Abstract
This work presents the results of the characterization of lung nodules in chest Computerized Tomography for benign/malignant classification. A set of image features was used in the Computer-aided Diagnosis system to distinguish benign from malignant nodules and, therefore, diagnose lung cancer. A filter-based feature selection approach was used in order to define an optimal subset with higher accuracy. A large and heterogeneous set of 293 features was defined, including shape, intensity and texture features. We used different KNN and SVM classifiers to evaluate the features subsets. The estimated results were tested in a dataset annotated by radiologists. Promising results were obtained with an area under the Receiver Operating Characteristic curve (AUC value) of 96:2 ± 0:5% using SVM.

Abstract
Cloud computing is the latest trend in business for providing software, platforms and services over the Internet. However, a widespread adoption of this paradigm has been hampered by the lack of security mechanisms. In view of this, the aim of this work is to propose a new approach for detecting anomalies in cloud network traffic. The anomaly detection mechanism works on the basis of a Support Vector Machine (SVM). The key requirement for improving the accuracy of the SVM model, in the context of cloud, is to reduce the total amount of data. In light of this, we put forward the Poisson Moving Average predictor which is the core of the feature extraction approach and is able to handle the vast amount of information generated over time. In addition, two case studies are employed to validate the effectiveness of the mechanism on the basis of real datasets. Compared with other approaches, our solution exhibits the best performance in terms of detection and false alarm rates.

Abstract
Poker has been gradually gaining the attention of the scientific community, mostly in researchers on Artificial Intelligence. The main reason is concerned with the fact that Poker provides great challenges to the research in the area. Unlike many other games, poker is a stochastic game of imperfect information, which creates a high amount of possibilities to every state of the game. In this work a different line of thought is followed by trying to create an agent capable of reproducing the way a professional Poker human player plays for all stages in a Texas Hold'em Poker game. For this purpose, a high level data model able to comprehend the maximum of information relevant to every state of the game was built, loaded with data from a database containing millions of plays made by a professional poker players, by using Talend Data Integration. To execute Data mining techniques Weka software package was used. The final results show that it is possible to create a virtual poker player that make very similar decisions of a professional poker player.

Abstract
Social networks have an evolving characteristic because of continuous interaction between users. Existing event detection tasks do not consider the analysis under a user-centric perspective. In this paper we propose to detect node centrality events, that is the task of finding events based on the position and roles of the nodes. We present a naive algorithm for detecting such events in network streams. Moreover, we apply our proposal in a case study, showing how node centrality events can be used for tracking user preferences changes.

Abstract
In this paper an accessible Web application that uses icons instead of text to performed YouTube video search, called SAMi, is presented. With this iconic interaction Web application (SAMi), we aimed to develop universal access on the Web, by presenting an alternative way of Web search (without using text); to be a starting point for the definition of an accessible interaction metaphor, based on universal design iconography for digital environments; and ultimately, to contribute to the democratization of access to the Web for all users, regardless of the degree of literacy. The main results obtained with the user test evaluation were: first-rate performance, higher satisfaction and total autonomy in their interaction with SAMi.

Abstract
PhenoSat is a software tool that extracts phenological information from satellite based vegetation index time-series. This chapter presents PhenoSat and tests its main characteristics and functionalities using a multi-year experiment and different vegetation types – vineyard and semi-natural meadows. Three important features were analyzed: (1) the extraction of phenological information for the main growing season, (2) detection and estimation of double growth season parameters, and (3) the advantages of selecting a sub-temporal region of interest. Temporal NDVI satellite data from SPOT VEGETATION and NOAA AVHRR were used. Six fitting methods were applied to filter the satellite noise data: cubic splines, piecewise-logistic, Gaussian models, Fourier series, polynomial curve-fitting and Savitzky-Golay. PhenoSat showed to be capable to extract phenological information consistent with reference measurements, presenting in some cases correlations above 70% (n=10; p=0.012). The start of in-season regrowth in semi-natural meadows was detected with a precision lower than 10-days. The selection of a temporal region of interest, improve the fitting process (R-square increased from 0.596 to 0.997). This improvement detected more accurately the maximum vegetation development and provided more reliable results. PhenoSat showed to be capable to adapt to different vegetation types, and different satellite data sources, proving to be a useful tool to extract metrics related with vegetation dynamics. © Springer International Publishing AG 2016.