Abstract
The buildings' energy consumption increasing requires solutions to improve their energy efficiency, thus reducing the electricity bill's associated costs. This paper aims to study the load profiles of a service building and its optimization to reduce the costs related to electricity consumption. The electrical load profiles are analyzed, and the electrical equipment and its consumption are characterized. Moreover, to increase energy efficiency and reduce energy costs, a renewable energy system based on photovoltaic panels is sized and integrated into the building. The analysis of the building's consumption profiles allowed the PV system's dimensioning to eliminate power peaks, enabling a reduction in the contracted power. The results demonstrate the effectiveness of the proposed solution, resulting in a reduction of the electricity bill.

Abstract
Falls, especially in the elderly, are one of the main factors of hospitalization. Time-consuming intervention can be fatal or cause irreversible damages to the victims. On the other hand, there is currently a significant amount of smart clothing equipped with various sensors, particularly gyroscopes and accelerometers, which can be used to detect accidents. The creation of a tool that automatically detects eventual falls allows helping the victims as soon as possible. This works focuses in the automatic fall detection from sensors signals using long short-term memory networks. To train and test this approach, the Sisfall dataset is used, which considers the simulation of 23 adults and 15 older people. These simulations are based on everyday activities and the falls that may result from their execution. The results indicate that the procedure provides an accuracy score of 97.1% on the test set.

Abstract
Congestive heart failure (CHF) is a severe condition that affects the pumping power of your cardiac muscle. In this work, long-term memory (LSTM) and Bidirectional LSTM (BiLSTM) networks were used to identify congestive heart failure human beings using datasets from the PhysioNET. Two approaches were adopted, the first considers beating signals directly to feed the LSTM networks, and the second one used features signals extracted from the beating signals. The BiLSTM considering features signals obtain the best results reaching an accuracy of 90%.

Abstract
A classifier using a Long Short-Term Memory (LSTM) network to identify human beings infected with Covid-19 is proposed in this work. This classifier has significant advantages over current testing methods: it is fast, contactless, and requires few monetary resources. The data considered for this study was extracted from the Coswara dataset using 140 individuals (70 healthy and 70 infected with Covid-19). This dataset contains respiratory signals, such as people counting numbers, coughing, or breathing. The classifier uses non-linear time sequence features extracted from the signals after a preprocessing stage. The classifier was able to discriminate whether a human is infected with Covid-19 with an accuracy of 92.1%, specificity of 85.7%, and sensitivity of 98.6% using 5-fold Cross-Validation. Based on the results obtained, the classifier can be used as an alternative for the Reverse Transcription Polymerase Chain Reaction (RT-PCR) tests.

Abstract
Nowadays, independent older people stay alone for long periods, which increases the risk of being seriously damaged after a fall without the quick attendance of medical services. Several smart clothing equipment was created to detect these falls using sensors such as accelerometers and gyroscopes, allowing a short intervention to the victims. This work considers the Sisfall database, where 23 adults and 15 older people performed several daily living simulations. The signals registered by three sensors were used to train a Long Short-Term Memory network and a Bi-Long Short-Term Memory network to detect everyday activities and falls. Several experiments were performed, where the BiLSTM model outperforms the LSTM model with a mean accuracy of 99.21% on the testing set.

Abstract
Alto Douro Wine Region is located in the Northeast of Portugal and is classified by UNESCO as a World Heritage Site. Snaked by the Douro River, the region has been producing wines for over 2000 years, with the world-famous Porto wine standing out. The vineyards, in that region, are built in a territory marked by steep slopes and the almost inexistence of flat land and water. The vineyards that cover the great slopes rise from the Douro River and form an immense terraced staircase. All these ingredients combined make the right key for exploring precision agriculture techniques. In this study, a preliminary approach allowing to perform terrace vineyards identification is presented. This is a key-enabling task towards the achievement of important goals such as production estimation and multi-temporal crop evaluation. The proposed methodology consists in the use of Convolutional Neural Networks (CNNs) to classify and segment the terrace vineyards, considering a high-resolution dataset acquired with remote sensing sensors mounted in unmanned aerial vehicles (UAVs).