models reached 96.34% accuracy in known scenarios, far exceeding the 76.72% analytical baseline. When tested on grinding conditions different from those used during training, the staged methodology achieved 80%–85% accuracy. This performance not only outperforms the analytical results, but also notably surpasses standard ML global models, which failed with accuracies below 60%. Embedding the physical structure of the process into machine learning provides the contextual awareness necessary for reliable industrial monitoring, enabling superior generalisation and robustness compared to both traditional analytical models and standard data-driven techniques.

In the era where digital technologies are becoming increasingly prevalent, it is anticipated that a majority of the global population will have at least a basic understanding of informatics. However, empirical evidence suggests that a significant portion of the global population remains digitally illiterate. This phenomenon is particularly pronounced in the case of the senior adult population. In light of the aforementioned challenges, this work integrates Computer Science Unplugged exercises, based on games and recreational activities without the use of computers, and L2T2L, a learning-by-teaching methodology whereby university students learn and then, in turn, teach that learning to other populations in a cascading manner. A case study was conducted in Lima, Peru, with the participation of 140 volunteers from centres for the elderly. Thirty-five students and one teacher from the Universidad Científica del Sur were responsible for initiating the transfer of knowledge from the university to the senior citizens, with the assistance of twelve individuals responsible for their care. The results demonstrate that the participants attained a commendable level of comprehension when attempting to complete all of the assigned tasks. Furthermore, the efficacy of L2T2L is evident in its adaptability and suitability for scenarios beyond those for which it was originally designed.

Parkinson’s disease (PD) is a neurodegenerative disorder marked by motor and cognitive impairments. The early prediction of cognitive deterioration in PD is crucial. This work aims to predict the change in the Montreal Cognitive Assessment (MoCA) at years 4 and 5 from baseline in the Parkinson’s Progression Markers Initiative database. The predictors included demographic and clinical variables: motor and non-motor symptoms from the baseline visit and change scores from baseline to the first-year follow-up. Various regression models were compared, and SHAP (SHapley Additive exPlanations) values were used to assess domain importance, while model coefficients evaluated variable importance. The LASSOLARS algorithm outperforms other models, achieving lowest the MAE, 1.55±0.23 and 1.56±0.19, for the fourth- and fifth-year predictions, respectively. Moreover, when trained to predict the average MoCA score change across both time points, its performance improved, reducing its MAE by 19%. Baseline MoCA scores and MoCA deterioration over the first-year were the most influential predictors of PD (highest model coefficients). However, the cumulative effect of other cognitive variables also contributed significantly. This study demonstrates that mid-term cognitive deterioration in PD can be accurately predicted from patients’ baseline cognitive performance and short-term cognitive deterioration, along with a few easily measurable clinical measurements.

The aim of this research is to study how games and game development can help students learn introductory concepts of a very abstract topic such as Computer Architecture. In a quasi-experimental scenario, quantitative and qualitative data has been collected from students before and after the intervention throughout three consecutive school years. Following the action-research methodology, year by year several changes have been implemented in the games, pursuing a better understanding of the concepts. Also during the last year a game development has been added in order to consolidate knowledge. No statistical differences were found between the knowledge acquired by students in the control and experimental groups during the first two years. Therefore, and given that motivation was higher when using games, the same game-based methodology was used in the third year in both groups. Afterwards, the students had to develop an interactive presentation in the form of an Escape Room to teach younger students the concepts they had learned. Only a few concepts gained knowledge after this intervention, but those concepts with less prior understanding did. Although advanced computer architecture concepts can be difficult to handle through games, there are basic concepts that can be worked on in this way. In addition, the excitement and motivation provided by games make a good introduction to the subject. Also the development of simple games helps to understand some of the concepts that were not well understood before.

This study explores prodromal Parkinson’s Disease (PD) by leveraging data from the Parkinson’s Progression Markers Initiative (PPMI). The main goal was to discriminate between prodromals that phenoconverted to PD in 7 years to those that did not. Through feature selection, the system identified key first visit predictors of PD phenoconversion, encompassing demographic, clinical, and structural magnetic resonance imaging (MRI) data. Employing seven machine learning algorithms in standard and balanced forms, we find Support Vector Machine (balanced) as most effective for demographic and clinical data, and Logistic Regression (balanced) when adding thicknesses and volumes of MRI data. The metrics were improve in the second case (AUC ROC of 0.84). Significant predictors include olfactory dysfunction, motor symptoms, psychomotor speed, and third ventricle dilation.

The partial consolidated tree bagging (PCTBagging) was presented as a multiple classifier that, based on a parameter, the consolidation percentage, can exploit more the possibilities of the inner ensembles, and obtain higher levels of interpretability, or can exploit more the possibilities of the ensembles, and obtain higher discriminant capacity. Thus, at the extreme values, with a consolidation percentage of 100 × Size, and, Level by level. The results show that the use of different criteria affects the discriminant capacity of the classifier for the same level of interpretability, and that this effect is greater the higher the percentage of consolidation is.

Computer applications provide people with disabilities with unique opportunities for interpersonal communication, social interaction and active participation. However, rigid user interfaces often present accessibility barriers to people with physical, sensory or cognitive impairments. User interface personalization is crucial to overcome these barriers, enabling computer access to a considerable section of the population with disabilities. Adapting the user interface to people with disabilities requires taking into consideration their physical, sensory or cognitive abilities and restrictions and hence providing alternative access procedures according to their capacities. In the chapter 15, "Personalizing the User Interface for People with Disabilities" [1], we present methods and techniques that are being applied to research and practice on user interface personalization for people with disabilities. In addition, we discuss possible approaches for diverse application fields where personalization is required: accessibility to the web using transcoding, web mining for eGovernment, and human-robot interaction for people with severe motor restrictions.

Non-motor manifestations of Parkinson’s disease (PD) appear early and have a significant impact on the quality of life of patients, but few studies have evaluated their predictive potential with machine learning algorithms. We evaluated 9 algorithms for discriminating PD patients from controls using a wide collection of non-motor clinical PD features from two databases: Biocruces (96 subjects) and PPMI (687 subjects). In addition, we evaluated whether the combination of both databases could improve the individual results. For each database 2 versions with different granularity were created and a feature selection process was performed. We observed that most of the algorithms were able to detect PD patients with high accuracy (>80%). Support Vector Machine and Multi-Layer Perceptron obtained the best performance, with an accuracy of 86.3% and 84.7%, respectively. Likewise, feature selection led to a significant reduction in the number of variables and to better performance. Besides, the enrichment of Biocruces database with data from PPMI moderately benefited the performance of the classification algorithms, especially the recall and to a lesser extent the accuracy, while the precision worsened slightly. The use of interpretable rules obtained by the RIPPER algorithm showed that simply using two variables (autonomic manifestations and olfactory dysfunction), it was possible to achieve an accuracy of 84.4%. Our study demonstrates that the analysis of non-motor parameters of PD through machine learning techniques can detect PD patients with high accuracy and recall, and allows us to select the most discriminative non-motor variables to create potential tools for PD screening.

Contribution: Adaptation and application of a methodology to introduce Informatics from an early age to students living in disadvantaged areas in Peru and analysis of its effects. Background: On the on hand, during the COVID-19 pandemic, students living in disadvantaged areas in Peru were confined to their home under the supervision of their family and without access to computers. On the other hand, the multistage sequencing knowledge transmission methodology (L2T2L), first proposed in JolasMATIKA (Basque Country), to introduce Informatics topics using CS Unplugged from university to school had shown to be effective. Research Question: Does the introduction from an early age into Informatics affect the appreciation of students living in disadvantaged areas about what Informatics is and their attitude toward it? Is the methodology used appropriate for times of pandemic? Methodology: A pilot project based on the L2T2L methodology was introduced at the Public School of the Religious Association Br. Thomas Helm S.M. (Peru) for primary and secondary education during the 2020/2021 pandemic academic year. University engineering students from the UTEC University were in charge of initiating the transmission of Informatics concepts to teachers of secondary and primary education who transmitted the knowledge to their respective students, using mobile phones. Surveys were used to gather data at the beginning and the end of the experience. Findings: A methodology adequate for introducing Informatics from an early age and for reducing the digital divide between technologically advanced communities and more disadvantaged communities. Students and family unit members changed their opinion about Informatics.

Within the field of social reintegration and re-education, this paper presents an educational experience carried out at the Iquitos Penitentiary Center, Lima, Peru, with the aim of providing an introduction to informatics to 25 inmates who volunteered to take part in the project. Twenty students and a teacher from the Scientific University of the South also in Peru, were responsible for initiating the transmission of knowledge from the university to inmates, with the collaboration and participation of the penitentiary coordinator. The main objectives of the case study were to validate both the suitability of the CS unplugged proposal and the adaptability of the L2T2L pedagogic strategy to the transmission of knowledge to adults, specifically penitentiary inmates. This strategy had been originally designed to transmit informatics knowledge from university to primary school. The validity and effectiveness of the experience was assessed using surveys. Results confirm that inmates achieved a good level of understanding when endeavoring to resolve most of the CS unplugged assignments designed for them. It was also seen that L2T2L is adaptable and valid for different scenarios other than those for which it was initially designed. Indeed, it was proven to be valid for transmitting knowledge to the prison population. Finally, it should be pointed out that the experience is easily replicable and that it brings an opportunity to introduce informatics into education programs in prisons, something which can contribute enormously to social reintegration and re-education, facilitating the subsequent reentry of inmates into the community once their period of imprisonment has ended.

The use of decision trees considerably improves the discriminating capacity of ensemble classifiers. However, this process results in the classifiers no longer being interpretable, although comprehensibility is a desired trait of decision trees. Consolidation (consolidated tree construction algorithm, CTC) was introduced to improve the discriminating capacity of decision trees, whereby a set of samples is used to build the consolidated tree without sacrificing transparency. In this work, PCTBagging is presented as a hybrid approach between bagging and a consolidated tree such that part of the comprehensibility of the consolidated tree is maintained while also improving the discriminating capacity. The consolidated tree is first developed up to a certain point and then typical bagging is performed for each sample. The part of the consolidated tree to be initially developed is configured by setting a consolidation percentage. In this work, 11 different consolidation percentages are considered for PCTBagging to effectively analyse the trade-off between comprehensibility and discriminating capacity. The results of PCTBagging are compared to those of bagging, CTC and C4.5, which serves as the base for all other algorithms. PCTBagging, with a low consolidation percentage, achieves a discriminating capacity similar to that of bagging while maintaining part of the interpretable structure of the consolidated tree. PCTBagging with a consolidation percentage of 100% offers the same comprehensibility as CTC, but achieves a significantly greater discriminating capacity. (c) 2021 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Nowadays the importance of digital competences is unarguable, and specially for people with functional diversity. On the other hand, the website should adapt to the user necessities automatically. This work focuses on the latter, in detecting navigation problems automatically. Firstly, the device used by the user will be detected by proposing two level hierarchy of supervised classifiers that divides in different levels errors of different criticality. Afterwards, in order to detect problems automatically, clustering algorithms and anomaly detection have been used, finding for each device a set of potential problems' indicators automatically. Moreover, the effect of cursor's adaptions in different problems has been analyzed.

Deep learning techniques are being increasingly used in the scientific community as a consequence of the high computational capacity of current systems and the increase in the amount of data available as a result of the digitalisation of society in general and the industrial world in particular. In addition, the immersion of the field of edge computing, which focuses on integrating artificial intelligence as close as possible to the client, makes it possible to implement systems that act in real time without the need to transfer all of the data to centralised servers. The combination of these two concepts can lead to systems with the capacity to make correct decisions and act based on them immediately and in situ. Despite this, the low capacity of embedded systems greatly hinders this integration, so the possibility of being able to integrate them into a wide range of micro-controllers can be a great advantage. This paper contributes with the generation of an environment based on Mbed OS and TensorFlow Lite to be embedded in any general purpose embedded system, allowing the introduction of deep learning architectures. The experiments herein prove that the proposed system is competitive if compared to other commercial systems.

It is said that with great power comes great responsibility. Nowadays, we rely on machine learning systems to make decisions. Unfortunately these systems suffer from algorithmic biases; they often produce results that are systemically prejudiced due to erroneous assumptions in the machine learning process. Consequently these systems can contribute to increase biases in society and this is something we should avoid undoubtedly. The importance of the topic and the effect it has in the society has made it become an important research topic during the last years giving rise to different solutions. In this work, we selected three state-of-the-art techniques, decoupled classifiers, fairness constraints and adversarial learning, that claim to reduce bias in machine learning algorithms and compared their performance over different databases and fairness evaluation metrics. The obtained results show that there is no system performing the best in all aspects and databases but gives some hints to select the best option according to the objective.

The digital divide in Europe has not yet been bridged and thus more contributions towards understanding the factors affecting the different dimensions involved are required. This research offers some insights into the topic by analyzing the e-Government adoption or practical use of e-Government across Europe (26 EU countries). Based on the data provided by the statistical office of the European Union (Eurostat), we defined two indexes, the E-Government Use Index (EGUI) and an extreme version of it taking into account only null or complete use (EGUI(+)), and characterized the use/non use of e-Government tools using supervised learning procedures in a selection of countries with different e-Government adoption levels. These procedures achieved an average accuracy of 73% and determined the main factors related to the practical use of e-Government in each of the countries, e.g. the frequency of buying goods over the Internet or the education level. In addition, we compared the proposed indexes to other indexes measuring the level of e-readiness of a country such as the E-Government Development Index (EGDI) its Online Service Index (OSI) component, the Networked Readiness Index (NRI) and its Government usage component (GU). The ranking comparison found that EGUI(+) is correlated with the four indexes mentioned at 0.05 significance level, as the majority of countries were ranked in similar positions. The outcomes contribute to gaining understanding about the factors influencing the use of e-Government in Europe and the different adoption levels.

Osasun-arlorako softwarean, beste esparru askotan bezala, erabilgarritasuna erronka handia da; batetik, datuak ugariak eta konplexuak direlako eta, bestetik, erabilera-testuingurua kritikoa delako. Jakina da langile klinikoek informazio kopuru egokia eskatzen dutela beren zereginak aurrera eramateko, eta, zentzu horretan, erabiltzaile-interfaze moldagarriak oso baliagarriak izan daitezke informazio-behar horiek asetzeko nahiz informazio-gainkargaren arazoari heltzeko. Erabiltzaile-interfazerako egokitzapenak inplementatu aurretik, baina, aldakorrak diren informazio-behar horiek identifikatu eta lehenetsi egin behar dira. Begi-arakatzaileak lagungarriak izan daitezke zeregin hauek erdiesteko, erabiltzaileen portaera bisuala antzeman baitezakete, zeina interesaren adierazle den. Zoritxarrez, arakatzaile horiek sistema hedatu batean erabiltzeak azpiegitura konplexuegia eskatzen du. Ekarpen honetan aztertu dugu ea erabiltzaileen portaera bisuala inferi ote daitekeen erabiltzaile horiek botiken segurtasunari lotutako arbel batean izandako elkarrekintzaren datuetatik abiatuz. Emaitzek aditzera eman dute bi alderdiak, hots, saguaren bidezko elkarrekintza eta portaera bisuala (karga kognitiboa), lotuta daudela; ezaugarri hauen arabera neurtuak, hurrenez hurren: saguaren ondoz ondoko bi kliken arteko denbora-tarteak eta sagu-pausatzeak, batetik, eta, bestetik, begiradaren finkapenaren iraupenak. Lanak eztabaidatzen du zer eragin izan dezakeen aurkikuntza horrek arbel medikoen egokitzapenen diseinuan.

Usability is a big challenge for medical software, on one side because data are of large size and complex and on the other because the context of use is critical. We know that clinicians call for the right amount and to this regard, adaptive user interfaces can help not only identifying these information needs but also alleviating the data overload. However, before implementing user interface adaptations, these particular information demands have to be identified and prioritised. Eye-trackers can help accomplishing such tasks, since they can gather the visual behaviour of users, which depict interest, but using them in a deployed system requires a complex infraestructure. In this contribution, we analyse whether visual behaviour of users on a medication safety dashboard can be inferred from their interaction data. The results show that the use of the mouse interaction and visual behaviour (cognitive load) are some-how connected, measured in terms of the following features respectively: dwell time and mouse hovers between two consecutive clicks, and duration of gaze fixations. The article discusses the significance of this statement for the design of adaptations in medical dashboards.

Contribution: A learning-by-teaching methodology through games can be used to promote informatics (computer science) in primary and secondary education. Applying the proposed activities can change students' perception of informatics from seeing it as merely using computers to seeing its relationship with mathematics. The experience can also help students acquire competences in teaching. Background: Although students, specifically in primary and secondary education, are increasingly competent in terms of technology use, it has been found that in many cases informatics, as a science, has been relegated to a secondary status; it is usually considered only as a tool or additional resource, and not as an object of study. Intended Outcomes: To refine the application of the learning-to-teach-to-learn (L2T2L) methodology, a learning-by-teaching methodology that has students learn and then, in turn, teach that learning to younger students, in cascade from university to secondary to primary students. To analyze its effects on students' attitudes toward informatics. Application Design: The model incorporates a learning-by-teaching approach in a multistage sequence across different kinds of learners and teachers, using fun, game-like materials. Findings: The use of the action research methodology allowed adjustment of the educational methodology, providing more reliable data and enough experience to suggest how to extend the project to a broader audience. Although the results obtained were less significant than expected, the experience did give students a more realistic view of informatics.

Tracking urban mobility with current heterogeneous sensing capabilities has opened a wide research area on analytical and predictive data-driven models for improvements in transport operations and planning. These improvements are applicable for individual users, service providers and decision-makers. People, vehicles and goods move along the city according to the physical resources (roads, bike-lanes, side-walks...) and non-physical resources (such as scheduled public transportation services). We present this set of resources as the Urban Movement Space (UMS). We collect the main challenges and research foundations that geoinformatic approaches need to cope when tackling transportation resources and mobility data. The work presented in this paper proposes a conceptual modelling framework to represent the urban movement space, in order to match observed tracking data accordingly, and allow further analytical queries. Our approach combines an open free-space and network-based space to model the time-varying urban movement space, considering seasonality and uncertainty of multimodal travel options.