Abstract
This paper presents a new approach to incipient fault diagnosis in power transformers, based on the results of dissolved gas analysis. A set of autoassociative neural networks or autoencoders are trained, so that each becomes tuned with a particular fault mode. Then, a parallel model is built where the autoencoders compete with one another when a new input vector is entered and the closest recognition is taken as the diagnosis sought. A remarkable accuracy is achieved with this architecture, in a large data set used for result validation. © 2011 IEEE.

Abstract
Mountain areas are the source of high quality and socioeconomic relevance water resources. The sustainable management of such regions is fundamental to maintain the water supply to populations in wide areas all over the planet. Serra da Estrela is the origin of water resources of strategic importance to Portugal. In the highest part of the mountain, especially above 1400 m a.s.l., the use of road de-icing chemicals (NaCl and, accessorily, CaCl) may affect both groundwater and surface water as well as soils and therefore is a major environmental concern that should be investigated. This article presents a multidisciplinary methodology meant to support the study of water pollution as a result of the use of road de-icing salts in a mountain environment. This methodology encompasses contributions from Hydrogeology, Hydrogeochemistry, Isotope Geochemistry, Hydrogeophysics, GIS supported geological mapping and mathematical modelling. The main purpose of the application of this methodology in Serra da Estrela is to prepare a hydrogeological conceptual model focused in the processes related to groundwater pollution by NaCl from road de-icing. Another objective is to improve the sustainability of water resources and to provide new guidelines for water exploration and exploitation in the region.

Abstract
Public transport users are increasingly connected in real time through mobile devices to social networks, such as Twitter and Facebook. This allows them both to access and to provide valuable operational and emotional information from and to fellow travellers. Transport network management could benefit from this exchange, and also participate by providing rewards to valuable contributors. This paper introduces a model for such cooperative exchanges of information and proposes a valuation system for the information provided and obtained. Users and automatic systems (sensors) would provide information, such as punctuality, noise levels, and assessments of driver's skills, referenced to particular vehicles, routes and times. Then other users accessing such information would classify it on the level of correctness and usefulness, under a validation scheme operated by the transport network management. Such information could either be openly available or private in some degree within a social network, taking account of security aspects that need to be preserved. In a mature environment, more valuable information could only be made available via subscription or freely available to highly valued contributing users. The use of social networks would provide an easy way of sharing information and also provide a sense of community to the involved travellers. Transport network management benefiting from relevant information exchanges could reward users contributing with valuable data, as an incentive to enhance participation. In this context, the information exchanged would achieve a real transactional value and present a new electronic commerce paradigm. Overall, such exchange could also be seen as a serious game.

Abstract

Abstract
This paper analyzes the application of clustering techniques for wind power scenario reduction. The results have shown the unimodal structure of the scenario generated under a Monte Carlo process. The unimodal structure has been confirmed by the modes found by the information theoretic learning mean shift algorithm. The paper also presents a new technique able to represent the wind power forecasting uncertainty by a set of representative scenarios capable of characterizing the probability density function of the wind power forecast. From an initial large set of sampled scenarios, a reduced discrete set of representative scenarios associated with a probability of occurrence can be created finding the areas of high probability density. This will allow the reduction of the computational burden in stochastic models that require scenario representation. © 2011 IEEE.

Abstract
SchematicMaps are mainly used for depicting transportation networks. They are generated through a schematization process where irrelevant details are eliminated and important details are emphasized. This process, being manually performed by teams of expert designers, is expensive and time consuming. Such manual execution is unsuitable for the production of schematic maps for location-based services or ondemand schematic maps, as near real-time and user-centered properties are needed. This work proposes GeneX, a framework that can support the automated generation of schematic maps. The framework and the new algorithms developed were able to completely eliminate erroneous map point placement, and to decrease by 33% the contention for map point placement, producing schematic maps without human intervention in soft real time.