Abstract
Machine learning algorithms can be applied to several practical problems, such as spam, fraud and intrusion detection, and customer preferences, among others. In most of these problems, data come in streams, which mean that data distribution may change over time, leading to concept drift. The literature is abundant on providing supervised methods based on error monitoring for explicit drift detection. However, these methods may become infeasible in some real-world applications-where there is no fully labeled data available, and may depend on a significant decrease in accuracy to be able to detect drifts. There are also methods based on blind approaches, where the decision model is updated constantly. However, this may lead to unnecessary system updates. In order to overcome these drawbacks, we propose in this paper a semi-supervised drift detector that uses an ensemble of classifiers based on self-training online learning and dynamic classifier selection. For each unknown sample, a dynamic selection strategy is used to choose among the ensemble's component members, the classifier most likely to be the correct one for classifying it. The prediction assigned by the chosen classifier is used to compute an estimate of the error produced by the ensemble members. The proposed method monitors such a pseudo-error in order to detect drifts and to update the decision model only after drift detection. The achievement of this method is relevant in that it allows drift detection and reaction and is applicable in several practical problems. The experiments conducted indicate that the proposed method attains high performance and detection rates, while reducing the amount of labeled data used to detect drift.

Abstract
Data processing (or the transformation of data into knowledge and/or information) has become an indispensable tool for decision-making in many areas of engineering. Engineering optimization problems with many objectives are common. However, the decision-making process for these problems is complicated since there are many trade-offs that are difficult to identify. Thus, in this work, multivariate statistical methods, Principal Component Analysis (PCA) and Cluster Analysis (CA), have been studied and applied to analyze the results of many objective engineering optimization problems. PCA reduces the number of objectives to a very small number, CA through the similarities and dissimilarities, creates groups of solutions, i.e., bringing together in the same group solutions with the same characteristics and behaviors. Two engineering optimization problems with many objectives are solved: a mechanical problem consisting in the optimal design of laminated plates, with four objectives and a problem of optimization of the radar waveform, with nine objectives. For the problem of the design of laminated plates through PCA allowed to reduce to two objectives and through CA it was possible to create three distinct groups of solutions. For the problem of optimization of the radar waveform, it was possible to reduce the objectives from nine to two objectives representing the greatest variability of the data, and CA defined three distinct groups of solutions. These results demonstrate that these tools are effective to assist the decision-making processes in the presence of a large number of solutions and/or objectives.

Abstract
COVID pandemic has changed the way in which we carry out our daily life and also have affected educational processes. Teaching and learning have changed from a most common face to face context to a blended or online context. This implies changes in the way to carry out the activates and have an impact in research projects such as RoboSTEAM. Such project, that applies Challenge Based Learning methodologies with application of Robotics and Mechatronics, requires to change its approach to show how it is possible to succeed in the new situation. This paper describes how the project has evolved, how it has been affected by COVID and the possible changes to carry out. Regarding this last issue remote labs and online tools are presented as solutions to support changes in the application of challenge-based learning methodology. © 2020 ACM.

Abstract
Digital marketing is gaining predominance in marketing strategies across the globe. Digitization is becoming more and more present in business, not just changes in consumer behavior, but the adoption of new technologies, tools, and applications is highly disruptive, with immediate impact on the business of all companies. The common link between digital marketing definitions is the use of tools, namely online tools. One of the biggest changes in human interaction is the recent proliferation of online social networks. Rapid growth of web-based platforms that facilitate online social behavior has significantly modified the nature of human activities, habitats, and interactions. Real-world social relationships have been migrated to the virtual world, resulting in online communities that bring people together from across the globe. This study aims to identify and describe the various digital marketing tools and which of these can be used to increase the SMEs competitiveness. © 2021, IGI Global.

Abstract
Conventionally, vital sign monitoring for neonatal infants inside the Neonatal Intensive Care Unit is performed via probes affixed to their skin. However, such instruments may cause damage to the epidermis and increase the risk of infection as well as promote discomfort to the infant. As an alternative to traditional means of monitoring heart rate, remote Photoplethysmography techniques have been surging among the scientific community. These techniques have been vastly explored for adult subjects but not for neonatal infants, who would greatly benefit from such applications. This study aims at developing a regular consumer camera-based framework for continuous and contactless extraction of the heart rate in adult subjects in challenging conditions and investigating the tool's ability to adapt to a new domain which consists of newborn subjects and the real-world conditions of a Neonatal Intensive Care Unit.

Abstract
AbstractPurposePredicting outcomes after resection of primary melanoma remains crude, primarily based on tumour thickness. We explored gene expression signatures for their ability to better predict outcomes.MethodsDifferential expression analysis of 194 primary melanomas resected from patients who either developed distant metastasis (n=89) or did not (n=105) was performed. We identified 121 metastasis-associated genes that were included in our prognostic signature, “Cam_121”. Several machine learning classification models were trained using nested leave- one-out cross validation (LOOCV) to test the signature’s capacity to predict metastases, as well as regression models to predict survival. The prognostic accuracy was externally validated in two independent datasets.ResultsCam_121 performed significantly better in predicting distant metastases than any of the models trained with the clinical covariates alone (pAccuracy=4.92×10-3), as well as those trained with two published prognostic signatures. Cam_121 expression score was strongly associated with progression-free survival (HR=1.7, p=3.44×10-6), overall survival (HR=1.73, p=7.71×10-6) and melanoma-specific survival (HR=1.59, p=0.02). Cam_121 expression score also negatively correlated with measures of immune cell infiltration (?=-0.73, p<2.2×10-16), with a higher score representing reduced tumour lymphocytic infiltration and a higher absolute 5-year risk of death in stage II melanoma.ConclusionsThe Cam_121 primary melanoma gene expression signature outperformed currently available alternatives in predicting the risk of distant recurrence. The signature confirmed (using unbiased approaches) the central prognostic importance of immune cell infiltration in long-term patient outcomes and could be used to identify stage II melanoma patients at highest risk of metastases and poor survival who might benefit most from adjuvant therapies.Translational relevancePredicting outcomes after resection of primary melanoma is currently based on traditional histopathological staging, however survival outcomes within these disease stages varies markedly. Since adjuvant systemic therapies are now being used routinely, accurate prognostic information is needed to better risk stratify patients and avoid unnecessary use of high cost, potentially harmful drugs, as well as to inform future adjuvant strategies. The Cam_121 gene expression signature appears to have this capability and warrants evaluation in prospective clinical trials.