Abstract
Adverse Drug Events (ADEs) are a major health problem, and developing accurate prediction methods may have a significant impact in public health. Ideally, we would like to have predictive methods, that could pinpoint possible ADRs during the drug development process. Unfortunately, most relevant information on possible ADRs is only available after the drug is commercially available. As a first step, we propose using prior information on existing interactions through recommendation systems algorithms. We have evaluated our proposal using data from the ADReCS database with promising results.

Abstract
Probabilistic Inductive Logic Programming (PILP) is a relatively unexplored area of Statistical Relational Learning which extends classic Inductive Logic Programming (ILP). Within this scope, we introduce SkILL, a Stochastic Inductive Logic Learner, which takes probabilistic annotated data and produces First Order Logic (FOL) theories. Data in several domains such as medicine and bioinformatics have an inherent degree of uncertainty, and because SkILL can handle this type of data, the models produced for these areas are closer to reality. SkILL can then use probabilistic data to extract non-trivial knowledge from databases, and also address efficiency issues by introducing an efficient search strategy for finding hypotheses in PILP environments. SkILL's capabilities are demonstrated using a real world medical dataset in the breast cancer domain.

Abstract
The volatility of the wind generation reduces the profits of wind generators as a consequence of the differences between the real wind generation and the wind power offered in the electricity markets. This paper presents two models: i) wind and generic storage system offering without a physical connection and ii) wind and generic storage system offering with a physical connection to mitigate the wind positive imbalances (excess of the wind generation with respect to the wind power offered). The objective of the models is to maximize the expected profit of selling the energy in the day-ahead market, where the energy can come from the wind power and the storage system. Moreover, the wind power imbalance is penalized in the balancing market reducing the profits. The problems are modeled using stochastic mixed integer linear programming. A case study of a week (168 hours) is simulated to evaluate the models. After the simulations, the results are discussed and a summary of the main conclusions are presented.

Abstract
The new concept development is a critical stage of the innovation process that can be seen as a new knowledge creation process. This paper presents a new approach and a software tool for a collaborative new concept development. Our approach considers Collaborative Innovation Networks as ecosystems for new knowledge creation and integration, and Web Mashups as supporting platforms for the development of virtual co-learning and knowledge co-creation environments. The achieved results confirm the utility and efficacy of the software tool and allow foreseeing its suitability for use in educational contexts.

Abstract
The liberalization of energy markets has imposed several modifications in the electricity market environment. The paradigm of monopoly market ceased to exist, and new models have been put into practice. The new models have increased the incentive on competitiveness, making market players struggle to achieve the best outcomes out of market participation. Producers aim at reaching the maximum profit on the sale of energy, while consumers try to minimize their spending on electrical energy. The proposed methodology considers the optimization of players' participation in multiple market opportunities. Reference prices that are expected in each market type at each moment are achieved through the application of neural networks. Using the forecasted prices, the proposed portfolio optimization method allocates the sale and purchase of electrical energy to different markets throughout the time, with the aim at achieving the most advantageous participation profile. A particle swarm approach is used to reduce the execution time while guaranteeing the minimum degradation of the results. Results of the swarm methodology are compared to those of a deterministic approach, using real data from the Iberian electricity market - MIBEL.

Abstract