Abstract
One of the caveats of laser-induced breakdown spectroscopy technique is the performance for quantification purposes, in particular when the matrix of the sample is complex or the problem spans over a wide range of concentrations. These two questions are key issues for geology applications including ore grading in mining operations and typically lead to sub-optimal results. In this work, we present the implementation of a class of clustered regression calibration algorithms, that previously search the sample space looking for similar samples before employing a linear calibration model that is trained for that cluster. For a case study involving lithium quantification in three distinct exploration drills, the obtained results demonstrate that building local models can improve the performance of standard linear models in particular in the lower concentration region. Furthermore, we show that the models generalize well for unseen data of exploration drills on distinct rock veins, which can motivate not only further research on this class of methods but also technological applications for similar mining environments.

Abstract
The evolution of virtual reality (VR) technologies has been notorious, both for leisure activities and for activities related to education. The efficiency of this technology in education leads us to point out several benefits and strengths, for students with specific educational needs (SEN), especially for those with autism spectrum disorders (ASD). In this sense, the growing number of students with ASD requires us to innovate so that we can rehabilitate this group of students, giving them a better quality of life. We can improve their skills: social, behavioural, emotional, cognitive; and even their daily tasks. VR offers a panoply of tools, such as interactive three-dimensional simulations of scenarios that can be used with students with ASD. In this literature review several studies were identified, where they differ in the type of applications developed and the technology used by the students. Although optimism prevails, we need more studies on the use of this technology in educational settings. Thus, this article presents a systematic review of the state of the art on VR perspectives and case studies applied to students with ASD. Case studies are presented where VR technology has been successfully applied and with results that demonstrate the effectiveness of the technology in students with ASD. We are aware that much has to be done still to make the potential of VR an effective reality in the educational context and to allow a better quality of life for students with autism spectrum disorders. Also, we believe that in the next years teachers will be ever more capable of creating specific VR experiences. However, it is essential to have a solid theoretical basis to support the correct use of VR regarding students with ASD. This is our goal with this contribution.

Abstract

Abstract
The timely identification of cohort participants at higher risk for attrition is important to earlier interventions and efficient use of research resources. Machine learning may have advantages over the conventional approaches to improve discrimination by analysing complex interactions among predictors. We developed predictive models of attrition applying a conventional regression model and different machine learning methods. A total of 542 very preterm (< 32 gestational weeks) infants born in Portugal as part of the European Effective Perinatal Intensive Care in Europe (EPICE) cohort were included. We tested a model with a fixed number of predictors (Baseline) and a second with a dynamic number of variables added from each follow-up (Incremental). Eight classification methods were applied: AdaBoost, Artificial Neural Networks, Functional Trees, J48, J48Consolidated, K-Nearest Neighbours, Random Forest and Logistic Regression. Performance was compared using AUC- PR (Area Under the Curve-Precision Recall), Accuracy, Sensitivity and F-measure. Attrition at the four follow-ups were, respectively: 16%, 25%, 13% and 17%. Both models demonstrated good predictive performance, AUC-PR ranging between 69 and 94.1 in Baseline and from 72.5 to 97.1 in Incremental model. Of the whole set of methods, Random Forest presented the best performance at all follow-ups [AUC-PR1: 94.1 (2.0); AUC-PR2: 91.2 (1.2); AUC-PR3: 97.1 (1.0); AUC-PR4: 96.5 (1.7)]. Logistic Regression performed well below Random Forest. The top-ranked predictors were common for both models in all follow-ups: birthweight, gestational age, maternal age, and length of hospital stay. Random Forest presented the highest capacity for prediction and provided interpretable predictors. Researchers involved in cohorts can benefit from our robust models to prepare for and prevent loss to follow-up by directing efforts toward individuals at higher risk.

Abstract
Motion-driven electromagnetic energy harvesting is a well-suited technological solution to autonomously power a broad range of autonomous devices. Although different harvester configurations and mechanisms have been already proposed to perform effective tuning and broadband harvesting, no methodology has proven to be effective to maximize the harvester performance for unknown and time-varying patterns of mechanical power sources externally exciting the harvesters. This paper provides, for the first time, a radically new concept of energy harvester to maximize the harvested energy for time-varying excitations: the self-adaptive electromagnetic energy harvester. This research work aims to analyze the electric energy harvesting gain when self-adaptive electromagnetic harvesters, using magnetic levitation architectures, are able to autonomously adapt their architecture as variations in the excitation patterns occur. This was accomplished by identifying the optimal harvester length for different excitation patterns and load resistances. Gains related to electric current and power exceeding 100 can be achieved for small-scale harvesters. The paper also describes comprehensive case studies to verify the feasibility of the self-adaptive harvester, considering the energy demand from the adaptive mechanism, namely the sensing, processing and actuation systems. These successful results highlight the potential of this innovative methodology to design highly sophisticated energy harvesters, both for a small- and large-scale power supply.

Abstract
Background: Gene expression studies are an important tool in biological and biomedical research. The signal carried in expression profiles helps derive signatures for the prediction, diagnosis and prognosis of different diseases. Data science and specifically machine learning have many applications in gene expression analysis. However, as the dimensionality of genomics datasets grows, scalable solutions become necessary. Methods: In this paper we review the main steps and bottlenecks in machine learning pipelines, as well as the main concepts behind scalable data science including those of concurrent and parallel programming. We discuss the benefits of the Dask framework and how it can be integrated with the Python scientific environment to perform data analysis in computational biology and bioinformatics. Results: This review illustrates the role of Dask for boosting data science applications in different case studies. Detailed documentation and code on these procedures is made available at https:// github. com/martaccmoreno/gexp-ml-dask. Conclusion: By showing when and how Dask can be used in transcriptomics analysis, this review will serve as an entry point to help genomic data scientists develop more scalable data analysis procedures.