Abstract
Patients with medically refractory epilepsy may benefit from surgical resection of the epileptic focus. Subdural electrodes are implanted to accurately locate the seizure onset and locate the eloquent areas to be spared. However, the visualization of the subdural electrodes may be limited by the current methods. The aim of this work was to assist physicians in the localization of subdural electrodes in relation to anatomical landmarks using co-registration methods and by removing the cerebellum from MRI images. Three patients with refractory epilepsy were studied, in whom subdural electrodes were implanted. All electrodes were correctly localized in a 3D view over the cortex and their visualization was improved by the removal of cerebellum. This method promises to be useful in the optimization of the surgical plan.

Abstract
In this paper we propose and apply a methodology to study the relationship between the performance of bagging and the characteristics of the bootstrap samples. The methodology consists of 1) an extensive set of experiments to estimate the empirical distribution of performance of the population of all possible ensembles that can be created with those bootstraps and 2) a metalearning approach to analyze that distribution based on characteristics of the bootstrap samples and their relationship with the complete training set. Given the large size of the population of all ensembles, we empirically show that it is possible to apply the methodology to a sample. We applied the methodology to 53 classification datasets for ensembles of 20 and 100 models. Our results show that diversity is crucial for an important bootstrap and we show evidence of a metric that can measure diversity without any learning process involved. We also found evidence that the best bootstraps have a predictive power very similar to the one presented by the training set using naive models.

Abstract
This paper presents the applicability of a reinforcement learning algorithm based on the application of the Bayesian theorem of probability. The proposed reinforcement learning algorithm is an advantageous and indispensable tool for ALBidS (Adaptive Learning strategic Bidding System), a multi-agent system that has the purpose of providing decision support to electricity market negotiating players. ALBidS uses a set of different strategies for providing decision support to market players. These strategies are used accordingly to their probability of success for each different context. The approach proposed in this paper uses a Bayesian network for deciding the most probably successful action at each time, depending on past events. The performance of the proposed methodology is tested using electricity market simulations in MASCEM (Multi-Agent Simulator of Competitive Electricity Markets). MASCEM provides the means for simulating a real electricity market environment, based on real data from real electricity market operators.

Abstract
The Geophysical Institute of the University of Porto (IGUP) is an important marker in the scientific and technological culture developed over more than a century in the city of Porto, thus a strategy is being planned out for its recovery. This mission aims to take advantage of all the activities in the history of this institution, taking into account several components such as research in areas of natural hazards, seismology, weather and radiometry, support for graduate and post-graduate education at the University of Porto, scientific dissemination, training addressed to students of the 2nd and 3rd cycles of basic education and in the context of extracurricular activities that are currently the responsibility of the municipality of Vila Nova de Gaia as well as the installation of a pole of the Science Museum of the University of Porto. This infrastructure has some instruments related to seismology, meteorology and radiation, which are directly related to the measurement of variables involved in the estimation of seismic, meteorological and radiological hazards and can thus relate to risk estimation. As such, it has the potential to become a center for research in Natural Hazards, which may contribute with studies, data and parameters for civil society and the scientific community. The recovery that is now underway in the previously integrated PTO seismic station - Worldwide Standardized Seismographic Network (WWSSN), can help to achieve the implementation of a center of research in seismology and simultaneously acknowledge the geopolitical importance of this station. As such, in the present work we intend to show part of the analysis of seismic records relating to previously unknown Soviet nuclear explosions as well as bringing back to life inactive equipment that was switched off since the 1990s and thus enabling the recording of more modern digital seismic records. © 2014 LNEG – Laboratório Nacional de Geologia e Energia IP.

Abstract
Emotionally adaptive games are one of the holy grails of modern affective game research. However, current state of the art affective games rely on static game adaptation mechanics that assume a fixed emotional reaction from players every time. Not only this, most commercial titles have no affective adaptation loop whatsoever and their design is based on game design optimizations via typical beta-testing procedures, which falls short of ideal both in the level design and long-term gameplay experience fronts. In this paper, we demonstrate a generalizable approach for building predictive models of players' emotional reactions across different games and game genres. We describe a physiological approach for modelling players' emotional reactions, which relies on features extracted from players' emotional responses to game events, which were collected and extrapolated through their physiological data during actual gameplay sessions. Based on the optimal feature sets found by three feature selection algorithms (best first, sequential feature selection and genetic search), the collected features are used to create computational models of players' emotional reactions on the arousal and valence dimensions of emotion, using several machine learning algorithms. We expect this approach will allow both a more objective and quicker prototyping for digital games, as well as foster a future generation of affective games capable of modelling players' affective profiles over time, thus adapting to their changing preferences and needs.

Abstract
In this work the performance assessment of a digitised radio-over-fibre (DRoF) system is presented considering the transmission of orthogonal frequency division multiplexing (OFDM) signals. Specifically, the impact of the high peak-to-average-ratio (PAPR) in the ADC/DAC quantization noise is addressed by means of simulation results. In order to minimize the impact of the digitisation process, we present a study of the improvement of the system performance when commonly used pre-distortion techniques suitable for PAPR reduction are considered. Additionally, the performance of the selected pre-distortion techniques is assessed experimentally, in terms of the modulation error ratio (MER) in an OFDM-DRoF link transmission, considering the impact of optical attenuation. It is observed that the transmission of OFDM signals in DRoF is severely affected by the inherent high PAPR levels and that, by using pre-distortion techniques with ADC/DAC with 7 bits, it is possible to increase the modulation error ratio (MER) by 15 dB or to increase the optical fibre by 6.5 km (8.5% increase) without the need of additional complexity at the OFDM receiver.