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.

Abstract
Adversarial machine learning is an area of study that examines both the generation and detection of adversarial examples, which are inputs specially crafted to deceive classifiers, and has been extensively researched specifically in the area of image recognition, where humanly imperceptible modifications are performed on images that cause a classifier to perform incorrect predictions. The main objective of this paper is to study the behavior of multiple state of the art machine learning algorithms in an adversarial context. To perform this study, six different classification algorithms were used on two datasets, NSL-KDD and CICIDS2017, and four adversarial attack techniques were implemented with multiple perturbation magnitudes. Furthermore, the effectiveness of training the models with adversaries to improve recognition is also tested. The results show that adversarial attacks successfully deteriorate the performance of all the classifiers between 13% and 40%, with the Denoising Autoencoder being the technique with highest resilience to attacks.

Abstract
This paper proposes a new methodology to automatically segment and measure the volume of pulmonary nodules in lung computed tomography (CT) scans. Estimating the malignancy likelihood of a pulmonary nodule based on lesion characteristics motivated the development of an unsupervised pulmonary nodule segmentation and volume measurement as a preliminary stage for pulmonary nodule characterization. The idea is to optimally cluster a set of feature vectors composed by intensity and shape-related features in a given feature data space extracted from a pre-detected nodule. For that purpose, a metaheuristic search based on evolutionary computation is used for clustering the corresponding feature vectors. The proposed method is simple, unsupervised and is able to segment different types of nodules in terms of location and texture without the need for any manual annotation. We validate the proposed segmentation and volume measurement on the Lung Image Database Consortium and Image Database Resource Initiative - LIDC-IDRI dataset. The first dataset is a group of 705 solid and sub-solid (assessed as part-solid and non-solid) nodules located in different regions of the lungs, and the second, more challenging, is a group of 59 sub-solid nodules. The average Dice scores of 82.35% and 71.05% for the two datasets show the good performance of the segmentation proposal. Comparisons with previous state-of-the-art techniques also show acceptable and comparable segmentation results. The volumes of the segmented nodules are measured via ellipsoid approximation. The correlation and statistical significance between the measured volumes of the segmented nodules and the ground-truth are obtained by Pearson correlation coefficient value, obtaining an R-value >= 92.16% with a significance level of 5%.