Abstract
The Rede Telematica da Saude (RTS) is a telematic network connecting health care providers in the Aveiro region (Portugal), aiming at supporting the continuity of care. Using the RTS, health care professionals and institutions can securely share clinical data. RTS makes use of an integration engine, which accesses the scattered data sources to create a virtual unified view of patients' information. RTS is deployed over a wide-area private network, shared among a great variety of bandwidth links, systems and applications, which can impact the infrastructure service levels in multiple ways. In this paper, we describe the development of a toolkit for monitoring the performance of the distributed integration process. These analysis mechanisms make it is possible to detect bottlenecks and introduce optimizations in the system, especially with respect to the integration engine module. Its deployment in the production RTS health telematic network assists the maintenance team and the decision taking process to handle usage trends and systems needs.

Abstract
In Epilepsy, seizure semiology analysis is routinely used for diagnostic purpose. The behavior of the patient during seizures is usually evaluated by expert qualitative observation where several signs are identified. In the clinical literature, several ictal phenomena are described but still involved in controversy. In this paper, we present our effort to establish a quantified movement analysis method to be widely used as an additional tool to clarify this controversy.

Abstract
In this paper we present the evolution of a quantitative movement analysis methodology for epileptic seizures. With this improved method we analyzed 20 seizure video sequences, 10 classified as automotor and 10 as hypermotor, from 17 different patients. The results obtained show we could classify all (100%) of the hypermotor seizures solely based on a quantified movement parameter - called movement extent extracted with our method. Other quantitative parameters were also studied. This striking result paves the way to the contribution of quantitative movement methods in automated epileptic seizure detection systems.

Abstract
This work assesses the ability of Self Organizing Maps (SOMs) to find nonlinear association and/or connectivity among biosignals. The proposed method can find numerous applications where nonlinear biosignals are measured in spatiotemporal manner. Experiments are performed on tens of thousands of biosignals that are obtained from real biosignals by implementing a nonlinear transform, delays, additive and multiplicative random noise. Results showed that resolving association among biosignals under strong nonlinear transformation, noise, and delay is effective using SOMs.

Abstract
EpiGauss is a method that combines single dipole model with dipole clustering to characterize active brain generators in space and time related to EEG events. EpiGauss was applied to study epileptogenic activity in 4 patients suffering of hypothalamic hamartoma related epilepsy, a rare syndrome with a unique epileptogenic source - the hamartoma lesion - and natural propagation hypothesis - from hamartoma to the surface EEG focus. The results are compared to Rap-MUSIC and Single Moving Dipole methods over the same patients.

Abstract
This paper studies the suitability of brain activity, namely electroencephalogram signals, as raw material for conducting biometric authentication of individuals. Brain responses were extracted in particular scenarios, namely with visual stimulation leading to biological brain responses known as visual evoked potentials. In our study, we evaluated a novel method, using only 8 occipital electrodes and the energy of differential EEG signals, to extract information about the subjects for further use as their biometric features. To classify the features obtained from each individual we used a one-class classifier per subject. These classifiers are trained only with target class features, which is the correct procedure to apply in biometric authentication scenarios. Two types of one-class classifiers were tested, K-Nearest Neighbor and Support Vector Data Description. Two other classifier architectures were also studied, both resulting from the combination of the two previously mentioned classifiers. After testing these classifiers with the features extracted from 70 subjects, the results showed that brain responses to visual stimuli are suitable for an accurate biometric authentication.