Abstract
Recent studies have shown that the early detection of neurodegenerative diseases (such as Parkinson) can significantly improve the effectiveness of treatments that increase quality of life, reducing the costs associated with the disease. In this paper, the proposed methodology consists in detecting early signs of Parkinson's disease through speech, with the presence of background noise. The approach uses machine learning algorithms and signal processing techniques to correctly distinguish between healthy controls and Parkinson's disease patients. In order to detect early signs of the disease, a database with patients at different stages of the Parkinson's disease is used. The learning algorithms were optimized for generalization and accuracy. An analysis of the results obtained from the proposed methodology show potential uses of machine learning algorithms in biomedical applications to detect early signs of Parkinson's disease.

Abstract
Foreseen climate change points to shifts in agricultural production patterns worldwide, which may impact ecosystems directly, as well as the economic and cultural contexts of the wine industry. Moreover, the combined effects of environmental threats (light, temperature, and water relations) at different scales are expected to impair natural grapevine mechanisms, decreasing yield and the quality of grapes. Hence, the interaction between several factors, such as climate, terroir features, grapevine stress responses, site-specific spatial-temporal variability, and the management practices applied, which represents and effective challenge for sustainable Mediterranean viticulture, allowed researchers to develop adaptive strategies to cope with environmental stresses. Here, we review the effects of abiotic stresses on Mediterranean-like climate viticulture and the impacts of summer stress on grapevine growth, yield, and quality potential, as well as the subsequent plant responses and the available adaptation strategies for winegrowers and researchers. Our main findings are as follows: (1) environmental stresses can trigger dynamic responses in grapevines, comprising photosynthesis, phenology, hormonal balance, berry composition, and the antioxidant machinery; (2) field research methodologies, laboratory techniques, and precision viticulture are essential tools to evaluate grapevine performance and the potential quality for wine production; and (3) advances in the existing adaptation strategies are vital to maintain sustainability and regional wine identity in a changing climate. Also, these topics suggest that rational and focused management of grapevines may enlighten grapevine summer stress responses and improve the resilience of agro-ecosystems under harsh conditions. Despite the challenge of developing different strategic responses, winegrowers should clearly define their objectives, so applied research can provide rational technical support for the decision making process towards sustainable viticulture.

Abstract
The design of fluorescent molecules with structural features for efficient immobilization in polymeric supports or binding matrixes is an active research topic, which aims to create materials with optical and mechanical properties suitable for sensing applications. Herein, we describe the synthesis and characterization of two new fluorescent ligands prepared by a combination of a rosamine platform and an isophthalate receptor using amine and amide linkages. In order to evaluate their potential application as fluorescence sensors, the photophysical properties of the ligands were accessed by UV-Vis and photoluminescence measurements in solution and after immobilization (infiltrated in TiO2 thin films). Furthermore, molecular and electronic structures of both ligands were rationalized by DFT and TD-DFT calculations. Interesting features were found for the ligand containing an amide bond, which has shown to be less prone to aggregation and has higher emission capacity, being a promising candidate in fluorescence sensor devices.

Abstract
Two rosamine derivatives were used as fluorescent sensors for the detection of NO2, a toxic and oxidant gas whose presence in populated areas needs to be controlled. Both compounds shared the same molecular structure but had different peripheral substituents: a carboxylic acid and an amino group. Transparent nanocrystalline TiO2 films were prepared by screen printing and used as substrates, where the rosamines were incorporated by simple immersion into their respective solutions to form composite films. According to the molecular structures of the rosamines, the anchoring to the substrates was proposed to be by either covalent bonding and electrostatic interaction, or only electrostatic interaction, and was determined by the different substituents in each rosamine. Upon their exposure to increasing concentrations of NO2, both types of composite films showed intense and fast spectral changes, and the speed of response was related to the concentration of the gas. The anchoring mode and the electrophilic effect of the substituents determined the better sensing capability and the faster response shown by the carboxylic derivative in all cases.

Abstract
Teaching industrial robots by demonstration can significantly decrease the repurposing costs of assembly lines worldwide. To achieve this goal, the robot needs to detect and track each component with high accuracy. To speedup the initial object recognition phase, the learning system can gather information from assembly manuals in order to identify which parts and tools are required for assembling a new product (avoiding exhaustive search in a large model database) and if possible also extract the assembly order and spatial relation between them. This paper presents a detailed analysis of the fine tuning of the Stanford Named Entity Recognizer for this text tagging task. Starting from the recommended configuration, it was performed 91 tests targeting the main features / parameters. Each test only changed a single parameter in relation to the recommend configuration, and its goal was to see the impact of the new configuration in the precision, recall and F1 metrics. This analysis allowed to fine tune the Stanford NER system, achieving a precision of 89.91%, recall of 83.51% and F1 of 84.69%. These results were retrieved with our new manually annotated dataset containing text with assembly operations for alternators, gearboxes and engines, which were written in a language discourse that ranges from professional to informal. The dataset can also be used to evaluate other information extraction and computer vision systems, since most assembly operations have pictures and diagrams showing the necessary product parts, their assembly order and relative spatial disposition.

Abstract
Interest in robotics field as a teaching tool to promote the STEM areas has grown in the past years. The search for solutions to promote robotics is a major challenge and the use of real robots always increases costs. An alternative is the use of a simulator. The construction of a simulator related with the Portuguese Autonomous Driving Competition using Gazebo as 3D simulator and ROS as a middleware connection to promote, attract, and enthusiasm university students to the mobile robotics challenges is presented. It is intended to take advantage of a competitive mindset to overcome some obstacles that appear to students when designing a real system. The proposed simulator focus on the autonomous driving competition task, such as semaphore recognition, localization, and motion control. An evaluation of the simulator is also performed, leading to an absolute error of 5.11% and a relative error of 2.76% on best case scenarios relating to the odometry tests, an accuracy of 99.37% regarding to the semaphore recognition tests, and an average error of 1.8 pixels for the FOV tests performed.