Abstract
With the increasing adoption of teledermatology, there is a need to improve the automatic organization of medical records, being dermatological image modality a key filter in this process. Although there has been considerable effort in the classification of medical imaging modalities, this has not been in the field of dermatology. Moreover, as various devices are used in teledermatological consultations, image acquisition conditions may differ. In this work, two models (VGG-16 and MobileNetV2) were used to classify dermatological images from the Portuguese National Health System according to their modality. Afterwards, four incremental learning strategies were applied to these models, namely naive, elastic weight consolidation, averaged gradient episodic memory, and experience replay, enabling their adaptation to new conditions while preserving previously acquired knowledge. The evaluation considered catastrophic forgetting, accuracy, and computational cost. The MobileNetV2 trained with the experience replay strategy, with 500 images in memory, achieved a global accuracy of 86.04% with only 0.0344 of forgetting, which is 6.98% less than the second-best strategy. Regarding efficiency, this strategy took 56 s per epoch longer than the baseline and required, on average, 4554 megabytes of RAM during training. Promising results were achieved, proving the effectiveness of the proposed approach.

Abstract
Considerable amounts of data are required for a deep learning model to generalize to unseen cases successfully. Furthermore, such data is often manually labeled, making its annotation process costly and time-consuming. We propose using unlabeled real-world data in conjunction with automatically labeled synthetic data, obtained from simulators, to surpass the increasing need for annotated data. By obtaining real counterparts of simulated samples using CycleGAN and subsequently performing fine-tuning with such samples, we manage to improve a vehicle part's detection system performance by 2.5%, compared to the baseline exclusively trained on simulated images. We explore adding a semantic consistency loss to CycleGAN by re-utilizing previous work's trained networks to regularize the conversion process. Moreover, the addition of a post-processing step, which we denominate global NMS, highlights our approach's effectiveness by better utilizing our detection model's predictions and ultimately improving the system's performance by 14.7%.

Abstract
The high incidence of cervical cancer in women has prompted the research of automatic screening methods. This work focuses on two of the steps present in such systems, more precisely, the identification of cervical lesions and their respective classification. The development of automatic methods for these tasks is associated with some shortcomings, such as acquiring sufficient and representative clinical data. These limitations are addressed through a hybrid pipeline based on a deep learning model (RetinaNet) for the detection of abnormal regions, combined with random forest and SVM classifiers for their categorization, and complemented by the use of domain knowledge in its design. Additionally, the nuclei in each detected region are segmented, providing a set of nuclei-specific features whose impact on the classification result is also studied. Each module is individually assessed in addition to the complete system, with the latter achieving a precision, recall and F1 score of 0.04, 0.20 and 0.07, respectively. Despite the low precision, the system demonstrates potential as an analysis support tool with the capability of increasing the overall sensitivity of the human examination process.

Abstract
The demand for cost-effective broadband wireless underwater communications has increased in the past few years, motivated by the video collection performed by Autonomous Underwater Vehicles (AUVs) in areas such as environmental monitoring and oil and gas industries. However, the current technological limitations make it hard to implement a viable broadband wireless communications system for transferring the large amounts of data collected. Existing underwater communications solutions, using wireless optical or Radio Frequency (RF), limit high definition wireless video transfer to distances up to tens of meters. In case of underwater acoustic communications, long ranges can be achieved, but the low bandwidth makes them unsuitable for video streaming, even for standard definition video.In this paper we propose a solution, named Underwater Adaptive and Reliable Video Streaming (UARVS), that offers a video streaming service built upon the GROW data muling approach. UARVS exploits the use of data mules - small and agile AUVs - that travel between two physical nodes, bringing the data from an underwater survey unit to a central station at the surface. To validate the solution, an experimental testbed was built using airtight PVC cylinders, on a freshwater tank. The experimental results obtained show that UARVS enables an adaptive and continuous flow of video, avoids butter underruns, and reacts to data mule losses and delays.

Abstract
Background: Trauma is a public health issue with a significant social and economic impact. However, national data on its characterization and the role of nursing in its management is still scarce. Objective: To assess the effectiveness of prehospital nursing interventions in stabilizing trauma victims provided by nurses of Immediate Life Support Ambulances in Portugal. Methodology: Observational, prospective, and descriptive-correlational study. Data were collected by nurses of the Immediate Life Support Ambulances in mainland Portugal, from 01/03/2019 to 30/04/2020, and the Azores, from 01/10/2019 to 30/04/2020. Trauma severity indices were assessed before and after the nursing interventions. Results: This study included 606 cases (79.4% blunt trauma; 40.8% road accidents) reported by 171 nurses. Nurses performed mostly interventions for hemodynamic support (88.9%) and non-pharma-cological pain control (90.6%) of trauma victims. The nursing interventions improved the Revised Trauma Score and the Shock Index (p<0.001). Conclusion: Prehospital nursing interventions improve trauma victims’ clinical status.

Abstract
Sap flow measurements of trees are today the most common method to determine evapotranspiration at the tree and the forest/crop canopy level. They provide independent measurements for flux comparisons and model validation. The most common approach to measure the sap flow is based on intrusive solutions with heaters and thermal sensors. This sap flow sensor technology is not very reliable for more than one season crop; it is intrusive and not adequate for low diameter trunk trees. The non-invasive methods comprise mostly Radio-frequency (RF) technologies, typically using satellite or air-born sources. This system can monitor large fields but cannot measure sap levels of a single plant (precision agriculture). This article studies the hypothesis to use of RF signals attenuation principle to detect variations in the quantity of water present in a single plant. This article presents a well-defined experience to measure water content in leaves, by means of high gains RF antennas, spectrometer, and a robotic arm. Moreover, a similar concept is studied with an off-the-shelf radar solution-for the automotive industry-to detect changes in the water presence in a single plant and leaf. The conclusions indicate a novel potential application of this technology to precision agriculture as the experiments data is directly related to the sap flow variations in plant.