Abstract
An amendment to this paper has been published and can be accessed via a link at the top of the paper. © 2020, The Author(s).

Abstract
Research in imbalanced domain learning has almost exclusively focused on solving classification tasks for accurate prediction of cases labelled with a rare class. Approaches for addressing such problems in regression tasks are still scarce due to two main factors. First, standard regression tasks assume each domain value as equally important. Second, standard evaluation metrics focus on assessing the performance of models on the most common values of data distributions. In this paper, we present an approach to tackle imbalanced regression tasks where the objective is to predict extreme (rare) values. We propose an approach to formalise such tasks and to optimise/evaluate predictive models, overcoming the factors mentioned and issues in related work. We present an automatic and non-parametric method to obtain relevance functions, building on the concept of relevance as the mapping of target values into non-uniform domain preferences. Then, we proposeSERA, a new evaluation metric capable of assessing the effectiveness and of optimising models towards the prediction of extreme values while penalising severe model bias. An experimental study demonstrates howSERAprovides valid and useful insights into the performance of models in imbalanced regression tasks.

Abstract
Nonlinear complexity measures computed from beat-to-beat arterial BP dynamics have shown associations with standard cardiac surgical risk indices. They reflect the physiological adaptability of a system and has been proposed as dynamical biomarkers of overall health status. We sought to determine the impact of anesthetic induction and cardiopulmonary bypass (CPB) upon the complexity measures computed from perioperative BP time series. In this prospective, observational study, 300 adult patients undergoing cardiac surgery were included. Perioperative period was divided as: (1) Preoperative (PreOp); (2) ORIS-induction to sternotomy; (3) ORSB- sternotomy to CPB; (4) ORposB-post CPB and within 30 min before leaving OR and (5) postoperative phase (PostOp)-initial 30 min in the cardiac surgical intensive care unit. BP waveforms for systolic (SAP), diastolic (DAP), mean arterial pressure (MAP) and pulse pressure (PP) were recorded, and their corresponding complexity index (MSE n-ary sumation ) was calculated. Significant decrease in MSE( n-ary sumation )from Preop to PostOp phases was observed for all BP time series. Maximum fall was seen during post anesthetic induction (ORIS) phase. Mild recovery during the subsequent phases was observed but they never reached the baseline values. In an exploratory analysis, preoperative MSE( n-ary sumation )showed a significant correlation with postoperative length of ICU stay. Blood pressure complexity varies at different time points and is not fixed for a given individual. Preoperative BP Complexity decreased significantly following anesthetic induction and did not recover to baseline until 30 min after surgery. Prevention of this significant fall may offer restoration of MSE( n-ary sumation )throughout surgery. Furthermore, preoperative BP complexity needs to be explored as a predictor of major postoperative adverse events by itself or in addition with the current risk indices.

Abstract
Accessibility is one of the key measures of urban transportation planning, which quantify how easy is the access to a facility. Public transport accessibility concerns of the access level of geographical locations to public transport. In this paper, accessibility is used as an indicator to estimate social exclusion based on the maximum distance that someone has to walk to reach the public transport. The concept of the 6-minute walking distance (6MWD) is applied to measure accurately the walking ability for different groups of the population. A real life case study is conducted to get insight into the transportation network of the Porto Metropolitan Area, Portugal. For this purpose, geographic, demographic and infrastructure data were collected and integrated. Also, webservices are used to measure walking distances between locations. The results of this study allowed to characterize regions by different levels of accessibility, providing insight into the social exclusion in public transport. This assessment is used not only to identify inequities but also to get an overview of the service quality of public transport. © 2020 The Authors. Published by ELSEVIER B.V.

Abstract
This paper presents an automatic semantic migration prototype based on Knowledge Discovery from Digital Archive Data for ontology population in the domain of Archives metadata, ISAD(G). Natural Language Processing (NLP) techniques are used for language processing and Semantic Web techniques for querying and updating the Ontology ArchOnto, a CIDOC-CRM (Conceptual Reference Model) extension. This work is done in the context of project EPISA (Entity and Property Inference for Semantic Archives) where the Portuguese National Archives, Torre do Tombo (ANTT) is one of the partners. The data model and description vocabularies we adopted are built upon the CIDOC-CRM standard, an ontology, developed for museums by the International Committee for Documentation (CIDOC) of the International Council of Museums (ICOM). A detailed example of a baptism document metadata migration is presented to highlight the challenges on the natural language interpretation and the ontology representation. Copyright

Abstract
Programmable Logic Controllers (PLCs) still are the state-of-the-art regarding the industrial automation control, but the Industry 4.0 advent is imposing new requirements, e.g., related to the capability to acquire and process data on real-time at the edge computational layer. On the other hand, the current availability of cheaper and more powerful processors opens new windows to develop low-cost and more advanced industrial controllers aligned with the Industry 4.0 principles. In this context, an important challenge is to improve the current state-of-the-art PLCs by taking into consideration the low-cost but powerful computational boards that will allow to embed IoT technologies and data analytics. This work describes the development of a low-cost but powerful industrial controller based on the use of the single-board computer Raspberry Pi, which allows executing logic control programs codified in IEC 61131-3, IEC 61499, or even in Java or Python, while maintaining the industrial requirements. The proposed platform was experimentally used to control an automation process based on a Fischertechniks platform.