Abstract

Abstract
In the area machine learning / data mining many diverse algorithms are available nowadays and hence the selection of the most suitable algorithm may be a challenge. Tbhis is aggravated by the fact that many algorithms require that certain parameters be set. If a wrong algorithm and/or parameter configuration is selected, substandard results may be obtained. The topic of metalearning aims to facilitate this task. Metalearning typically proceeds in two phases. First, a given set of algorithms A (e.g. classification algorithms) and datasets D is identified and different pairs < ai,dj > from these two sets are chosen for testing. The dataset di is described by certain meta-features which together with the performance result of algorithm ai constitute a part of the metadata. In the second phase the metadata is used to construct a model, usually again with recourse to machine learning methods. The model represents a generalization of various base-level experiments. The model can then be applied to the new dataset to recommend the most suitable algorithm or a ranking ordered by relative performance. This article provides more details about this area. Besides, it discusses also how the method can be combined with hyperparameter optimization and extended to sequences of operations (workflows).

Abstract
This paper addresses the identification of reduced order models for variable speed pump-turbine plants, including the representation of the dynamic behaviour of the main components: hydraulic system, turbine governors, electromechanical equipment and power converters. A methodology for the identification of appropriated reduced order models both for turbine and pump operating modes is presented and discussed. The methodological approach consists of three main steps: 1) detailed pumped-storage power plant modelling in SIMSEN; 2) reduced order models identification and 3) specification of test conditions for performance evaluation.

Abstract
The paper presents a tuning method for PID controllers which substantially improves closed-loop disturbance rejection performance while keeping the tracking performance. The tuning method is based on the internal disturbance compensator which parameters are calculated according to the Magnitude Optimum criterion. The results of experiments show that the proposed model-based approach gives superior disturbance-rejection response and lower controller activity when compared to Disturbance Rejection Magnitude Optimum tuning method. © Springer International Publishing Switzerland 2017.

Abstract
Future real-time embedded systems will increasingly incorporate mixed application models with timing constraints running on the same multi-core platform. These application models are dataflow applications with timing constraints and traditional real-time applications modelled as independent arbitrary-deadline tasks. These systems require guarantees that all running applications execute satisfying their timing constraints. Also, to be cost-efficient in terms of design, they require efficient mapping strategies that maximize the use of system resources to reduce the overall cost. This work proposes an approach to integrate mixed application models (dataflow and traditional real-time applications) with timing requirements on the same multi-core platform. It comprises three main algorithms: 1) Slack-Based Merging, 2) Timing Parameter Extraction, and 3) Communication-Aware Mapping. Together, these three algorithms play a part in allowing mapping and scheduling of mixed application models in embedded real-time systems. The complete approach and the three algorithms presented have been validated through proofs and experimental evaluation. © 2017 Copyright held by the owner/author(s).

Abstract
This works intends to be a reduced, but complete literature review about the role of the implementation process in the new technological paradigm for manufacturing, called "Industry 4.0". This is a very recent subject that already generated a wide range of literature and discussion, although it had not yet been studied in-depth, making the term "industry 4.0" and its related concepts blurrier than concrete. The expression "implementation of industry 4.0" is too wide, since it is the result of the implementation of "industry 4.0" technologies and not the paradigm per se. The main objective of this work is to study what is known until now about the implementation of "industry 4.0". With that objective, this paper starts by presenting a definition of what is "industry 4.0" and contextualizing it in today's manufacturing environment. Then some preconditions that are required for the implementation of "industry 4.0" are presented, followed by the specificities that some particular technologies have.