Abstract
Intelligent agriculture in general, but especially when agricultural fields are very heterogeneous, requires a large number of sensors in order to obtain an effective control and thus increase productivity. This need becomes more evident in vineyards on the farms of the demarcated Douro region due to the specificities of the territory and the vineyards themselves. Thus, it is necessary to have low cost sensors which are, essentially, easy to install and maintain. In the present work, a node with these characteristics was developed, which, in addition, is low consumption and communicates wirelessly through a Long Rang Wide Area Network (LoRaWAN) network. To obtain an easy installation, a library of clusters was created for the LoRaWAN network and dedicated to sensors used in agriculture, especially those using an asynchronous serial protocol for intelligent sensors. Three nodes were developed and tested with sensors used in agriculture to measure several environmental parameters (soil and air temperature; wind speed, gust and direction; soil water content, water tension and electrical conductivity; solar radiation; precipitation; atmospheric and vapor pressure; relative humidity; and lightning strikes count). The three nodes send data to a server through an existing gateway on the farm. The data are decoded and sent to an Internet-of-Things analytics platform where it is aggregated, viewed and analyzed. Samples of the data collected are presented. The developed nodes are of small dimensions (85x65x35mm), thus making them easy to handle and install. Energy consumption depends on the distance to the gateway, and the number and type of sensors connected to each node. In the implemented cases, the maximum consumption was approximate to 400 mu A. The development of a cluster based library makes the node plug-and-play. The developed nodes will be a great step forward for the use of wireless sensors in smart agriculture in Douro vineyards.

Abstract
Augmented Reality (AR) is a field of knowledge that emerged in the middle of the last century, and its use has been spreading because of its usefulness, but also because of mobile platforms, accessible to most users. AR characteristics are valued in several fields of human activity, and also in the field of Education and Training, being AR pointed out as useful to the learning process. In this paper we search and analyse surveys and reviews of AR. We present a AR’s definition, and we create a classification scheme of two dimensions for AR: the dimension of the fields of application of AR, and the dimension of the technologies of AR.

Abstract

Abstract
This paper highlights a new learning model that introduces a contextual dimension to the well-known Q-Learning algorithm. Through the identification of different contexts, the learning process is adapted accordingly, thus converging to enhanced results. The proposed learning model includes a simulated annealing (SA) process that accelerates the convergence process. The model is integrated in a multi-agent decision support system for electricity market players negotiations, enabling the experimentation of results using real electricity market data. © 2020 The authors and IOS Press.

Abstract
Directive-driven programming models, such as OpenMP, are one solution for exploring the potential parallelism when targeting multicore architectures. Although these approaches significantly help developers, code parallelization is still a non-trivial and time-consuming process, requiring parallel programming skills. Thus, many efforts have been made toward automatic parallelization of the existing sequential code. This article presents AutoPar-Clava, an OpenMP-based automatic parallelization compiler which: (1) statically detects parallelizable loops in C applications; (2) classifies variables used inside the target loop based on their access pattern; (3) supportsreductionclauses on scalar and array variables whenever it is applicable; and (4) generates a C OpenMP parallel code from the input sequential version. The effectiveness of AutoPar-Clava is evaluated by using the NAS and Polyhedral Benchmark suites and targeting a x86-based computing platform. The achieved results are very promising and compare favorably with closely related auto-parallelization compilers, such as Intel C/C++ Compiler (icc), ROSE, TRACO and CETUS.

Abstract
With the outstanding predictive performance of Convolutional Neural Networks on different tasks and their widespread use in real-world scenarios, it is essential to understand and trust these black-box models. While most of the literature focuses on post-model methods, we propose a novel in-model joint architecture, composed by an explainer and a classifier. This architecture outputs not only a class label, but also a visual explanation of such decision, without the need for additional labelled data to train the explainer besides the image class. The model is trained end-to-end, with the classifier taking as input an image and the explainer's resulting explanation, thus allowing for the classifier to focus on the relevant areas of such explanation. Moreover, this approach can be employed with any classifier, provided that the necessary connections to the explainer are made. We also propose a three-phase training process and two alternative custom loss functions that regularise the produced explanations and encourage desired properties, such as sparsity and spatial contiguity. The architecture was validated in two datasets (a subset of ImageNet and a cervical cancer dataset) and the obtained results show that it is able to produce meaningful image- and class-dependent visual explanations, without direct supervision, aligned with intuitive visual features associated with the data. Quantitative assessment of explanation quality was conducted through iterative perturbation of the input image according to the explanation heatmaps. The impact on classification performance is studied in terms of average function value and AOPC (Area Over the MoRF (Most Relevant First) Curve). For further evaluation, we propose POMPOM (Percentage of Meaningful Pixels Outside the Mask) as another measurable criteria of explanation goodness. These analyses showed that the proposed method outperformed state-of-the-art post-model methods, such as LRP (Layer-wise Relevance Propagation).