Abstract
Nodes in complex networks inherently represent different kinds of functional or organizational roles. In the dynamic process of an information cascade, users play different roles in spreading the information: some act as seeds to initiate the process, some limit the propagation and others are in-between. Understanding the roles of users is crucial in modeling the cascades. Previous research mainly focuses on modeling users behavior based upon the dynamic exchange of information with neighbors. We argue however that the structural patterns in the neighborhood of nodes may already contain enough information to infer users' roles, independently from the information flow in itself. To approach this possibility, we examine how network characteristics of users affect their actions in the cascade. We also advocate that temporal information is very important. With this in mind, we propose an unsupervised methodology based on ensemble clustering to classify users into their social roles in a network, using not only their current topological positions, but also considering their history over time. Our experiments on two social networks, Flickr and Digg, show that topological metrics indeed possess discriminatory power and that different structural patterns correspond to different parts in the process. We observe that user commitment in the neighborhood affects considerably the influence score of users. In addition, we discover that the cohesion of neighborhood is important in the blocking behavior of users. With this we can construct topological fingerprints that can help us in identifying social roles, based solely on structural social ties, and independently from nodes activity and how information flows.

Abstract
Worldwide, over 250 million people are affected by chronic lung conditions such as Asthma and COPD. These can cause breathlessness, a harsh decrease in quality of life and, if not detected and duly managed, even death. In this paper, we aim to find the best and most efficient combination of signal processing and machine learning approaches to produce a smartphone application that could accurately classify lung function, using microphone recordings as the only input. A total of 61 patients performed the forced expiration maneuver providing a dataset of 101 recordings. The signal processing comparison experiments were conducted in a backward selection approach, reducing from 54 to 12 final envelopes, per recording. The classification experiments focused first on differentiating Normal from Abnormal lung function, and second in multiple lung function patterns. The results from this project encourage further development of the system.

Abstract

Abstract
The fast development of field, data processing equipment and software has allowed the use of geophysical methods to an ever increasing range of applications. Hence nowadays it is much easier to conduct massive field surveys combining different methods, to obtain more accurate and denser data, so that complex modeling and interpretation at limited costs can be carried out. Landfills have been targeted by geophysical methods in order to investigate their environmental impacts. In fact, landfills have been the classic way to deposit domestic and industrial waste and have generated a large range of negative environmental impacts in groundwater and soils. These problems often persist even after the effective use of the landfills and subsequent recovery processes. Owing to their characteristics, landfills are difficult to access and because of the general lack of accurate information regarding the shape, nature of the refuse, history and development of the landfill, non-invasive, nondestructive methods and sometimes autonomous data acquisition devices must be used to monitor impacts and to investigate and prevent groundwater and soil contamination. Geophysical methods can be applied to investigate a wide range of aspects related with the assessment of the environmental impact of landfills. Problems such as geometry definition, geological settings, contamination plume location and monitoring investigation of internal structure and refuse zoning, determination of fluid flow direction and paths or the determination of sealing conditions and leakage may be more successfully evaluated if a carefully chosen geophysical survey is part of any investigation program. Because of the nature and complexity of the problems to investigate, only multidisciplinary approaches, involving geophysics, hydrochemical, hydrogeological and geological information, can provide meaningful results for a thorough assessment of the landfills impact on the environment. This work intends to demonstrate the application of geophysical methods in the investigation of the environmental impacts, as described above, of industrial and domestic landfills during their life time and after closure. Thus, several examples will be discussed illustrating the use of 2D, 3D and time lapse resistivity, electromagnetic, ground probing radar, self-potential, magnetic, gravity surveys and airborne thermal mapping. Most of the geophysical data will be presented and shortly discussed together with information from boreholes, geology, hydrogeology and hydrochemical data. As it will be shown, it is clear that only a judicious combination of methods and information from different nature can provide tools for the diagnosis and assessment of the impact of landfills in the environment, for the investigation of the best engineering solutions to remediate them and for the possible recovery of refuse with economic interest.

Abstract
The Brazilian population increase and the purchase power growth have resulted in a widespread use of electric home appliances. Consequently, the demand for electricity has been growing steadily in an average of 5% a year. In this country, electric demand is supplied predominantly by hydro power. Many of the power plants installed do not operate efficiently from water consumption point of view. Energy Dispatch is defined as the allocation of operational values to each turbine inside a power plant to meet some criteria defined by the power plant owner. In this context, an optimal scheduling criterion could be the provision of the greatest amount of electricity with the lowest possible water consumption, i.e. maximization of water use efficiency. Some power plant operators rely on "Normal Mode of Operation" (NMO) as Energy Dispatch criterion. This criterion consists in equally dividing power demand between available turbines regardless whether the allocation represents an efficient good operation point for each turbine. This work proposes a multiobjective approach to solve electric dispatch problem in which the objective functions considered are maximization of hydroelectric productivity function and minimization of the distance between NMO and "Optimized Control Mode" (OCM). Two well-known Multiobjective Evolutionary Algorithms are used to solve this problem. Practical results have shown water savings in the order of million m(3)/s. In addition, statistical inference has revealed that SPEA2 algorithm is more robust than NSGA-II algorithm to solve this problem.

Abstract
The adoption of smart cards in urban public transport has fundamentally changed how transport providers manage and plan their networks. Traveller information services, in particular, have leveraged this contextual data for targeting passengers and providing relevant information. Thus, it becomes increasingly relevant for the next generation of services to obtain on-time contextual passenger information, to support the development of intelligent information services. In this paper an adaptation of the Top-K algorithm is proposed for predicting journey destination, applied to different scenarios in public transport. The performance and efficiency are analysed and compared to a decision tree classifier. Finally, the feasibility and potential of applying the proposed methods to large-scale systems in a real-world environment is discussed.