Abstract
Nowadays imbalanced learning represents one of the most vividly discussed challenges in machine learning. In these scenarios, one or some of the classes in the problem have a significantly lower a priori probability, usually leading to trivial or non-desirable classifiers. Because of this, imbalanced learning has been researched to a great extent by means of different approaches. Recently, the focus has switched from binary classification to other paradigms where imbalanced data also arise, such as ordinal classification. This paper tests the application of learning pairwise ranking with multiple granularity levels in an ordinal and imbalanced classification problem where the aim is to construct an accurate model for donor-recipient allocation in liver transplantation. Our experiments show that approaching the problem as ranking solves the imbalance issue and leads to a competitive performance.

Abstract
The deregulation of the electricity sector has culminated in the introduction of competitive markets. In addition, the emergence of new forms of electric energy production, namely the production of renewable energy, has brought additional changes in electricity market operation. Renewable energy has significant advantages, but at the cost of an intermittent character. The generation variability adds new challenges for negotiating players, as they have to deal with a new level of uncertainty. In order to assist players in their decisions, decision support tools enabling assisting players in their negotiations are crucial. Artificial intelligence techniques play an important role in this decision support, as they can provide valuable results in rather small execution times, namely regarding the problem of optimizing the electricity markets participation portfolio. This paper proposes a heuristic method that provides an initial solution that allows metaheuristic techniques to improve their results through a good initialization of the optimization process. Results show that by using the proposed heuristic, multiple metaheuristic optimization methods are able to improve their solutions in a faster execution time, thus providing a valuable contribution for players support in energy markets negotiations.

Abstract
Today any OEM automotive industry that wants a status of a world-class organization has to follow a proper supplier quality management based on the worldwide recognized international standards. With this, the customer within a supply chain should have the sureness that the company has supplier capabilities in place to provide a service that consistently meets its needs and expectations. Although some of this Supplier Quality Management Systems (SQMS) are deeply integrated and used inside of an organization, sometimes they are implemented using inappropriate or limited tools, making the work of employees harder and acting often as entropy sources in those systems. Having the right tools to handle Inspections as well as Nonconformance, Complaint, Corrective Action and Concession processes is key to successfully track the supplier performance. This paper presents a platform to support a SQMS, that fits the technical specification ISO/TS 16949 requirements.

Abstract
Mobility mining has lots of applications in urban planning and transportation systems. In particular, extracting mobility patterns enables service providers to have a global insight about the mobility behaviors which consequently leads to providing better services to the citizens. In the recent years several data mining techniques have been presented to tackle this problem. These methods usually are either spatial extension of temporal methods or temporal extension of spatial methods. However, still a framework that can keep the natural structure of mobility data has not been considered. Non-negative tensor factorizations (NNTF) have shown great applications in topic modelling and pattern recognition. However, unfortunately their usefulness in mobility mining is less explored. In this paper we propose a new mobility pattern mining framework based on a recent non-negative tensor model called BetaNTF. We also present a new approach based on interpretability concept for determination of number of components in the tensor rank selection process. We later demonstrate some meaningful mobility patterns extracted with the proposed method from bike sharing network mobility data in Boston, USA.

Abstract
A methodology to rapidly produce environments that combine the intuition of in situ augmented reality (AR) with the commodity of virtual reality (VR) is proposed in this paper, by bringing together unmanned aerial systems (UAS) imagery and procedural modelling. While fully synthesized environments provide a very accurate visualization of the conserved parts of the real-world, missing parts - namely ruins - can be complemented with procedurally modelled structures. Regarding methodology's steps, firstly, a UAS flight mission gathers georeferenced imagery data about the site of interest. Then, the image set is converted to an accurate 3D model of the referred site, through photogrammetry. By considering the geographic information that also results from the previous process, ruins are manually outlined for georeferencing purposes. To complement ruins' missing information, virtual models of buildings are produced too, in a procedural modelling tool. Finally, at the full VR environment setup step, all elements are imported and subjected to geometric transformations that aim to match the procedurally modelled buildings with the outlined ruins. To improve the insight about the process work-flow, system's architecture and implementation are presented along with a case-study regarding a historically relevant site - Vila Velha's city gates (Vila Real, Portugal) - and preliminary results.

Abstract
Adaptability and energy-efficient sensing are essential properties to sustain the easy deployment and lifetime of WSNs. These properties assume a stronger role in autonomous sensing environments where the application objectives or the parameters under measurement vary, and human intervention is not viable. In this context, this paper proposes LiteSense, a self-adaptive sampling scheme for WSNs, which aims at capturing accurately the behavior of the physical parameters of interest in each WSN context yet reducing the overhead in terms of sensing events and, consequently, the energy consumption. For this purpose, a set of low-complexity rules auto-regulates the sensing frequency depending on the observed parameter variation. Resorting to real environmental datasets, we provide statistical results showing the ability of LiteSense in reducing sensing activity and power consumption, while keeping the estimation accuracy of sensing events.