Abstract
This work focuses on a reservoir with water leaks since its construction, the Beninar reservoir. The purpose of this reservoir was to regulate the Adra River basin, lying between the provinces of Almeria and Granada, and located south of Sierra Nevada Mountains (in the Inner Zones of the Betic Cordilleras, SE Spain). This basin extends over 746 km(2), at an altitude of 2780 m, with a very rough terrain and frequent torrential water flow. Due to the continuous extension of greenhouses in the east and west parts of Almeria, the water demand for agriculture and urban consumption increases day by day. As a consequence, aquifers are being overexploited, causing the current system to not be sustainable for a long time, that is, the storage capacity of the underground media and their possible contributions to an efficient management of resources have not been adequately taken into account. The Beninar dam has always had problems with water leaks. The dam was built even knowing that the land was not the most suitable, due to the frequent earth movements that took place in the town of Beninar, which was submerged beneath the waters of the reservoir. In this work, we process multi-temporal SAR datasets coming from the C-band satellites ERS-1/2, Envisat, and Sentinel-1A/B using MT-InSAR techniques, being able to monitor the deformation behavior of this dam for a long time period of more than 25 years, from 1992 to 2018.

Abstract
This paper discusses the integration of emergent ICTs, such as the Internet of Things (IoT), the Arrowhead Framework, and the best practices from the area of condition monitoring and maintenance. These technologies are applied, for instance, for roller element bearing fault diagnostics and analysis by simulating faults. The authors first undertook the leading industry standards for condition-based maintenance (CBM), i.e., open system architecture-condition-based maintenance (OSA-CBM) and Machinery Information Management Open System Alliance (MIMOSA), which has been working towards standardizing the integration and interchangeability between systems. In addition, this paper highlights the predictive health monitoring methods that are needed for an effective CBM approach. The monitoring of industrial machines is discussed as well as the necessary details are provided regarding a demonstrator built on a metal sheet bending machine of the Greenbender family. Lastly, the authors discuss the benefits of the integration of the developed prototypes into a service-oriented platform, namely the Arrowhead Framework, which can be instrumental for the remotization of maintenance activities, such as the analysis of various equipment that are geographically distributed, to push forward the grand vision of the servitization of predictive health monitoring methods for large-scale interoperability.

Abstract
Sensors are susceptible to failure when exposed to extreme conditions over long periods of time. Besides they can be affected by noise or electrical interference. Models (Machine Learning or others) obtained from these faulty and noisy sensors may be less reliable. In this paper, we propose a data augmentation approach for making neural networks more robust to missing and faulty sensor data. This approach is shown to be effective in a real life industrial application that uses data of various sensors to predict the wear of an automotive fuel-system component. Empirical results show that the proposed approach leads to more robust neural network in this particular application than existing methods.

Abstract
This paper presents an optimal bidding and offering strategy for a virtual power plant (VPP), which participates in day-ahead (DA) and balancing markets. The VPP comprises distributed energy resources, plug-in electric vehicles (PEVs) and flexible demands. The objective of the problem is maximizing the VPP's profit while demand response (DR) providers who aggregated the loads try to supply the required demand under their jurisdiction with minimum costs. The proposed optimization problem is formulated as a bi-level stochastic scheduling programming to address uncertainties in DA and balancing electricity prices, renewable energy source's (RES) and DR relationship. Simulation results demonstrate the applicability and effectiveness of the proposed model to any real markets. Also, numerical results show that the flexibility of responsive loads and PEVs can improve the VPP operator's energy management and increase its expected profit. © 2020 IEEE.

Abstract
Objectives: To develop and validate a clinical model to identify patients admitted to hospital with community-acquired infection (CAI) caused by pathogens resistant to antimicrobials recommended in current CAI treatment guidelines. Methods: International prospective cohort study of consecutive patients admitted with bacterial infection. Logistic regression was used to associate risk factors with infection by a resistant organism. The final model was validated in an independent cohort. Results: There were 527 patients in the derivation and 89 in the validation cohort. Independent risk factors identified were: atherosclerosis with functional impairment (Karnofsky index <70) [adjusted OR (aOR) (95% CI) = 2.19 (1.41-3.40)]; previous invasive procedures [adjusted OR (95% CI) = 1.98 (1.28-3.05)]; previous colonization with an MDR organism (MDRO) [aOR (95% CI) = 2.67 (1.48-4.81)]; and previous antimicrobial therapy [aOR (95% CI) = 2.81 (1.81-4.38)]. The area under the receiver operating characteristics (AU-ROC) curve (95% CI) for the final model was 0.75 (0.70-0.79). For a predicted probability >= 22% the sensitivity of the model was 82%, with a negative predictive value of 85%. In the validation cohort the sensitivity of the model was 96%. Using this model, unnecessary broad-spectrum therapy would be recommended in 30% of cases whereas undertreatment would occur in only 6% of cases. Conclusions: For patients hospitalized with CAI and none of the following risk factors: atherosclerosis with functional impairment; previous invasive procedures; antimicrobial therapy; or MDRO colonization, CAI guidelines can safely be applied. Whereas, for those with some of these risk factors, particularly if more than one, alternative antimicrobial regimens should be considered.

Abstract
Medical imaging is a rich source of invaluable information necessary for clinical judgements. However, the analysis of those exams is not a trivial assignment. In recent times, the use of deep learning (DL) techniques, supervised or unsupervised, has been empowered and it is one of the current research key areas in medical image analysis. This paper presents a survey of the use of DL architectures in computer-assisted imaging contexts, attending two different image modalities: the actively studied computed tomography and the under-studied positron emission tomography, as well as the combination of both modalities, which has been an important landmark in several decisions related to numerous diseases. In the making of this review, we analysed over 180 relevant studies, published between 2014 and 2019, that are sectioned by the purpose of the research and the imaging modality type. We conclude by addressing research issues and suggesting future directions for further improvement. To our best knowledge, there is no previous work making a review of this issue.