Abstract
This paper explores the usage of unmanned aerial vehicles (UAVs) to acquire remotely sensed very high-resolution imagery for classification of an agrosilvopastoral system in a rural region of Portugal. Aerial data was obtained using a low-cost UAV, equipped with an RGB sensor. Acquired imagery undergone a photogrammetric processing pipeline to obtain different data products: an orthophoto mosaic, a canopy height model (CHM) and vegetation indices (VIs). A superpixel algorithm was then applied to the orthophoto mosaic, dividing the images into different objects. From each object, different features were obtained based in its maximum, mean, minimum and standard deviation. These features were extracted from the different data products: CHM, VIs, and color bands. Classification process – using random forest algorithm – classified objects into five different classes: trees, low vegetation, shrubland, bare soil and infrastructures. Feature importance obtained from the training model showed that CHM-driven features have more importance when comparing to those obtained from VIs or color bands. An overall classification accuracy of 86.4% was obtained.

Abstract

Abstract
After the computational thinking sessions in the previous 2016-2018 editions of TEEM Conference, the fourth edition of this track has been organized in the current 2019 edition. Computational thinking is still a very significant topic, especially, but not only, in pre-university education. In this edition, the robotic has a special role in the track, with a strength relationship with the STEM and STEAM education of children at the pre-university levels, seeding the future of our society. © 2019 ACM.

Abstract
Rural regions concentrate on themselves a very rich set of ancestral traditions. The perpetuation of such traditions has been achieved through transmission between generations. Unfortunately, all this knowledge is typically elders-centered and it lacks effective processes of digitalization, storage and providing-systems for that all this heritage can effectively be perpetuated through future generations that are digital-born. From this base, it was created a project case study limited to the Portuguese Northeast region, named Viv@vó – living in the grandma's house. This paper presents the ICT platform that was created in this project and some main achievements during the project development process. Tourism and mainly experience and cultural heritage tourism are growing in tourist’s interests. Rural regions have an untapped potential for this slice of tourism industry. Rural regions have an enormous collection of ancestral knowledge that we are responsible to deliver to future generations as an inheritance to which they are entitled. Copyright © 2019. Carlos R. CUNHA, Aida CARVALHO, Luís AFONSO, Daniel SILVA, Paula Odete FERNANDES, Luís Carlos PIRES, Carlos COSTA, Ricardo CORREIA, Elsa RAMALHOSA, Alexandra I. CORREIA and Alexandre PARAFITA.

Abstract
This study aims to contribute to the understanding of children’s word-of-mouth communication: how it is processed, its dimensions and its relation to other sources of information and to young consumers’ use of the Internet. Theoretical contributions from consumer socialization, new media and word-of-mouth communication studies are assembled, and an exploratory qualitative analysis in the form of focus group interviews with 7–11-year-old children is reported. We provide empirical evidence for word-of-mouth communication being a common activity among children. Observation and marketing exposure both complement and trigger word-of-mouth activity. Electronic word-of-mouth communication is less frequent, but the Internet is a relevant source of information and marketing exposure; it assists children’s learning about products and brands and furthers their purchase decision processes. This study suggests that word-of-mouth communication received by children is more complex and dynamic as compared to extant literature, suggesting that future research further explores its sought and unsought components, as well as its relationship with non-verbal peer influence that results from observation. © 2019, Academy of Marketing Science.

Abstract
Electricity markets are complex environments with very dynamic characteristics. The large-scale penetration of renewable energy sources has brought an increased uncertainty to generation, which is consequently, reflected in electricity market prices. In this way, novel advanced forecasting methods that are able to predict electricity market prices taking into account the new variables that influence prices variation are required. This paper proposes a new model for day-ahead electricity market prices forecasting based on the application of an artificial neural network. The main novelty of this paper relates to the pre-processing phase, in which the relevant data referring to the different variables that have a direct influence on market prices such as generation, temperature, consumption, among others, is analysed. The association between these variables is performed using spearman correlation, from which results the identification of which data has a larger influence on the market prices variation. This pre-analysis is then used to adapt the training process of the artificial neural network, leading to improved forecasting results, by using the most relevant data in an appropriate way. © 2019 IEEE.