Abstract
In the recent past structural changes in the operation and topology of the electrical system have occurred. These changes have coincided with the emergence of distributed energy resources (DERs). Relating to supply side technologies, distributed generation (DG) units have become increasingly common. The demand side has also seen the growth of new technological applications, including electric vehicles (EVs). These changes to the electrical system are being especially felt at the low voltage network level. Technical Virtual Power Plants (TVPPs) have been used to optimally schedule these DERs to increase the network flexibility and at the same time increasing the reliability and power quality of the network and this can bring economic benefits to both the TVPP operator and the customer. This paper develops a stochastic mixed-integer linear programming (MILP) optimization model to maximize the profit of a TVPP. The main objective of the TVPP is to increase operational flexibility of the low voltage network by aggregating DERs, including DG units, Heating Ventilation and Air Conditioning units, and EVs. The model is examined through the use of the IEEE 119-Bus test system. Results demonstrate that the inclusion of DG units and EVs, the profit of the TVPP increases by approximately 45% and system flexibility is increased while respecting the technical constraints of the network and the thermal comfort of the consumers.

Abstract

Abstract
Yearly, the number of Distributed Energy Resources (DER) integrated into the power grid increases has increased, having a large impact on power generation globally, promoting the introduction of renewable energy resources (RER). To increase the flexibility of the power system with integrated RER, the introduction of energy storage systems (ESS) is essential. Demand response (DR) programs also help to increase grid flexibility, resulting in increased grid reliability as grid congestion and losses decrease. However, this new paradigm shift needs further research and careful analysis. In this work, two types of DR programs are addressed to promote greater participation by different consumers features. To interconnect the different consumers, DR aggregators are inserted to ensure that individual consumers have influence on the power market. All these aspects, if accompanied by information, measurement, communication, and control systems, give rise to the smart grids, playing an essential role. The results show, considering the worst uncertainty case scenario, that there is a suitable total RER of 2151.50 kW, against 3227.30 kW, by not considering the RER uncertainty.

Abstract
Several systemic diseases affect the retinal blood vessels, and thus, their assessment allows an accurate clinical diagnosis. This assessment entails the estimation of the arteriolar-to-venular ratio (AVR), a predictive biomarker of cerebral atrophy and cardiovascular events in adults. In this context, different automatic and semiautomatic image-based approaches for artery/vein (A/V) classification and AVR estimation have been proposed in the literature, to the point of having become a hot research topic in the last decades. Most of these approaches use a wide variety of image properties, often redundant and/or irrelevant, requiring a training process that limits their generalization ability when applied to other datasets. This paper presents a new automatic method for A/V classification that just uses the local contrast between blood vessels and their surrounding background, computes a graph that represents the vascular structure, and applies a multilevel thresholding to obtain a preliminary classification. Next, a novel graph propagation approach was developed to obtain the final A/V classification and to compute the AVR. Our approach has been tested on two public datasets (INSPIRE and DRIVE), obtaining high classification accuracy rates, especially in the main vessels, and AVR ratios very similar to those provided by human experts. Therefore, our fully automatic method provides the reliable results without any training step, which makes it suitable for use with different retinal image datasets and as part of any clinical routine.

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