Abstract
Recycling of post-consumer wood waste into wood-based panels may be hindered by the presence of physical and chemical impurities in the waste stream. Therefore greater attention should be given to assessing the quality of wood waste and in particular to heavy metals contamination. One of the elements that poses concern is Chromium (Cr). Cr compounds can be toxic, particularly hexavalent chromium (Cr(VI)), which is a known human carcinogen. Hence, screening for Cr in wood waste plays a pivotal role in enhancing recycling facility operations and mitigating contamination before final product incorporation. In this study, a Laser-Induced Breakdown Spectroscopy (LIBS) methodology was optimized for screening wood waste for Cr and validated by X-ray Fluorescence (XRF) measurements. LIBS spectral complexity and sample matrix effects challenges were addressed through careful selection of Cr lines and tailored data analysis algorithms. The results showed that LIBS imaging successfully provided a straightforward timely output revealing the contaminated wood samples, crucial for quick decision-making in production lines.

Abstract
Local electricity markets are emerging as a viable solution to overcome the challenges brought by the large penetration of distributed renewable generation and the need to put consumers as central players in the system, with an active and dynamic role. Although there is significant literature addressing the topic of local electricity markets, this is still a rather new and emerging topic. Hence, this study provides an overall view of this domain and a perspective on future needs and challenges that must be addressed. This review introduces the most important concepts in the local electricity market domain, provides an analysis on the different policy and regulatory framework, exposes the most relevant worldwide initiatives related to the field implementation, and scrutinizes the alternative local market models proposed in the literature. The discussion puts forth the main benefits and barriers of the currently proposed local market models, and the expected impact of their widespread implementation. The review is concluded with the wrap-up and discussion on the most relevant paths for future research and development in this field of study.

Abstract
People are living longer, promoting new challenges in healthcare. Many older adults prefer to age in their own homes rather than in healthcare institutions. Portugal has seen a similar trend, and public and private home care solutions have been developed. However, age-related pathologies can affect an elderly person's ability to perform daily tasks independently. Ambient Assisted Living (AAL) is a domain that uses information and communication technologies to improve the quality of life of older adults. AI-based fall detection systems have been integrated into AAL studies, and posture estimation tools are important for monitoring patients. In this study, the OpenCV and the YOLOv7 machine learning framework are used to develop a fall detection system based on posture analysis. To protect patient privacy, the use of a thermal camera is proposed to prevent facial recognition. The developed system was applied and validated in the real scenario.

Abstract
Chest X-ray scans are frequently requested to detect the presence of abnormalities, due to their low-cost and non-invasive nature. The interpretation of these images can be automated to prioritize more urgent exams through deep learning models, but the presence of image artifacts, e.g. lettering, often generates a harmful bias in the classifiers and an increase of false positive results. Consequently, healthcare would benefit from a system that selects the thoracic region of interest prior to deciding whether an image is possibly pathologic. The current work tackles this binary classification exercise, in which an image is either normal or abnormal, using an attention-driven and spatially unsupervised Spatial Transformer Network (STERN), that takes advantage of a novel domain-specific loss to better frame the region of interest. Unlike the state of the art, in which this type of networks is usually employed for image alignment, this work proposes a spatial transformer module that is used specifically for attention, as an alternative to the standard object detection models that typically precede the classifier to crop out the region of interest. In sum, the proposed end-to-end architecture dynamically scales and aligns the input images to maximize the classifier's performance, by selecting the thorax with translation and non-isotropic scaling transformations, and thus eliminating artifacts. Additionally, this paper provides an extensive and objective analysis of the selected regions of interest, by proposing a set of mathematical evaluation metrics. The results indicate that the STERN achieves similar results to using YOLO-cropped images, with reduced computational cost and without the need for localization labels. More specifically, the system is able to distinguish abnormal frontal images from the CheXpert dataset, with a mean AUC of 85.67% -a 2.55% improvement vs. the 0.98% improvement achieved by the YOLO-based counterpart in comparison to a standard baseline classifier. At the same time, the STERN approach requires less than 2/3 of the training parameters, while increasing the inference time per batch in less than 2 ms. Code available via GitHub.

Abstract
The present chapter scrutinises invariable question tags in British English and European Portuguese from a contrastive point of view. Most previous research focuses on variable question tags and, if contrastive, compares other languages. This study shows that invariable question tags are more frequent and varied in European Portuguese than in British English. Furthermore, the results reveal that, while some invariable question tags appear across the two languages, others are registered only in one of them, despite the existence of equivalent expressions in the other. Additional asymmetries emerge concerning linguistic features of invariable question tags across the two languages. Based on the significant correlations between invariable question tags and their features, a model of predicted associations is put forward. © The Editor(s) (ifapplicable) and The Author (s),under exclusive license to Springer Nature Switzerland AG 2024.

Abstract
This research presents an anomaly detection algorithm for a Vanadium Redox Flow Battery (VRFB) using battery dataset as an example. The algorithm determines the anomaly detection threshold by fitting a Gaussian mixed model (GMM) to an anomaly-free dataset and testing it against a dataset containing only anomalies. By forcing the test dataset to classify all observations as anomalies, the threshold can be found. Applying again the model to the training dataset, classifies 11% of normal observations as failures, indicating that, not all observations were captured by the GMM, resulting in false positives. A percentage based on the likelihood values is suggested for replication to other systems, and a ratio of anomaly detection over time is proposed for preventive maintenance alerts.