Abstract
Learning in non-stationary environments is not an easy task and requires a distinctive approach. The learning model must not only have the ability to continuously learn, but also the ability to acquired new concepts and forget the old ones. Additionally, given the significant importance that social networks gained as information networks, there is an ever-growing interest in the extraction of complex information used for trend detection, promoting services or market sensing. This dynamic nature tends to limit the performance of traditional static learning models and dynamic learning strategies must be put forward. In this paper we present a learning strategy to learn with drift in the occurrence of concepts in Twitter. We propose three different models: a time-window model, an ensemble-based model and an incremental model. Since little is known about the types of drift that can occur in Twitter, we simulate different types of drift by artificially timestamping real Twitter messages in order to evaluate and validate our strategy. Results are so far encouraging regarding learning in the presence of drift, along with classifying messages in Twitter streams.

Abstract
Large-scale deployment of renewables in island power systems is attracting local attention of grid operators as a way of reducing fuel fossil consumption. Planning a grid based on renewable power plants poses serious challenges to the normal operation of a power system, namely on frequency and voltage stability. Regardless of its inherent problems, there is a consensus that in a future not far away, the green energy could supply most of local needs with less production based on fuel burning. In past grid code compliance, wind turbines did not require services for supporting grid operation. To shift to large-scale integration of renewables, the island grid code should incorporate a new set of requirements in order to regulate the inclusion of these services. Hence, this paper focuses on grid code requirements for large renewable energy integration based distributed generation in island power systems. The paper also discusses additional requirements such as "virtual" wind inertia for improving regulation capability of wind farms and electric energy storage applications for better renewable generation performance. Moreover, a comparative analysis of insular grid code compliance to these requirements in European context is presented.

Abstract

Abstract
The success of neurosurgery strongly depends on the pre-neurosurgical evaluation phase, in which the delineation of the areas to be removed or to be stimulated must be very accurate. For patients undergoing Deep Brain Stimulation (DBS) it is vital the delineation of the target area prior to surgery, and after the implantation of the DBS lead to confirm the electrodes positioning. In this paper we present a system to accurately determine the 3D position of DBS electrodes implanted within the brain of Parkinson and Dystonia patients. The system was tested using a multimodal dataset from 16 patients (8 with Parkinson's disease and 8 with dystonia) and, on average, the differences between the detected electrodes positions and the ones estimated manually by an experienced physician were less than a voxel in all cases. Copyright

Abstract
The Electric Vehicle (EV) is one source of flexibility to the electric power system. When aggregated by a market agent, it can offer its flexibility in the balancing reserve market. In order to meet this goal, a framework of optimization and forecasting algorithms must designed to cover the different time horizons of the decision process. This paper describes a full framework for EV aggregators participating in different electricity market sessions. This framework is illustrated for the balancing reserve market and the impact of forecasts of different quality for the balancing reserve direction is evaluated. The test case consists in synthetic time series generated from real data for 3000 EV participating in the Iberian electricity market.

Abstract
Combining conventional and unconventional generations with hard forecasting properties and consumption variability has made the task of fitting large amounts of wind generation into unit commitment procedures very challenging. In this context, massive integration of electric vehicles in the electric systems, is expected. This paper aims at evaluating the adequacy of a generating system taking into account the electric vehicles and high wind power integration level in its energy mix. This study was conducted on the European project MERGE framework, and the results have shown that the generating system evaluated is reliable. Nevertheless, the simulations carried out for scenarios with adverse weather conditions (dry years) have revealed specific circumstances that might jeopardize the system adequacy.