Abstract
Motion sensing plays an important role in the study of human movements, motivated by a wide range of applications in different fields, such as sports, health care, daily activity, action recognition for surveillance, assisted living and the entertainment industry. In this paper, we describe how to classify a set of human movements comprising daily activities using a wearable motion capture suit, denoted as FatoXtract. A probabilistic integration of different classifiers recently proposed is employed herein, considering several spatiotemporal features, in order to classify daily activities. The classification model relies on the computed confidence belief from base classifiers, combining multiple likelihoods from three different classifiers, namely Na < ve Bayes, artificial neural networks and support vector machines, into a single form, by assigning weights from an uncertainty measure to counterbalance the posterior probability. In order to attain an improved performance on the overall classification accuracy, multiple features in time domain (e.g., velocity) and frequency domain (e.g., fast Fourier transform), combined with geometrical features (joint rotations), were considered. A dataset from five daily activities performed by six participants was acquired using FatoXtract. The dataset provided in this work was designed to be extremely challenging since there are high intra-class variations, the duration of the action clips varies dramatically, and some of the actions are quite similar (e.g., brushing teeth and waving, or walking and step). Reported results, in terms of both precision and recall, remained around 85 %, showing that the proposed framework is able to successfully classify different human activities.

Abstract
Matrix and data manipulation programming languages are an essential tool for data analysts. However, these languages are often unstructured and lack modularity mechanisms. This paper presents a business intelligence approach for studying the manifestations of lack of modularity support in that kind of languages. The study is focused on MATLAB as a well established representative of those languages. We present a technique for the automatic detection and quantification of concerns in MATLAB, as well as their exploration in a code base. Ubiquitous Self Organizing Map (UbiSOM) is used based on direct usage of indicators representing different sets of tokens in the code. UbiSOM is quite effective to detect patterns of co-occurrence between multiple concerns. To illustrate, a repository comprising over 35, 000 MATLAB files is analyzed using the technique and relevant conclusions are drawn.

Abstract
Higher Education Institutions (HEIs) have come a long way on the usage of Information Systems (IS) at the several phases of the execution of their business plan. These organizations are very peculiar in the sense that most of the IS technologies have been developed as a consequence of the research work of the HEIs, positioning them as creators and as consumers of IS technologies. In fact, a considerable part of the IS products, currently available for the education sector, was initially created in a HEI as an in-house development. For these reason, the adoption of IS technologies by HEIs has followed two distinct paths: the in-house creation, previously described; and a current market adoption, similarly to most other companies IS adoption. Up to 2013 the IS applications for HEIs was mostly provided as web applications running on the HEI local datacenters and devoted to some specific phases of the HEI business plan. Currently, in 2016, this scenario has evolved in two ways: (i) to a wider range of type of applications, including: the old type of web application; new mobile applications; and new web application, running on the cloud and used as a service, (ii) to a more extended support coverage regarding the HEI business model phases, i.e., there are more IS applications supporting more aspects of the HEIs’ activities. In 2013, it was published a study regarding the accessibility support in HEI IS applications and related user practices. Due to the advances in IS technologies and their adoption by HEIs, it is now time to update this perspective on accessibility and HEIs IS, in order to assess how the progresses on IS applications used in HEIs have dealt with the accessibility concerns. The study updates the IS accessibility features as well as the new systems and new types of systems currently in use. © Springer International Publishing AG 2017.

Abstract
Feature Selection is important to improve learning performance, reduce computational complexity and decrease required storage. There are multiple methods for feature selection, with varying impact and computational cost. Therefore, choosing the right method for a given data set is important. In this paper, we analyze the advantages of metalearning for feature selection employment. This issue is relevant because a wrong decision may imply additional processing, when FS is unnecessarily applied, or in a loss of performance, when not used in a problem for which it is appropriate. Our results showed that, although there is an advantage in using metalearning, these gains are not yet sufficiently relevant, which opens the way for new research to be carried out in the area.

Abstract
Portugal is seen worldwide as a case of success in the large-scale integration of renewables in its power system, especially for wind power. Consistent policies and sound management decisions are fundamental, but a sustainable process is not possible without the development of endogenous knowledge. This paper summarizes a set of models, both applied by the industry and representing actual technologic advancement, denoting the context of research and innovation in the country that helps to explain such success. Novelties arise in reliability assessment for systems with renewables, active and reactive power control, integration of wind farms, storage, electric vehicle integration, wind and solar power forecasting and distribution operation and state estimation taking advantage of smart grid structures. In all cases, one relevant trait is evident: the pervasive use of computational intelligence tools.

Abstract
This paper presents an accessible platform for the automatic creation of icons through a simple (web) form. The platform allows the creation of personalized icons that can be used as a navigation or search option in web context replacing the usual text keyword metaphor. With the development of this platform we aimed to provide a simpler automatic method of icon creation, allowing users to personalize their icons and share them with others. The icons created are stored in a database that can be used in different Web or digital contexts. As a proof of concept, the platform was integrated with an existing Web application for video searching in the YouTube platform through icons hyperlinks: SAMi [1]. The resulting integrated platform was assessed for usability (user tests) and accessibility (with an automatic assess tool). The results showed the interface is accessible to a group of people with intellectual disabilities, increasing their performance, satisfaction, motivation and autonomy. © Springer International Publishing AG 2017.