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.

Abstract
Industry 4.0 has been changing and improving the manufacturing processes. To embrace these changes, factories must keep up to date with all the new emerging technologies. In the automotive industry, the growing demand for customization and constant car model changes leads to an inevitable grow of complexity of the final product quality inspection process. In the project INDTECH 4.0, smart technologies are being explored in an automotive factory assembly line to automate the vehicle quality control, which still relies on human inspection based on paper conformity checklists. This paper proposes an automated inspection process based on computer vision to assist operators in the conformity assessment of informative labels affixed inside the engine compartment of the car. Two of the most recent object detection algorithms: YOLOv5 and YOLOX are evaluated for the identification of labels in the images. Our results show high mean average precision on both algorithms (98%), which overall, tells us that both algorithms showed good performances and have potential to be implemented in the shop floor to support the vehicle quality control.

Abstract
With the increase of distance learning, in general, and e-learning, in particular, having a system capable of determining the engagement of students is of primordial importance, and one of the biggest challenges, both for teachers, researchers and policymakers. Here, we present a system to detect the engagement level of the students. It uses only information provided by the typical built-in web-camera present in a laptop computer, and was designed to work in real time. We combine information about the movements of the eyes and head, and facial emotions to produce a concentration indexwith three classes of engagement: very engaged, nominally engaged and not engaged at all. The system was tested in a typical e-learning scenario, and the results show that it correctly identifies each period of time where students were very engaged, nominally engaged and not engaged at all. Additionally, the results also show that the students with best scores also have higher concentration indexes.

Abstract
In this paper, a new framework for accurate reliability analysis is proposed based on improving the directional simulation by using metaheuristic algorithms. Usually for highly nonlinear and complex performance functions, finding the unit vector direction requires very high calculations or impossible practically. Hence, the novel improved version incorporates the Harris Hawks Optimization algorithm, where the unit vector of direction is formulated as a constrained optimization problem and estimated using metaheuristic algorithms. Given that metaheuristic algorithms have been introduced to solve unconstrained problems, the penalty function method is used to convert the constrained problem into an unconstrained problem. The applicability of the proposed framework is firstly tested on five highly nonlinear benchmark functions and then applied to solve four high-dimensional engineering problems. The performance of six simulations-based reliability analysis methods and the first-order reliability method were compared with the proposed method. Besides the feasibility of other metaheuristic algorithms were investigated. The results show high-performance abilities of the improved version of the directional simulation for solving highly nonlinear engineering problems.

Abstract
Mobile devices, as smartphones and tablets, have presented an exponential growth, being part of our everyday life, particularly considering children [1]. Their daily habits are undoubtedly influenced by technology and the applications they use can affect socialization and learning processes [2]. Specifically, games are the most popular type of applications and have the potential to change attitudes and behaviours. Emphasizing the importance of this area, we decided to create a serious game that stimulates the children' responsibility for taking care of pets while they play, called My Buddy. In this paper, we present the development and assessment process of a 3D serious game, where the user is asked to interact with a pet and nurture it. The interface was developed based on the universal design philosophy, presenting itself attractive to children without disabilities, but also accessible to children with visual or motor disabilities. As such, we present a multimodal interface based on touch and speech commands. The game was tested in terms of usability, with a heuristic evaluation, and the results obtained highlight the potential of such interfaces.

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.