Abstract
In this paper we address the problem of clustering interval data, adopting a model-based approach. To this purpose, parametric models for interval-valued variables are used which consider configurations for the variance-covariance matrix that take the nature of the interval data directly into account. Results, both on synthetic and empirical data, clearly show the well-founding of the proposed approach. The method succeeds in finding parsimonious heterocedastic models which is a critical feature in many applications. Furthermore, the analysis of the different data sets made clear the need to explicitly consider the intrinsic variability present in interval data.

Abstract
This chapter presents an evolutionary analysis, at the Portuguese and European levels, that features Higher Education centred on the University's Mission, the building and importance of National Innovation System, and related dynamics. The university should fulfil the fundamental role related with creation, preservation, and dissemination of knowledge and generate skills and key competences to respond to increasingly more complex problems in a rapidly changing environment, as well as to enable multidisciplinary approaches that are in the university's own and peculiar nature, and which is fostered by the relationships with the systems that drive the interaction with the target communities. Referring to the last quarter of the 20th century, the chapter outlines the emergence of the "Research University" in the context of the slow but progressive increase in value of Science and Technology and Research and Development, with the organization of the related National Systems in order to be able to foster innovation.

Abstract
For the linear Hotelling model with firms located at the boundaries of the segment line, we study the price competition in a scenario of incomplete information in the production costs of both firms. We introduce the bounded uncertain costs (BUC) condition in the production costs and we prove that there is a local optimum price strategy if and only if the BUC condition holds. We compute explicitly the local optimum price strategy and we prove that it does not depend upon the distributions of the production costs of the firms, except on their first moments. We prove that the ex-post profit of a firm is smaller than its ex-ante profit if and only if the production cost of the other firm is greater than its expected cost.

Abstract
Liver cancer is the sixth most frequently diagnosed cancer and, particularly, Hepatocellular Carcinoma (HCC) represents more than 90% of primary liver cancers. Clinicians assess each patient's treatment on the basis of evidence-based medicine, which may not always apply to a specific patient, given the biological variability among individuals. Over the years, and for the particular case of Hepatocellular Carcinoma, some research studies have been developing strategies for assisting clinicians in decision making, using computational methods (e.g. machine learning techniques) to extract knowledge from the clinical data. However, these studies have some limitations that have not yet been addressed: some do not focus entirely on Hepatocellular Carcinoma patients, others have strict application boundaries, and none considers the heterogeneity between patients nor the presence of missing data, a common drawback in healthcare contexts. In this work, a real complex Hepatocellular Carcinoma database composed of heterogeneous clinical features is studied. We propose a new cluster-based oversampling approach robust to small and imbalanced datasets, which accounts for the heterogeneity of patients with Hepatocellular Carcinoma. The preprocessing procedures of this work are based on data imputation considering appropriate distance metrics for both heterogeneous and missing data (HEOM) and clustering studies to assess the underlying patient groups in the studied dataset (K-means). The final approach is applied in order to diminish the impact of underlying patient profiles with reduced sizes on survival prediction. It is based on K-means clustering and the SMOTE algorithm to build a representative dataset and use it as training example for different machine learning procedures (logistic regression and neural networks). The results are evaluated in terms of survival prediction and compared across baseline approaches that do not consider clustering and/or oversampling using the Friedman rank test. Our proposed methodology coupled with neural networks outperformed all others, suggesting an improvement over the classical approaches currently used in Hepatocellular Carcinoma prediction models.

Abstract
This paper analyses the impact of the penetration of electric vehicles (EVs) charging loads on thermal ageing of a distribution transformer of a private industrial client that allows EVs to charge while their owners are at work and at three different working shifts during a day. Furthermore, the system is part of an isolated electric grid in a Portuguese Island. In this paper, a transformer thermal model is used to estimate the hotspot temperature given the load ratio. Real data were used for the main inputs of the model, i.e. private industrial client load, transformer parameters, the characteristics of the factory and electric vehicle parameters.

Abstract
Cutting and packing problems generally address the cutting or packing of smaller items into a larger container object. Usually, the main methodologies used in the Circular Open Dimension Problem (CODP) are nonlinear programming methods or methods that combine different heuristics. The aim of this project is at devising and using an agent-based simulation approach to determine the length of the open rectangle in CODP; more specifically, we look into the Circular two-dimension Open Dimension Problem. Agents (circles, which can have different dimensions) were given a set of simple rules that allow them to be placed in the world (i.e. an open rectangle). These rules are inferred from the formal CODP formulation and from the behavior defined in the agents.