Abstract
The evaluation index of renewable power forecasting plays an important role in guiding the power grid dispatching department and the operation of renewable power plants. Most of the current evaluation indexes can hardly reflect the relationship between prediction error and system flexibility. Firstly, this paper studies the evaluation index of system flexibility, determines the weight of different flexibility indexes by entropy method, and quantifies the flexibility of power system. On the basis of the existing index, the system flexibility is introduced to improve the existing index, and a new error evaluation index Root Weighted Squared Error is obtained. The simulation results show that the new evaluation index has good performance in measuring the level of single station prediction and multi-station scheduling.

Abstract
For the first time in Europe hundreds of rare disease (RD) experts team up to actively share and jointly analyse existing patient’s data. Solve-RD is a Horizon 2020-supported EU flagship project bringing together >300 clinicians, scientists, and patient representatives of 51 sites from 15 countries. Solve-RD is built upon a core group of four European Reference Networks (ERNs; ERN-ITHACA, ERN-RND, ERN-Euro NMD, ERN-GENTURIS) which annually see more than 270,000 RD patients with respective pathologies. The main ambition is to solve unsolved rare diseases for which a molecular cause is not yet known. This is achieved through an innovative clinical research environment that introduces novel ways to organise expertise and data. Two major approaches are being pursued (i) massive data re-analysis of >19,000 unsolved rare disease patients and (ii) novel combined -omics approaches. The minimum requirement to be eligible for the analysis activities is an inconclusive exome that can be shared with controlled access. The first preliminary data re-analysis has already diagnosed 255 cases form 8393 exomes/genome datasets. This unprecedented degree of collaboration focused on sharing of data and expertise shall identify many new disease genes and enable diagnosis of many so far undiagnosed patients from all over Europe.

Abstract
Robotics is very appealing and is long recognized as a great way to teach programming, while drawing inspiring connections to other branches of engineering and science such as maths, physics or electronics. Although this symbiotic relationship between robotics and programming is perceived as largely beneficial, educational approaches often feel the need to hide the underlying complexity of the robotic system, but as a result fail to transmit the reactive essence of robot programming to the roboticists and programmers of the future. This paper presents Rosy, a novel language for teaching novice programmers through robotics. Its functional style is both familiar with a high-school algebra background and a materialization of the inherent reactive nature of robotic programming. Working at a higher-level of abstraction also teaches valuable design principles of decomposition of robotics software into collections of interacting controllers. Despite its simplicity, Rosy is completely valid Haskell code compatible with the ROS~ecosystem. We make a convincing case for our language by demonstrating how non-trivial applications can be expressed with ease and clarity, exposing its sound functional programming foundations, and developing a web-enabled robot programming environment.

Abstract

Abstract
Machine Learning is one of the most trending topics nowadays. The reason is of course for being more and more present in our everyday life, even if we do not notice it. What goes even more unnoticed is the fact that every Machine Learning model needs computational power. And of course, it also needs data. But how many data are necessary to build the best Machine Learning model possible, and how many times do we need to retrain a model so that it does not become obsolete as data change? That kind of questions are the ones that can reduce unnecessary costs to a company. In this paper we propose a novel approach to predict the performance of a model given some characteristics of the data, that are called meta-features. The goal is, indeed, to only train a new model when some error metric (e.g., RMSE) is expected to decrease substantially compared with a previously trained model. This approach is best applied in scenarios of data streaming or in Big Data, as well on Interactive Machine Learning scenarios. We validate it on a real Fraud Detection case and this scenario is also briefly described.

Abstract
Nas últimas décadas a utilização da inteligência artificial tem sido frequente no desenvolvimento de aplicações computacionais. Mais recentemente a aprendizagem automática, especialmente pelo uso da aprendizagem profunda (deep learning), tem impulsionado o crescimento e ampliado o desenvolvimento de sistemas inteligentes para diferentes domínios. No cenário atual de crescimento tecnológico estão a surgir com maior frequência os sistemas de recomendação (recommender systems) com diferentes técnicas para a filtragem de informações em grandes bases de dados. Um desafio é prover a recomendação adaptativa para mitigar a sobrecarga de informações em ambientes on-line. Este artigo revisa trabalhos anteriores e aborda alguns dos aspectos teórico-conceptuais e teórico-práticos que constituem os sistemas de recomendação, caracterizando o emprego de redes neuronais profundas (Deep Neural Network – DNN) para prover a recomendação sequencial apoiada pela recomendação baseada em sessão.;In recent decades, artificial intelligence use has been frequent in the computational applications development. More recently, machine learning, especially through the use of deep learning, has driven growth and expanded the intelligent systems development for different domains. In the current scenario of technological growth, the recommender systems appear with increasing frequency through their different techniques for information filtering in large datasets. It is a challenge to provide adaptive recommendation to mitigate information overload in online environments. This article reviews previous works and addresses some of the theoretical-conceptual and theoretical-practical aspects that constitute the recommender systems, characterizing the use of deep neural network (DNN) to provide sequential recommendation supported by session-based recommendation.