Abstract
Natural gas (NG) is commonly used in kitchens, powering stoves, ovens, and other appliances. While it is known for its efficiency and convenience, NG contributes to the release of nitrogen dioxide (NO2) and can have significant implications for human health. In this study, the importance of the use of NG in kitchens on human exposure to NO2 was analyzed. An extensive literature review in the field was conducted, and the NO2 levels were assessed in kitchens with NG cookers in Aveiro and electric cookers in Porto, both in Portugal. Higher levels of NO2 were found in kitchens in Aveiro, where NO2 levels outdoors are lower than in Porto. This pollutant can spread to other rooms, especially when ventilation is lacking, which is particularly concerning during colder seasons and at night. As around 70% of the time is spent at home, this can have a significant impact on human exposure to NO2. Therefore, although Aveiro has low levels of NO2 outdoors, its population may be exposed to much higher levels of this pollutant than the Porto population, a city with air quality issues, but predominantly using electric cookers. This finding emphasizes the need for the stricter regulation of NG use indoors to protect human health and also suggests a shift in human health protection policies from mere monitoring/control of outdoor air quality to a comprehensive assessment of human exposure, including exposure to indoor air quality.

Abstract
Coffee capsules have gained high levels of popularity in the last decades due to their convenience of use, flavour choices, and consistent extraction quality. As governmental bodies are promoting more circular solutions for packaging products, concerns have been raised regarding the environmental impacts of single-use coffee capsules, namely their end-of-life treatment and effective recyclability. This paper presents a novel design based on thin steel sheet material application for new packaging solutions that can support a more circular economy. To validate this new design, a framework was presented for a cross-assessment of Life Cycle Assessment with Circularity Analysis to compare the new tinplate capsule with conventional polypropylene and aluminium capsules. The novel design is more circular (0.97 in the material circularity indicator), in comparison with the polypropylene (0.1) and aluminium (0.80) conventional capsules, due to the ferromagnetic properties that allow for better effectiveness during sorting in urban packaging recycling facilities. As for the environmental assessment, the tinplate has higher environmental impacts than the aluminium and the polypropylene capsules (more 63 % and more 92 %, respectively) due to the high energy intensity processes required to produce this material. These results demonstrate that the novel tinplate capsule should complement the strong results in circularity with further improvements in its environmental performance, namely by the transition of the steel industry to the upcoming generation of decarbonized steel production.

Abstract
After the learning process, certain types of images may not be modeled correctly because they were not well represented in the training set. These failures can then be compensated for by collecting more images from the real-world and incorporating them into the learning process - an expensive process known as active learning. The proposed twist, called active supervision, uses the model itself to change the existing images in the direction where the boundary is less defined and requests feedback from the user on how the new image should be labeled. Experiments in the context of class imbalance show the technique is able to increase model performance in rare classes. Active human supervision helps provide crucial information to the model during training that the training set lacks.

Abstract
Spectral point-of-care technology is reagentless with minimal sampling (<10 mu L) and can be performed in real-time. White blood cells are non-dominant in blood and in spectral information, suffering significant interferences from dominant constituents such as red blood cells, hemoglobin and billirubin. White blood cells of a bigger size can account for 0.5% to 22.5% of blood spectra information. Knowledge expansion was performed using data augmentation through the hybridization of 94 real-world blood samples into 300 synthetic data samples. Synthetic data samples are representative of real-world data, expanding the detailed spectral information through sample hybridization, allowing us to unscramble the spectral white blood cell information from spectra, with correlations of 0.7975 to 0.8397 and a mean absolute error of 32.25% to 34.13%; furthermore, we achieved a diagnostic efficiency between 83% and 100% inside the reference interval (5.5 to 19.5 x 10(9) cell/L), and 85.11% for cases with extreme high white blood cell counts. At the covariance mode level, white blood cells are quantified using orthogonal information on red blood cells, maximizing sensitivity and specificity towards white blood cells, and avoiding the use of non-specific natural correlations present in the dataset; thus, the specifity of white blood cells spectral information is increased. The presented research is a step towards high-specificity, reagentless, miniaturized spectral point-of-care hematology technology for Veterinary Medicine.

Abstract
The early and accurate diagnosis of brain tumors is critical for effective treatment planning, with Magnetic Resonance Imaging (MRI) serving as a key tool in the non-invasive examination of such conditions. Despite the advancements in Computer-Aided Diagnosis (CADx) systems powered by deep learning, the challenge of accurately classifying brain tumors from MRI scans persists due to the high variability of tumor appearances and the subtlety of early-stage manifestations. This work introduces a novel adaptation of the EfficientNetv2 architecture, enhanced with Global Attention Mechanism (GAM) and Efficient Channel Attention (ECA), aimed at overcoming these hurdles. This enhancement not only amplifies the model's ability to focus on salient features within complex MRI images but also significantly improves the classification accuracy of brain tumors. Our approach distinguishes itself by meticulously integrating attention mechanisms that systematically enhance feature extraction, thereby achieving superior performance in detecting a broad spectrum of brain tumors. Demonstrated through extensive experiments on a large public dataset, our model achieves an exceptional high-test accuracy of 99.76%, setting a new benchmark in MRI-based brain tumor classification. Moreover, the incorporation of Grad-CAM visualization techniques sheds light on the model's decision-making process, offering transparent and interpretable insights that are invaluable for clinical assessment. By addressing the limitations inherent in previous models, this study not only advances the field of medical imaging analysis but also highlights the pivotal role of attention mechanisms in enhancing the interpretability and accuracy of deep learning models for brain tumor diagnosis. This research sets the stage for advanced CADx systems, enhancing patient care and treatment outcomes.

Abstract
Accurate localization in autonomous robots enables effective decision-making within their operating environment. Various methods have been developed to address this challenge, encompassing traditional techniques, fiducial marker utilization, and machine learning approaches. This work proposes a deep-learning solution employing Convolutional Neural Networks (CNN) to tackle the localization problem, specifically in the context of the RobotAtFactory 4.0 competition. The proposed approach leverages transfer learning from the pre-trained VGG16 model to capitalize on its existing knowledge. To validate the effectiveness of the approach, a simulated scenario was employed. The experimental results demonstrated an error within the millimeter scale and rapid response times in milliseconds. Notably, the presented approach offers several advantages, including a consistent model size regardless of the number of training images utilized and the elimination of the need to know the absolute positions of the fiducial markers.