Abstract
Spectral information is characterized by multi-scaled interference, convolution and variability. Spectral lines are fragmented and diffused along the spectra. In many cases, matrix and physical effects do not allow to determine specific bands. Despite this limitation, the observed spectra contains significant amounts of information about the sample composition and characteristics, which once understood, can make spectroscopy an ideal technology for analyzing complex samples, such as bodyfluids and tissues. Breaking down and deciphering the structure of spectral information is paramount for the development of reagent-free point-of-care devices. A self-learning artificial intelligence was developed to take advantage of spectral complex information structure. It determines the relationships between composition and/or spectral features in high-dimensional space, where different sub-spaces correlate to specific constituents or characteristics. It also establishes a knowledgebase, by feature space transformations and optimizing co-variance search direction under the correct 'matrix effect' context. An example of hemogram analysis with erythrocyte and leucocyte counts is presented to demonstrate the advantages of the developed methodology.

Abstract
This paper describes the implementation of an end-to-end Internet of Things (IoT) solution, focusing specifically in the multi-protocol sensor node with LoRaWAN and Wi-Fi connectivity options (Pycom's FiPy). A performance assessment will be presented, addressing a comparison between the different protocols (LoRaWAN vs. Wi-Fi) in terms radio coverage, timing issues, among others. Further, it will be investigated the integration onto the sensor node of sensor/actuator circuit blocks for energy metering, supported on Microchip's ATM90E26 single-phase meter. This will provide a practical use case in the field of Industry 4.0, leading to preliminary insights for power quality monitoring. © 2019 IEEE.

Abstract
Reinforcement learning techniques bring a new perspective to enduring problems. Developing skills from scratch is not only appealing due to the artificial creation of knowledge. It can also replace years of work and refinement in a matter of hours. From all the developed skills in the RoboCup 3D Soccer Simulation League, running is still considerably relevant to determine the winner of any match. However, current approaches do not make full use of the robotic soccer agents’ potential. To narrow this gap, we propose a way of leveraging the Proximal Policy Optimization using the information provided by the simulator for official RoboCup matches. To do this, our algorithm uses a mix of raw, computed and internally generated data. The final result is a sprinting and a stopping behavior that work in tandem to bring the agent from point a to point b in a very short time. The sprinting speed stabilizes at around 2.5 m/s, which is a great improvement over current solutions. Both the sprinting and stopping behaviors are remarkably stable. © 2019, Springer Nature Switzerland AG.

Abstract
Pressurised networks are widely used to transport gas through extensive distances. To secure the gas transport at safety levels and also economic viability, the networks are thoroughly monitored. Paramount to network control and analysis is the modelling of the gas dynamics in the pipelines and its consequent simulation. In this work, the pipeline is represented by a quasi-hyperbolic PDE, whose exact solution is not easy to withdraw, and in alternative we opt for an approximation. The construction of the initial function, very important to obtain a good approximation, is done using a separation of variables. Special relevance is given to issues as consistency, stability and convergence in order to evaluate a class of FD methods for the solution of gas network models, in particular the quasi-hyperbolic equation. Horizontal pipelines are considered as well as some particular centred schema for an inclined pipeline.

Abstract
The main objective of this paper is to present a new and cost-effective Information and Communication Technology (ICT) tool that can lead to efficient energy management in buildings and optimal operation of electricity networks with increased share of Renewable Energy Sources (RES) and Electric Vehicles (EVs). The new ICT infrastructure is based on the Digital Audio Broadcasting (DAB) standard and its interoperability with smart metering technology, Intelligent Transportation Systems (ITS) and Building Automation Systems (BAS). The main idea involves the attachment of a DAB receiver to electric devices (from small household appliances up to EVs and solar systems and other RES). In this paper, the DAB protocol is described, enabling high cyber-physical security. Moreover, the results of addressing a thermostatically-controlled load using DAB-signaling in Switzerland are also presented. The next steps envisioned are i) the validation of the final protocol version and of the DAB receivers for various electric appliances and DR schemes and, ii) demonstration of the new technology in real-life cases through the National DAB broadcaster in Greece. (C) 2019 The Authors. Published by Elsevier Ltd.

Abstract
Wi-Fi networks lack energy consumption management mechanisms. In particular, during nighttime periods, the energy waste may be significant, since all Access Points (APs) are kept switched on even though there is minimum or null traffic demand. The fact that more than 80% of all wireless traffic is originated or terminated indoor, and served by WiFi, has led the scientific community to look into energy saving mechanisms forWi-Fi networks. State of the art solutions address the problem by switching APs on and off based on manually inserted schedules or by analyzing real-time traffic demand. The first are vendor specific; the second may induce frequent station (STA) handoffs, which has an impact on network performance. The lack of implementability of solutions is also a shortcoming in most works. We propose an algorithm, named Energy Consumption Management Algorithm (ECMA), that learns the daytime and nighttime periods of the Wi-Fi network. ECMA was designed having in mind its implementability over legacyWi-Fi equipment. At daytime, the radio interfaces of the AP (2.4 GHz and 5 GHz) are switched on and off automatically, according to the traffic demand. At nighttime, clusters of APs, covering the same area, are formed, leaving one AP always switched on for basic coverage and the redundant APs swichted off to maximize energy savings, while avoiding coverage and performance hampering. Simulation results show energy savings of up to 50% are possible using the ECMA algorithm.