Abstract
Introduction: Breast volume estimation is considered crucial for breast cancer surgery planning. A single, easy, and reproducible method to estimate breast volume is not available. This study aims to evaluate, in patients proposed for mastectomy, the accuracy of the calculation of breast volume from a low-cost 3D surface scan (Microsoft Kinect) compared to the breast MRI and water displacement technique. Material and Methods: Patients with a Tis/T1-T3 breast cancer proposed for mastectomy between July 2015 and March 2017 were assessed for inclusion in the study. Breast volume calculations were performed using a 3D surface scan and the breast MRI and water displacement technique. Agreement between volumes obtained with both methods was assessed with the Spearman and Pearson correlation coefficients. Results: Eighteen patients with invasive breast cancer were included in the study and submitted to mastectomy. The level of agreement of the 3D breast volume compared to surgical specimens and breast MRI volumes was evaluated. For mastectomy specimen volume, an average (standard deviation) of 0.823 (0.027) and 0.875 (0.026) was obtained for the Pearson and Spearman correlations, respectively. With respect to MRI annotation, we obtained 0.828 (0.038) and 0.715 (0.018). Discussion: Although values obtained by both methodologies still differ, the strong linear correlation coefficient suggests that 3D breast volume measurement using a low-cost surface scan device is feasible and can approximate both the MRI breast volume and mastectomy specimen with sufficient accuracy. Conclusion: 3D breast volume measurement using a depth-sensor low-cost surface scan device is feasible and can parallel MRI breast and mastectomy specimen volumes with enough accuracy. Differences between methods need further development to reach clinical applicability. A possible approach could be the fusion of breast MRI and the 3D surface scan to harmonize anatomic limits and improve volume delimitation.

Abstract
In Portugal, the dropout rate of university courses is around 29%. Understanding the reasons behind such a high desertion rate can drastically improve the success of students and universities. This work applies existing data mining techniques to predict the academic dropout mainly using the academic grades. Four different machine learning techniques are presented and analyzed. The dataset consists of 331 students who were previously enrolled in the Computer Engineering degree at the Universidade de Tras-os-Montes e Alto Douro (UTAD). The study aims to detect students who may prematurely drop out using existing methods. The most relevant data features were identified using the Permutation Feature Importance technique. In the second phase, several methods to predict the dropouts were applied. Then, each machine learning technique's results were displayed and compared to select the best approach to predict academic dropout. The methods used achieved good results, reaching an Fl-Score of 81% in the final test set, concluding that students' marks somehow incorporate their living conditions.

Abstract
Despite being one of the most cost-effective methods, email marketing remains challenging due to the low rate of opened emails and the high percentage of unsubscribed campaigns. Since the sender and the subject line are the only information that the recipient sees at first when receiving an email, the decision to open an email critically depends on these two factors, which should stand out and catch the recipient's attention. Therefore, the motivation behind this study is to support email campaign editors in choosing a subject line based on its potential quality. We propose and compare several models to measure the quality of a subject line, considering its potential to promote the email opening. The subject lines' structure and content are explored together with different machine learning techniques (Random Forest, Decision Trees, Neural Networks, Naive Bayes, Support Vector Machines, and Gradient Boosting). To validate the proposed model, a data set of 140,000 emails' subject lines was used. The results revealed that the models proposed are very promising to support the definition of the email marketing subject lines and show that the combination of data regarding the structure, the content of the subject lines, and senders characteristics leads to more accurate classifications of the potential of the subject line.

Abstract
Protection and control systems represent an essential part of distribution networks, ensuring the physical integrity of components and improving system reliability. Protection devices isolate a portion of the network affected by a fault, while control devices reduce the number of de-energized loads by transferring loads to neighboring feeders. The integration of distributed generation has the potential to improve the continuity of energy services through islanding operation during outage conditions. In this context, this paper presents a multi-objective optimization approach for the size and allocation of protection and control devices in distribution networks with microgrids supplied by renewable energy sources. Reclosers, fuses, remote-controlled switches, and directional relays are considered in the formulation. The demand and generation uncertainties define the islanding operation and the load transfer possibilities. A genetic algorithm is presented to solve the allocation problem. The compromise programming is performed to choose the best solution from the Pareto front. Results show interesting setups for the protection system and viability of islanding operation.

Abstract
Facial expressions are one of the most common way to externalize our emotions. However, the same emotion can have different effects on the same person and has different effects on different people. Based on this, we developed a system capable of detecting the facial expressions of a person in real-time, occluding the eyes (simulating the use of virtual reality glasses). To estimate the position of the eyes, in order to occlude them, Multi-task Cascade Convolutional Neural Networks (MTCNN) were used. A residual network, a VGG, and the combination of both models, were used to perform the classification of 7 different types of facial expressions (Angry, Disgust, Fear, Happy, Sad, Surprise, Neutral), classifying the occluded and non-occluded dataset. The combination of both models, achieved an accuracy of 64.9% for the occlusion dataset and 62.8% for no occlusion, using the FER-2013 dataset. The primary goal of this work was to evaluate the influence of occlusion, and the results show that the majority of the classification is done with the mouth and chin. Nevertheless, the results were far from the state-of-the-art, which is expect to be improved, mainly by adjusting the MTCNN.

Abstract
Distributional semantics based on neural approaches is a cornerstone of Natural Language Processing, with surprising connections to human meaning representation as well. Recent Transformer-based Language Models have proven capable of producing contextual word representations that reliably convey sense-specific information, simply as a product of self supervision. Prior work has shown that these contextual representations can be used to accurately represent large sense inventories as sense embeddings, to the extent that a distance-based solution to Word Sense Disambiguation (WSD) tasks outperforms models trained specifically for the task. Still, there remains much to understand on how to use these Neural Language Models (NLMs) to produce sense embeddings that can better harness each NLM's meaning representation abilities. In this work we introduce a more principled approach to leverage information from all layers of NLMs, informed by a probing analysis on 14 NLM variants. We also emphasize the versatility of these sense embeddings in contrast to task-specific models, applying them on several sense-related tasks, besides WSD, while demonstrating improved performance using our proposed approach over prior work focused on sense embeddings. Finally, we discuss unexpected findings regarding layer and model performance variations, and potential applications for downstream tasks.& nbsp;