Abstract
In lung cancer diagnosis, the design of robust Computer Aided Diagnosis (CAD) systems needs to include an adequate differentiation of benign from malignant nodules. This paper presents a CAD system for the classification of lung nodules in chest Computed Tomography (CT) scans as the way to diagnose lung cancer. The proposed method measures a set of 295 heterogeneous characteristics, including morphology, intensity or texture features, that were used as input of different KNN and SVM classifiers. The system was modeled and trained using a groundtruth provided by specialists taken from a public lung image dataset, the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). This image dataset includes chest CT scans with lung nodule location together with information about the degree of malignancy, among other properties, provided by multiple expert clinicians. In particular, the computed degree of malignancy try to follow the manual labeling by the different radiologists. Promising results were obtained with a first order SVM with an exponential kernel achieving an area under the receiver operating characteristic curve of 96.2 +/- 0.5% when compared with the groundtruth provided in the public CT lung image dataset.

Abstract
Feature selection and feature ranking are two aspects of the same learning task. They are well studied in batch scenarios, but not in the streaming setting. This paper presents a study on feature ranking from data streams in online learning regression models. The main challenge here is the relevance of features might change over time: features relevant in the past might be irrelevant now and vice-versa. We propose three new online feature ranking algorithms designed for Hoeffding algorithms. We have implemented the three methods in AMRules, a streaming regression algorithm to learn model rules. We compare their behaviour experimentally and present the pros and cons of each method. Copyright 2017 ACM.

Abstract
Different XML formats are widely used for data exchange and processing, being often necessary to mutually convert between them. Standard XML transformation languages, like XSLT or XQuery, are unsatisfactory for this purpose since they require writing a separate transformation for each direction. Existing bidirec- tional transformation languages mean to cover this gap, by allowing programmers to write a single program that denotes both transformations. However, they often 1) induce a more cumbersome programming style than their traditionally unidirectional relatives, to establish the link between source and target formats, and 2) offer limited configurability, by making implicit assumptions about how modifications to both formats should be translated that may not be easy to predict. This paper proposes a bidirectional XML update language called BiFluX (BIdirectional FunctionaL Updates for XML), inspired by the Flux XML update language. Our language adopts a novel bidirectional programming by update paradigm, where a program succinctly and precisely describes how to update a source document with a target document in an intuitive way, such that there is a unique "inverse" source query for each update program. BiFluX extends Flux with bidirectional actions that describe the con- nection between source and target formats. We introduce a core BiFluX language, and translate it into a formally verified bidirectional update language BiGUL to guarantee a BiFluX program is well-behaved.

Abstract
The world is moving towards to the fourth industrial revolution, usually linked with the Industrie 4.0 initiative, enables the digitization of manufacturing factories by using Cyber-Physical Systems and emergent technologies like Internet of Things and Internet of Services. The seamless reconfiguration of these complex industrial cyber-physical systems is an important challenge for the complete implementation of this revolution, being necessary to re-think the way such mechanisms can be designed and engineered. This paper presents an agent based reconfiguration system for the dynamic and seamless reconfiguration of a physically-reconfigurable modular micro-flow production system in the area of manufacturing of aerospace engine components.

Abstract
Relevance is usually estimated by search engines using document content, disregarding the user behind the search and the characteristics of the task. In this work, we look at relevance as framed in a situational context, calling it situational relevance, and analyze if it is possible to predict it using documents, users and tasks characteristics. Using an existing dataset composed of health web documents, relevance judgments for information needs, user and task characteristics, we build a multivariate prediction model for situational relevance. Our model has an accuracy of 77.17%. Our findings provide insights into features that could improve the estimation of relevance by search engines, helping to conciliate the systemic and situational views of relevance. In a near future we will work on the automatic assessment of document, user and task characteristics.

Abstract