Abstract
This work reports the first use of cork as substrate to produce 3-electrode electrochemical devices, which may be very important to conduct sustainable worldwide biochemical testing in point-of-care. It consists of laminated cork covered by a thin-film of an insulating resin and printed in a 3-electrode system format. Silver ink was used to print electrical tracks and the reference electrode, while carbon ink was used to print working and auxiliary electrodes. The analytical performance of the cork-based devices was and compared to other common supports, as PET and ceramics in the form of screen-printed electrodes (SPEs). The cork-based devices displayed higher current values and better reversibility features and were able to undergo stable modification with conductive nanomaterials. They were further applied to detect sulfadiazine (SDZ), an antibiotic of human use that is also an environmental contaminant, by modifying the working electrode with a molecularly imprinted polymer (MIP) layer obtained by electropolymerization of pyrrol. The results confirmed the ability of the MIP film to detect SDZ selectively and showed reproducible increasing current signals for increasing concentrations of SDZ, from 8.0 to 186.0 ?M. Direct comparison with commercial carbon SPEs showed greater sensitivity for the cork-based SPEs, with 10? lower limits of detection. Overall, cork-based devices are a valuable alternative to currently available SPEs systems, considering environment and cost features and also the analytical gains of this approach. These are especially important in times where a global biochemical testing became necessary for improved public health management.

Abstract
ABSTRACT: The modelling of agents in the simulation models and tools is of primary importance if the quality and the validity of the simulation outcomes are at stake. This is the first version of the report that deals with the representation of electricity market actors’ in the agent based models (ABMs) used in TradeRES project. With the AMIRIS, the EMLab-Generation (EMLab), the MASCEM and the RESTrade models being in the centre of the analysis, the subject matter of this report has been the identification of the actors’ characteristics that are already covered by the initial (with respect to the project) version of the models and the presentation of the foreseen modelling enhancements. For serving these goals, agent attributes and representation methods, as found in the literature of agent-driven models, are considered initially. The detailed review of such aspects offers the necessary background and supports the formation of a context that facilitates the mapping of actors’ characteristics to agent modelling approaches. Emphasis is given in several approaches and technics found in the literature for the development of a broader environment, on which part of the later analysis is deployed. Although the ABMs that are used in the project constitute an important part of the literature, they have not been included in the review since they are the subject of another section.

Abstract

Abstract
In this paper we propose and analyze a game theoretical model regarding the dynamical interaction between government fiscal policy choices toward innovation and training (I&T), firm's innovation, and worker's levels of training and education. We discuss four economic scenarios corresponding to strict pure Nash equilibria: the government and I&T poverty trap, the I&T poverty trap, the I&T high premium niche, and the I&T ideal growth. The main novelty of this model is to consider the government as one of the three interacting players in the game that also allow us to analyse the I&T mixed economic scenarios with a unique strictly mixed Nash equilibrium and with I&T evolutionary dynamical cycles.

Abstract
Photovoltaic (PV) as one of the most promising energy alternatives brings a set of serious challenges in the operation of the power systems including PV system protection. Accordingly, it has become even more vital to provide reliable protection for the PV generations. To this end, this paper proposes two-stage data-driven methods. In the first stage, a feature selection method, namely t-distributed stochastic neighbor embedding (t-SNE) is implemented to select the optimal features. Then, the output of t-SNE is directly fed into the strong data-driven classification algorithm, namely robust soft learning vector quantization (RSLVQ) to detect PV array fault and identify the fault types in the second stage. The proposed method is able to detect the two different line-to-line faults (in strings and out of strings) and open circuit fault and fault type considering partial shedding effects. The results have been discussed based on simulation results and have been demonstrated the high accuracy and reliability of the proposed two-stage method in detection and fault type identification based on confusion matrix values.

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%.