Abstract
Forests worldwide have been devastated by fires. Forest fires cause incalculable damage to fauna and flora. In addition, a forest fire can lead to the death of people and financial damage in general, among other problems. To avoid wildfire catastrophes is fundamental to detect fire ignitions in the early stages, which can be achieved by monitoring ignitions through sensors. This work presents an integer programming approach to decide where to locate such sensors to maximize the coverage provided by them, taking into account different types of sensors, fire hazards, and technological and budget constraints. We tested the proposed approach in a real-world forest with around 7500 locations to be covered and about 1500 potential locations for sensors, showing that it allows obtaining optimal solutions in less than 20 min. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Agriculture work is physically demanding and the sector workers have a high incidence of musculoskeletal disorders. The shift to Agriculture 5.0 and the advancement of precision agriculture have involved the digitalization of this industry, but tend to marginalise the workers, though they are still essential to more thorough tasks that cannot be automated. In order to tackle the necessity to support the monitoring of agriculture workers, we developed quantification algorithms, incorporated in a mobile application, which calculate metrics based on the signals gathered by wearable sensors. Our proximity to the Douro region lead us to focus on metrics that could be more meaningful for viniculture, namely the quantification of trunk inclinations and shear cuts, very common in this production. The developed algorithms showed an error of 1.36 degrees for the calculus of inclination and 2.43 cuts for the prediction of cuts when tested with on-field data. These results suggest that the created system has the viability to be used by agricultures and give reliable feedback on their workers.

Abstract
Nowadays, social media are inevitably part of people's daily lives. Thus, political communication should also go through digital communication channels, particularly on social media. In such channels, it is important to define a digital marketing and communication strategy to attract new voters and consecutively more votes. As in offline communication channels and also in digital communication, one of the indispensable points in political communication is the candidate’s image. This image must show its own style and differentiate the candidate from his opponents. The main objective of this study is to understand the influence of social media on Portuguese voters’ decision-making process. Throughout the study, different research questions were also analyzed to access which social media are the most used to follow the online political campaign and which criteria influence the voting decision-making process. To achieve this purpose, exploratory research was carried out through questionnaire surveys. Three surveys were conducted based on the Portuguese presidential elections of January 24, 2021. The surveys were distributed before, during, and after the end of the electoral campaign, and 106 people were questioned and answered all 3 surveys. With the results of this study, it was possible to conclude that only 11% of respondents changed their voting intention due to the political communication made by political parties on social media during this electoral campaign. The social media most used by respondents was Facebook, which is also the one they consider the safest and most trustworthy to follow political communication in online media.

Abstract
This study examined the determinants of purchase intention of green cosmetics, and eight semi-structured interviews were performed to identify them. The determinants identified were environmental awareness, lifestyle, willingness to pay, ethical issues and social and economic justice, cosmetic quality, concern with health, certification labels, trust in the brand, and advertising. Environmental awareness, lifestyle, willingness to pay, quality issues, ethics, and social and economic justice, as well as quality expectations, health concerns, and product knowledge, are the most significant determinants in the intention to purchase green cosmetics. Determinants such as certification labels, brand trust, and advertising are less significant. The research is relevant for the cosmetics industry and its brands to adapt their strategy and product offering to meet consumers’ needs and increase the consumption of green cosmetics and can also serve as a basis for the development of new quantitative studies on the purchase intention of green cosmetics. © 2023 by IGI Global.

Abstract
Federated learning (FL) demonstrates its advantages in integrating distributed infrastructure, communication, computing and learning in a privacy-preserving manner. However, the robustness and capabilities of existing FL methods are challenged by limited and dynamic data and conditions, complexities including heterogeneities and uncertainties, and analytical explainability. Bayesian federated learning (BFL) has emerged as a promising approach to address these issues. This survey presents a critical overview of BFL, including its basic concepts, its relations to Bayesian learning in the context of FL, and a taxonomy of BFL from both Bayesian and federated perspectives. We categorize and discuss client- and server-side and FLbased BFL methods and their pros and cons. The limitations of the existing BFL methods and the future directions of BFL research further address the intricate requirements of real-life FL applications.

Abstract
This paper introduces a tomography-like method for assessing grape maturation. It analyses inner tissue spectra through point-of-measurement (POM) sensing. A multi-block hierarchical principal component analysis (MHPCA) algorithm was used for the spectral reconstruction of total grapes (skin, pulp, and seed). Two grape cultivars, Loureiro (white; n = 216) and Vinhao (red; n = 205) were measured at 12 dates after veraison (DAV). The reconstructed spectra showed no significant differences (p < 0.001) from the originals for both grapes. Loureiro had better statistical metrics (Person's correlation coefficient (r) values for: total grape: 0.99, skin: 1; pulp: 1, seed: 0.94) than Vinhao (r values for: total grape: 0.92, skin: 0.92; pulp: 0.95, seed: 0.95). Using self learning artificial intelligence (SL-AI), the following parameters were predicted for both grapes: soluble solids content (%; MAPE <13%), puncture force (N; MAPE <29%), chlorophyll content (a.u.; MAPE <29%), and anthocyanin content (a.u.; MAPE <17%, Vinhao only). When comparing observed values with predicted skin, pulp, and seed spectra, Vinhao showed no statistical differences for most parameters, except pulp chlorophyll on one DAV in the final maturation stage. The same was done with the Loureiro cultivar. Although Loureiro mostly showed no statistical differences in assessed parameters across tissues and dates, variations were found in pulp and skin chlorophyll content and puncture force. This tomography-like approach based on tissue maturation can help viticulturists to access instant data on grape maturation, supporting informed decision-making and promoting more sustainable agricultural practices.