Abstract
Research and development of autonomous mobile robotic solutions that can perform several active agricultural tasks (pruning, harvesting, mowing) have been growing. Robots are now used for a variety of tasks such as planting, harvesting, environmental monitoring, supply of water and nutrients, and others. To do so, robots need to be able to perform online localization and, if desired, mapping. The most used approach for localization in agricultural applications is based in standalone Global Navigation Satellite System-based systems. However, in many agricultural and forest environments, satellite signals are unavailable or inaccurate, which leads to the need of advanced solutions independent from these signals. Approaches like simultaneous localization and mapping and visual odometry are the most promising solutions to increase localization reliability and availability. This work leads to the main conclusion that, few methods can achieve simultaneously the desired goals of scalability, availability, and accuracy, due to the challenges imposed by these harsh environments. In the near future, novel contributions to this field are expected that will help one to achieve the desired goals, with the development of more advanced techniques, based on 3D localization, and semantic and topological mapping. In this context, this work proposes an analysis of the current state-of-the-art of localization and mapping approaches in agriculture and forest environments. Additionally, an overview about the available datasets to develop and test these approaches is performed. Finally, a critical analysis of this research field is done, with the characterization of the literature using a variety of metrics.

Abstract
The missing data issue is often found in real-world datasets and it is usually handled with imputation strategies that replace the missing values with new data. Recently, generative models such as Variational Autoencoders have been applied for this imputation task. However, they were always used to perform the entire imputation, which has presented limited results when comparing to other state-of-the-art methods. In this work, a new approach called Variational Autoencoder Filter for Bayesian Ridge Imputation is introduced. It uses a Variational Autoencoder at the beginning of the imputation pipeline to filter the instances that are later fitted to a Bayesian ridge regression used to predict the new values. The approach was compared to four state-of-the-art imputation methods using 10 datasets from the healthcare context covering clinical trials, all injected with missing values under different rates. The proposed approach significantly outperformed the remaining methods in all settings, achieving an overall improvement between 26% and 67%.

Abstract
The dropout of university students has been a factor of concern for educational institutions, affecting various aspects such as the institution’s reputation and funding and rankings. For this reason, it is essential to identify which students are at risk. In this study, algorithms based on decision trees and random forests are proposed to solve these problems using real data from 331 students from the University of Trásos-Montes and Alto Douro. In this work with these learning algorithms together with the training strategies, we managed to obtain an 89% forecast of students who may abandon their studies based on the evaluations of both semesters related to the first year and personal data. © 2021, Springer Nature Switzerland AG.

Abstract
Saliency maps have been used as one possibility to interpret deep neural networks. This method estimates the relevance of each pixel in the image classification, with higher values representing pixels which contribute positively to classification. The goal of this study is to understand how the complexity of the network affects the interpretabilty of the saliency maps in classification tasks. To achieve that, we investigate how changes in the regularization affects the saliency maps produced, and their fidelity to the overall classification process of the network. The experimental setup consists in the calculation of the fidelity of five saliency map methods that were compare, applying them to models trained on the CIFAR-10 dataset, using different levels of weight decay on some or all the layers. Achieved results show that models with lower regularization are statistically (significance of 5%) more interpretable than the other models. Also, regularization applied only to the higher convolutional layers or fully-connected layers produce saliency maps with more fidelity.

Abstract
The objective of this work is study, implementation and evaluation of compression techniques used in bioelectrical signals, applied to electroencephalography. For that, the fundamental concepts of Fast Walsh Hadamard Transform (FWHT), the Discrete Cosine Transform (DCT) and the Discrete Wavelet Transform (DWT), in essence, the mathematical models were studied. In these systems, the applicability and principles of operation were considered the Peak Signal to Noise Ratio (PSNR), Signal to Noise Ratio (SNR), Mean Absolute Error (MAE) and mean squared error. Later, it is proposed the implementation of the compression algorithms. For the implementation of the techniques, computational tools of tests were developed, and for the purposes of validation and comparison of the results were used, with the appropriate adaptations, and described in the work, being these among the most recognised in terms of evaluation of signal quality. Finally, we present the results and the conclusions, where we sought a compromise of the implementations between the estimated percentage of DCT and the level of degradation of the signal provided by the compression application. In this sense, it was verified that they presented satisfactory results.

Abstract
Conventional electrical networks are slowly changing. A strong sense of policy urges as well as commitments have recently been surfacing in many countries to integrate more environmentally friendly energy sources into electrical systems. In particular, stern efforts have been made to integrate more and more solar and wind energy sources. One of the major setbacks of such resources arises as a result of their intermittent nature, creating several problems in the electrical systems from a technical, market, operation, and planning perspectives. This work focuses on the operation of an electrical system with large-scale integration of solar and wind power. In order to cope with the intermittency inherent to such power sources, it is necessary to introduce more flexibility into the system. In this context, demand response, energy storage systems, and dynamic reconfiguration of the system are introduced, and the operational performance of the resulting system is thoroughly analyzed. To carry out the required analysis, a stochastic mixed-integer linear programming operational model is developed, whose efficacy is tested on an IEEE 119-bus standard network system. Numerical results indicate that the joint deployment and management of various flexibility mechanisms into the system can support a seamless integration of large-scale intermittent renewable energies.