Abstract
Machine learning processes consist in collecting data, obtaining a model and applying it to a given task. Given a new task, the standard approach is to restart the learning process and obtain a new model. However, previous learning experience can be exploited to assist the new learning process. The two most studied approaches for this are meta-learning and transfer learning. Metalearning can be used for selecting the predictive model to use on a new dataset. Transfer learning allows the reuse of knowledge from previous tasks. However, when multiple heterogeneous tasks are available as potential sources for transfer, the question is which one to use. One approach to address this problem is metalearning. In this paper we investigate the feasibility of this approach. We propose a method to transfer weights from a source trained neural network to initialize a network that models a potentially very different target dataset. Our experiments with 14 datasets indicate that this method enables faster convergence without significant difference in accuracy provided that the source task is adequately chosen. This means that there is potential for applying metalearning to support transfer between heterogeneous datasets.

Abstract
A wine forecast model for one of the most arid wine regions of the Europe-Alentejo was improved and tested for the period 1998-2014. During this period, Alentejo region had strong upward trends in wine production associated to the increase of vineyard area. The forecast model was supported on a hierarchical analysis, including the determination of the potential production at flowering by quantifying airborne pollen concentration, followed by a climate based evaluation of the possible impact of fruit-set conditions in the limitation of production. Through the monitoring of airborne pollen flows it is possible to define an accurate main pollen season and determine the regional pollen index that will be used as independent variable in the regional forecast model. The time trend, which was initially removed from data, was then added back to obtain the forecast. Stepwise regression and cross-validation were employed during the period 1998-2014 for calibration of the model used for predicting annual wine production. The developed model explained about 86% of wine variance over the years with absolute average error of 6% for the cross validation and 87% of cases had differences between actual and forecasted wine production below 10%. The reliability and early-indication ability of the proposed forecast model justify their use to respond to a number of government agencies and wine industry concerns and activities.

Abstract
The present research work presents an experimental campaign of ambient vibration tests performed on twenty infill masonry walls from two buildings under construction and from another existent building. The main objective is to evaluate the influence of the boundary conditions, geometric dimensions, presence of openings with different dimensions as well as the existence of grooves along the wall for the installation of electrical cables, in the out-of-plane main frequencies of the infill walls tested. In the paper, it is presented a detailed description of the studied buildings, testing setups, equipment used, and further information regarding the walls tested. The main test results are presented and discussed.

Abstract
The FlexOffer (FO) concept was initially created within the EU FP7 project MIRABEL [1]. It permits exposing demand and supply loads with associated flexibilities in time and quantity for energy commerce, load levelling, and different use-cases. To put it in a simple way, a FO specifies an amount of energy, a duration, an earliest begin time, a latest finish time, and a price, e.g., "I want 50 KWh over 3 hours between 5 PM and 12 PM, for a value of 0.25 €/kWh".

Abstract
Eyesight is an important sense that helps humans to avoid dangers and navigate in our world. Blind people usually have enhanced accuracy and sensibility of their other natural senses in order to sense their surroundings. But sometimes this is not enough because the human senses can be affected by external sources of noise or disease. That is why technology has been used to develop many assistive tools. Artifacts like white canes or braille compasses help blind people moving around in the environment. In this article, the use of a system that detects and recognize nearby objects or obstacles is proposed, giving an audible feedback to the user. It is designed as a wireless system in order to be comfortable to be carried by the user. The system helps visual impaired people to move around in indoor or outdoor scenarios. The goals of this blind guide system is to detect obstacles that white canes or dogs cannot, extending its detection range. © 2016 ACM.

Abstract
The emergence of complex supply chains is one of the most important consequences of globalization. The management of these supply chains requires increased efforts by organizations that, on one hand, are increasingly pressured by customers in terms of service levels, on the other hand, must manage their suppliers from various locations and with different local requirements. In this context, an appropriate management of information flows is needed to create the adequate visibility level for managing supply chain risk. This chapter presents an overview on the concepts of risk management, visibility and information management in supply chains. This study proposes a conceptual framework for the selection of risk mitigation strategies in the supply chain and characterizes the external and internal information flows decision makers need to implement two categories of risk mitigation strategies: redundancy and flexibility. © 2017, IGI Global.