Abstract
In recent years, the way that machine learning is used has undergone a paradigm shift driven by distributed and collaborative learning. Several approaches have emerged to enable pervasive computing and distributed learning in ubiquitous Internet of Things (IoT) systems. Numerous decentralized strategies have been proposed to deal with the limitations of centralized learning, including privacy and latency due to sharing local data, while utilizing distributed computations as a promising substitute to centralized learning. However, such distributed learning schemes come with new security and privacy concerns that should be addressed. Thus, in this paper, we first provide an overview for the emerging paradigms developed for distributed learning. Then, we performed a comprehensive survey for the privacy and security challenges associated with distributed learning along with the presented solutions to overcome them. Furthermore, we highlight key challenges and open future research directions toward implementing more robust distributed systems.

Abstract
We report the use of a carboxylated pyrrolidine-fused chlorin (TCPC) as a fluorescent probe for the determination of glutathione (GSH) in 7.4 pH phosphate buffer. TCPC is a very stable, highly emissive molecule that has been easily obtained from meso-tetrakis(4-methoxycarbonylphenyl) porphyrin (TCPP) through a 1,3-dipolar cycloaddition approach. First, we describe the coordination of TCPC with Hg(II) ions and the corresponding spectral changes, mainly characterized by a strong quenching of the chlorin emission band. Then, the TCPC-Hg2+ complex exhibits a significant fluorescence turn-on in the presence of low concentrations of the target analyte GSH. The efficacy of the sensing molecule was tested by using different TCPC:Hg2+ concentration ratios (1:2, 1:5 and 1:10) that gave rise to sigmoidal response curves in all cases with modulating detection limits, being the lowest 40 nM. The experiments were carried out under physiological conditions and the selectivity of the system was demonstrated against a number of potential interferents, including cysteine. Furthermore, the TCPC macrocycle did not showed a significant fluorescent quenching in the presence of other metal ions.

Abstract
The main objective of this paper is to introduce a new language resource for some varieties of Portuguese - European, Brazilian, Mozambican, and Angolan - and for British English, called DRIPPS (Discourse Relations In Perfect Participial Sentences). The corpus DRIPPS comprises, at the moment, 993 adverbial perfect participial sentences annotated with Discourse Relations and with the following Discourse Relational Devices: connectors, ordering of the clauses, temporal relations, tenses, and aspectual types. Additionally, an application with a Graphical User Interface (GUI) has been developed not only to browse and manipulate the corpus but also to allow the activation of specific Discourse Relation constraints, thereby selecting specific cases from the data set that can be analyzed separately. Besides calculating simple counts and percentages, insightful statistical graphs can be generated and visualized on the fly from the combination of the user-selected constraints and the loaded corpora. The application is pre-loaded with Portuguese and English cases and allows to import/load further cases from different languages/ varieties.

Abstract
Pressure ulcers are skin injuries that develop mainly over bony areas as the result of prolonged pressure caused by the immobility of bedridden patients. They constitute not only a source of additional suffering for these patients but also contribute to the burnout of healthcare professionals who must maintain continuous monitoring of these patients. Data from countries such as the UK or the USA allows the cost of this problem to be estimated to be, respectively, near 2 pound billion and $80 billion. In this article, we describe the SensoMatt approach to pressure ulcer prevention and management, which is being developed as a research project that includes partners from industry, healthcare, and academia. The SensoMatt solution is centered on a pressure sheet that is placed under the patient's mattress, complemented by an online management portal and a mobile app. These provide patients and healthcare providers with an unparalleled set of services that include personalized analysis, prevention warnings and recommendations.

Abstract
In this study, we evaluated the use of small pre-trained 3D Convolutional Neural Networks (CNN) on land use and land cover (LULC) slide-window-based classification. We pre-trained the small models in a dataset with origin in the Eurosat dataset and evaluated the benefits of the transfer-learning plus fine-tuning for four different regions using Sentinel-2 L1C imagery (bands of 10 and 20m of spatial resolution), comparing the results to pre-trained models and trained from scratch. The models achieved an F1 Score of between 0.69-0.80 without significative change when pre-training the model. However, for small datasets, pre-training the model improved the classification by up to 3%.

Abstract
During a pandemic, public discussion and decision-making may be required in face of limited evidence. Data-grounded analysis can support decision-makers in such contexts, contributing to inform public policies. We present an empirical analysis method based on regression modelling and hypotheses testing to assess events for the possibility of occurrence of superspreading contagion with geographically heterogeneous impacts. We demonstrate the method by evaluating the case of the May 1st, 2020 Demonstration in Lisbon, Portugal, on regional growth patterns of COVID-19 cases. The methodology enabled concluding that the counties associated with the change in the growth pattern were those where likely means of travel to the demonstration were chartered buses or private cars, rather than subway or trains. Consequently, superspreading was likely due to travelling to/from the event, not from participating in it. The method is straightforward, prescribing systematic steps. Its application to events subject to media controversy enables extracting well founded conclusions, contributing to informed public discussion and decision-making, within a short time frame of the event occurring.