Abstract
Light propagating in nonlinear optical materials opens the possibility to emulate quantum fluids of light with accessible tabletop experiments by taking advantage of the hydrodynamical interpretation. In this context, various optical materials have been studied in recent years, with nematic liquid crystals appearing as one of the most promising ones due to their controllable properties. Indeed, the application of an external electric field can tune their nonlocal response, and this mechanism may be useful for producing fluids of light and developing optical analogues. In this work, we extend the applicability of nematic liquid crystal to support optical analogues and study the possibility of emulating turbulent phenomena by using two fluids of light. These fluids interact with each other through the nonlinearity of the medium and generate instabilities that will lead to turbulent regimes. We also explore the possibility of exciting turbulent regimes through the decay of dark soliton stripes. The preliminary results are presented. © 2022, Universidade do Porto - Faculdade de Engenharia. All rights reserved.

Abstract
Purpose To provide a systematic review with meta-analysis providing evidence of the current diagnostic test accuracy (DTA) of pedicle screw electrical stimulation. Methods A systematic database search on PubMed, Scopus and Web of Science was performed according to the PRISMA-DTA guidelines, and eligibility criteria applied to reduce the results to: (1) only journal articles reporting electrical stimulation of the pedicle screw head, (2) screw position confirmation by imaging techniques, and (3) enough information allowing the calculation of a 2 x 2 contingency table. Sample characteristics, image confirmation method, electrical current threshold and stimulation results were retrieved and analyzed using according to appropriate DTA analysis methods, and allowing the calculation of specificity, sensitivity for pedicle screws insertion at the lumbar and thoracic levels. Results Lumbar screw stimulation presents a higher sensitivity (0.586 [0.336, 0.798] and specificity (0.984 [0.958, 0.994]) than thoracic screws (sensitivity: 0.270 [0.096; 0.562]; specificity: 0.958 [0.931, 0.975]). The same is observed in terms of the diagnostic odds ratio for lumbar (88.32 [32.136, 242.962]) and thoracic (8.460 [2.139, 33.469]) levels. When performing a sub-group analysis, it is possible to divide the lumbar stimulation threshold as 8 and 10-12 mA, and the thoracic threshold as 6 and 9-12 mA. A threshold of 8 mA at the lumbar level provides higher sensitivity and specificity. Increasing the threshold results in higher specificity but not sensitivity. In fact, at the range of 10-12 mA, the diagnostic validity is too low to confer this technique any robust diagnostic validity. Similarly, at the thoracic level, lower threshold currents are associated with increased sensitivity, but their diagnostic validity is very low. Conclusion Electrical stimulation of the pedicle screw can be used as an adequate diagnostic capability at the lumbar level with a threshold of 8 mA. However, thoracic stimulation is currently not reliable, with very low sensitivity and diagnostic validity at 6 mA or higher.

Abstract
Density estimation is an important tool for data analysis. Non-parametric approaches have a reputation for offering state-of-the-art density estimates limited to few dimensions. Despite providing less accurate density estimates, histogram-based approaches remain the only alternative for datasets in high-dimensional spaces. In this paper, we present a multivariate histogram approach to estimate the density of a dataset without restrictions on the number of dimensions, containing both numerical and categorical variables (without numerical encoding) and allowing missing data (without the need to preprocess them). Results from the empirical evaluation show that it is possible to estimate the density of datasets without restrictions on dimensionality, and the method is robust to missing values and categorical variables.

Abstract
Microscopy images have been increasingly analyzed quantitatively in biomedical research. Segmenting individual cell nucleus is an important step as many research studies involve counting cell nuclei and analysing their shape. We propose a novel weakly supervised instance segmentation method trained with image segmentation masks only. Our system comprises two models: an implicit shape Multi-Layer Perceptron (MLP) that learns the shape of the nuclei in canonical coordinates; and 2) an encoder that predicts the parameters of the affine transformation to deform the canonical shape into the correct location, scale, and orientation in the image. To further improve the performance of the model, we propose a loss that uses the total number of nuclei in an image as supervision. Our system is explainable, as the implicit shape MLP learns that the canonical shape of the cell nuclei is a circle, and interpretable as the output of the encoder are parameters of affine transformations. We obtain image segmentation performance close to DeepLabV3 and, additionally, obtain an F1-scoreIoU=0.5 of 68.47% at the instance segmentation task, even though the system was trained with image segmentations.

Abstract
Football is one of the most popular sports in the world, so the perception of the game and the prediction of results is of general interest to fans, coaches, media and gamblers. Although predicting football results is a very complex task, the football betting business has grown over time. The unpredictability of football results and the growing betting business justify the development of prediction models to support gamblers. In this article, we develop machine learning methods that take multiple statistics of previous matches and attributes of players from both teams as inputs to predict the outcome of football matches. Several prediction models were tested, with the experimental results showing encouraging performance in terms of the profit margin of football bets. © 2022 Elsevier B.V.. All rights reserved.

Abstract
X-ray bone semantic segmentation is one crucial task in medical imaging. Due to deep learning's emergence, it was possible to build high-precision models. However, these models require a large quantity of annotated data. Furthermore, semantic segmentation requires pixel-wise labeling, thus being a highly time-consuming task. In the case of hip joints, there is still a need for increased anatomic knowledge due to the intrinsic nature of the femur and acetabulum. Active learning aims to maximize the model's performance with the least possible amount of data. In this work, we propose and compare the use of different queries, including uncertainty and diversity-based queries. Our results show that the proposed methods permit state-of-the-art performance using only 81.02% of the data, with O(1) time complexity.