Abstract
In bioacoustic recognition approaches, a "flat" classifier is usually trained to recognize several species of anuran, where the number of classes is equal to the number of species. Consequently, the complexity of the classification function increases proportionally to the amount of species. To avoid this issue we propose a "hierarchical" approach that decomposes the problem into three taxonomic levels: the family, the genus, and the species level. To accomplish this, we transform the original single-label problem into a multi-dimensional problem (multi-label and multi-class) considering the Linnaeus taxonomy. Then, we develop a top-down method using a set of classifiers organized as a hierarchical tree. Thus, it is possible to predict the same set of species as a flat classifier, and additionally obtain new information about the samples and their taxonomic relationship. This helps us to understand the problem better and achieve additional conclusions by the inspection of the confusion matrices at the three levels of classification. In addition, we carry out our experiments using a Cross-Validation performed by individuals. This form of CV avoids mixing syllables that belong to the same specimens in the testing and training sets, preventing an overestimate of the accuracy and generalizing the predictive capabilities of the system. We tested our system in a dataset with sixty individual frogs, from ten different species, eight genus, and four families, achieving a final Micro-and Average-accuracy equal to 86% and 62% respectively.

Abstract
In this article we discuss the use of LBL acoustic networks for operations with multiple AUVs. Differently from standard LBL configurations, we propose to use the One-Way-Travel-Time of acoustic signals to compute the ranges between all the devices. Moreover, we derive the suitable algorithms for both the navigation of multiple vehicles, but also their external tracking. Experimental results are provided that support the evidence that our approach is successful in operations for multiple vehicles.

Abstract
PRONUTRISENIOR is a holistic approach that considers older adults as part of their environment, in order to better assist health professionals, caregivers and other professionals to monitor their nutritional status and thus reduce malnutrition in this population group. The education and empowerment of professionals were preceded by an assessment of the community and its environment. Such information was subsequently incorporated into the educational and informational materials to support training and empowerment programs. This paper presents the project rationale, describes the methods applied to attain the objectives defined within the scope of the older adults living in its environment, and presents general data on the studied population and sample.

Abstract
In this manuscript, we propose to adapt the B-Spline Explicit Active Surfaces (BEAS) framework for semi-automatic kidney segmentation in computed tomography (CT) images. To study the best energy functional for kidney CT extraction, three different localized region-based energies were implemented within the BEAS framework, namely localized Chan-Vese, localized Yezzi, and signed localized Yezzi energies. Moreover, a novel gradient-based regularization term is proposed. The method was applied on 18 kidneys from 9 CT datasets, with different image properties. Several energy combinations were contrasted using surface-based comparison against ground truth meshes, assessing their accuracy and robustness against surface initialization. Overall, the hybrid energy functional combining the localized signed Yezzi energy with gradient-based regularization simultaneously showed the highest accuracy and the lowest sensitivity to the initialization. Volumetric analysis demonstrated the feasibility of the method from a clinical point of view, with similar reproducibility to manual observers.

Abstract
Today, the variety of complex products, low volume and decreasing life cycles require a combination of multiple skills that, often, do not exist in a single organization. This raises the need to extend the traditional organization towards the extended virtual enterprise. During the last decade several research projects developed concepts, methods and tools to support the design and operation of the virtual enterprises. However, the impact in industry remains low mainly due to the lack of vertical and horizontal integration, both at business and technical level. Industry 4.0 may be the missing enabler for effective virtual enterprises, once it integrates both business entities and technical entities into a single concept - the Industry 4.0 component - thus enabling enhanced interoperability. This paper presents innovative Industry 4.0 approaches, concepts, methods and tools applied to real manufacturing environments, showing how they enable the creation of cyber-physical production systems leading to a flexible, efficient and seamlessly virtual enterprise.

Abstract
Among renewable power sources, wind energy is the most promising technology; however, the inter-temporal uncertainty of this source makes impossible its massive integration. Forecasting of wind generation is a key factor for the economical operation of the power system. Thus, the error related to this process is typically modeled by means of a determined probability distribution to be later incorporated to the unit scheduling and load dispatch optimization procedures. In this paper, wind power forecasting error has been modeled by using Weibull and Levy alpha-stable probability distributions and incorporated to the economic dispatch problem in order to probabilistically describe power production and generating cost. The proposed methodology is illustrated by analyzing a case study composed by 13 conventional generators; the obtained results are compared with Monte Carlo Simulation approach for evaluating and testing the capabilities of the proposed model, observing reasonable accuracy on the estimated results.