Abstract
Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that contextual embeddings can be used to achieve unprecedented gains in Word Sense Disambiguation (WSD) tasks. Our approach focuses on creating sense-level embeddings with full-coverage of WordNet, and without recourse to explicit knowledge of sense distributions or task-specific modelling. As a result, a simple Nearest Neighbors (k-NN) method using our representations is able to consistently surpass the performance of previous systems using powerful neural sequencing models. We also analyse the robustness of our approach when ignoring part-of-speech and lemma features, requiring disambiguation against the full sense inventory, and revealing shortcomings to be improved. Finally, we explore applications of our sense embeddings for concept-level analyses of contextual embeddings and their respective NLMs.

Abstract
The amount of data extracted from production processes has increased exponentially due to the proliferation of sensing technologies. When processed and analyzed, data can bring out valuable information and knowledge from manufacturing process, production system and equipment. In industries, equipment maintenance is an important key, and affects the operation time of equipment and its efficiency. Thus, equipment faults need to be identified and solved, avoiding shutdown in the production processes. Machine Learning (ML) methods have been emerged as a promising tool in Predictive Maintenance (PdM) applications to prevent failures in equipment that make up the production lines in the factory floor. However, the performance of PdM applications depends on the appropriate choice of the ML method. The aim of this paper is to present a systematic literature review of ML methods applied to PdM, showing which are being explored in this field and the performance of the current state-of-the-art ML techniques. This review focuses on two scientific databases and provides a useful foundation on the ML techniques, their main results, challenges and opportunities, as well as it supports new research works in the PdM field.

Abstract
The widespread usage of Machine Learning and Data Mining models in several key areas of our societies has raised serious concerns in terms of accountability and ability to justify and interpret the decisions of these models. This is even more relevant when models are too complex and often regarded as black boxes. In this paper we present several tools designed to help in understanding and explaining the reasons for the observed predictive performance of black box regression models. We describe, evaluate and propose several variants of Error Dependence Plots. These plots provide a visual display of the expected relationship between the prediction error of any model and the values of a predictor variable. They allow the end user to understand what to expect from the models given some concrete values of the predictor variables. These tools allow more accurate explanations on the conditions that may lead to some failures of the models. Moreover, our proposed extensions also provide a multivariate perspective of this analysis, and the ability to compare the behaviour of multiple models under different conditions. This comparative analysis empowers the end user with the ability to have a case-based analysis of the risks associated with different models, and thus select the model with lower expected risk for each test case, or even decide not to use any model because the expected error is unacceptable.

Abstract
We address the problem of generating electrical power through Airborne Wind Energy Systems, using a kite connected to a generator on the ground. We propose a controller to steer the kite to follow a pre-defined eight-shaped path based on a nonlinear guidance logic. The controller has an easy implementable explicit form, has asymptotic stability guarantees and a large domain of attraction. We report simulations of a complete production cycle, including a production phase and a recovery phase. Also, we provide a Lyapunov stability analysis. © 2019 American Automatic Control Council.

Abstract

Abstract
This work proposes a method to calculate the short- circuit currents in unbalanced three-phase power distribution systems with distributed generation (DG) from non- and renewable energy resources. It takes into account the physical and operational features of four different types of DGs: synchronous, induction, photovoltaic and double-fed induction generator (DFIG). The DG formulations depend upon the connection type that can be directly coupling to the power grid or by using electronic converters or coupling transformers. The proposed method uses the bus impedance matrix with Kron reduction for each generator and superposition conception in the short-circuit current calculation. The results are achieved under a real-work unbalanced distribution network with 135 buses providing typical values of the short-circuit current that are compared with values from commercial software in the evaluation of the proposed methodology.