Abstract
The study explores the technical optimization of an athlete through the use of intelligent system performance metrics that produce information obtained from inertial sensors associated to the coach's technical qualifications in real time, using Mixed Methods and Machine Learning. The purpose of this study is to illustrate, from the confusion matrices, the different performance metrics that provide information of high pertinence for the sports training in context. 2000 technical fencing actions with two levels of complexity were performed, captured through a single sensor applied in the armed hand and, simultaneously, the gesture’s qualification through a dichotomous way by the coach. The signals were divided into segments through Dynamic Time Warping, with the resulting extracted characteristics and qualitative assessments being fed to a Neural Network to learn the patterns inherent to a good or poor execution. The performance analysis of the resulting models returned a prediction accuracy of 76.6% and 72.7% for each exercise, but other metrics indicate the existence of high bias in the data. The study demonstrates the potential of intelligent algorithms to uncover trends not captured by other statistical methods. © Edições Desafio Singular.

Abstract
This paper describes the implementation of a simulated bioinspired 3D model, which was moved through segmented gestures using fractional calculation segmentation methods. It was observed that for the increase in the detection of such gestures from this segmentation an improvement in the recognition and standardization of gesture images using the FODPSO method would be obtained. We used the AlexNet neural network for training and recognition of the processed gestures, which resulted in a simulated 3D model of a spider moved by gestures recognized through a webcam, which had an accuracy of approximately 98% recognition through the neural network.

Abstract
Aging of Tawny Port wine is a multifactorial process critical for attaining the desired quality. Real time monitoring of important intrinsic and extrinsic factors that are known to affect the time and quality of the aging process are important to optimize and to manage the natural variability between wines aged in different long used wood barrels. For this study, a distributed monitoring system was installed in sixteen oak barrels, placed in two adjacent wineries - one of them with controlled temperature in the Douro Demarcated Region, Portugal. The monitoring process was performed using a RS-485 industrial network, which interconnects sensors that continuously measure wine temperature, pH, redox potential and wine's dissolved oxygen, as well as other sensors that measure parameters related to the barrels' environmental context, such as room temperature and relative humidity. This work presents the design, development and implementation of a remote distributed system to monitor such parameters, aiming to determine the existence of behaviour models for Port Tawny wine during aging in long-used oak barrels, depending on their storage history and to understand the evolution of wine pH, dissolved oxygen and redox potential in real winery conditions as well as their dependence on the wine's storage temperature. This approach is based on easy-to-use embedded systems, with the aim of giving a relevant contribution to other projects in the area of precision enology.

Abstract
The influence of the massive wall material, thickness and ventilation system on the Trombe wall thermal performance was analysed based on an analytical methodology. Results obtained from experimental work will also be added to this study. During the heating season, for the non-ventilated Trombe wall, the global heat gains decrease is not proportional to the thickness increase, and this ratio depends on the massive wall material heat storage capacity. A ventilation system in the massive wall leads to higher heat gains due to the air convection, but this growth is not in the same proportion for the different materials. If solid brick or earth is used, heat gain values are much higher than those obtained if there is no ventilation system, increasing to the double in the case of earth and 2.5 times more in the case of solid brick. When the massive wall is ventilated and made of granite, an increase in the gains of 44.06% is obtained when compared with the non-ventilated. During the cooling season, closing the ventilation system and the external shutter leads to heat gains considerably lower than those obtained during the heating season. In this case, earth can be a suitable material.

Abstract
The role of digital technologies for fostering sustainability and efficiency in forest-based supply chains is well acknowledged and motivated several studies in the scope of precision forestry. Sensor technologies can collect relevant data in forest-based supply chains, comprising all activities from within forests and the production of the woody raw material to its transformation into marketable forest-based products. Advanced planning systems can help to support decisions of the various entities in the supply chain, e.g., forest owners, harvest companies, haulage companies, and forest product processing industry. Such tools can help to deal with the complex interdependencies between different entities, often with opposing objectives and actions-which may increase efficiency of forest-based supply chains. This paper analyzes contemporary literature dealing with digital technologies in forest-based supply chains and summarizes the state-of-the-art digital technologies for real-time data collection on forests, product flows, and forest operations, as well as planning systems and other decision support systems in use by supply chain actors. Higher sustainability and efficiency of forest-based supply chains require a seamless information flow to foster integrated planning of the activities over the supply chainthereby facilitating seamless data exchange between the supply chain entities and foster new forms of collaboration. Therefore, this paper deals with data exchange and multi-entity collaboration aspects in combination with interoperability challenges related with the integration among multiple process data collection tools and advanced planning systems. Finally, this interdisciplinary review leads to the discussion of relevant guidelines that can guide future research and integration projects in this domain.

Abstract
This work presents the state-of-the-art of visual sensing systems for monitoring and control purposes in both agriculture and forest areas. Regarding agricultural activities, four main topics are explored: robotics and autonomous vehicles, plant protection, feature extraction and yield prediction. Although vast literature can be found on image processing and computer vision applied to agriculture, its applications in forest-based systems are less frequent. Throughout this article, several research areas such as diseases control, post-processing, parameters estimation, UAVs and satellites will be addressed.