Abstract
The problem of selecting learning algorithms has been studied by the meta-learning community for more than two decades. One of the most important task for the success of a meta-learning system is gathering data about the learning process. This data is used to induce a (meta) model able to map characteristics extracted from different data sets to the performance of learning algorithms on these data sets. These systems are built under the assumption that the data are generated by a stationary distribution, i.e., a learning algorithm will perform similarly for new data from the same problem. However, many applications generate data whose characteristics can change over time. Therefore, a suitable bias at a given time may become inappropriate at another time. Although meta-learning has been used to continuously select a learning algorithm in data streams, data characterization has received less attention in this context. In this study, we provide a set of guidelines to support the proposal of characteristics able to describe non-stationary data over time. This guidance considers both the order of arrival of the examples and the type of variables involved in the base-level learning. In addition, we analyze the influence of characteristics regarding their dependence on data morphology. Experimental results using real data streams showed the effectiveness of the proposed data characterization general scheme to support algorithm selection by meta-learning systems. Moreover, the dependent metafeatures provided crucial information for the success of some meta-models.

Abstract
A simple and inexpensive POS for application to light airborne platforms was developed, and a modified Kalman Filtering was designed to integrate GNSS/IMU/Image data, which uses the relative orientation information to improve the accuracy of the exterior orientation parameters. The precise relative orientation of conjugate images was obtained using a SIFT/SFM matching algorithm. The relative exterior orientations were transformed from the camera frame to the navigation frame before they were used as external update information of the Kalman Filter. Combining all the relative orientation information retrieved from images, the Kalman Filter can give an improved output for the exterior orientation parameters. Airborne result from the tests of one straight strip shows that the heading accuracy of a GNSS/MEMS-IMU was improved from 0.26 degrees to 0.10 degrees, and the result from one closed strip shows that heading accuracy was improved from 1.11 degrees to 0.85 degrees and roll accuracy from 0.54 degrees to 0.43 degrees.

Abstract

Abstract
Fast cardiac imaging requires a reduction of the number of transmit events. This is typically achieved through multiline-transmission and/or multiline-acquisition techniques but restricting the field-of-view to the anatomically relevant domain, e.g. the myocardium, can increase frame rate further. In the present work, an anatomical scan sequence was implemented and tested experimentally by performing real-time segmentation of the myocardium on conventional B-mode and feeding this information back to the scanner in order to define a fast myocardial scan sequence. Ultrasound imaging was performed using HD-PULSE, an experimental fully programmable 256 channel ultrasound system equipped with a 3.5MHz phased array. A univentricular polyvinyl alcohol phantom was connected to a pump to simulate the cardiac cycle to perform in vitro validation of this approach. Three volunteers were also imaged from an apical 4-chamber view to analyse the feasibility of this method in vivo. It is shown that this method is feasible to be applied in real-time and in vivo giving a minimum frame rate gain of 1.5. Although the anatomical image preferably excludes the apical cap of the ventricle, this region is often unanalyzable due to near field clutter anyway. The advantage of this method is that spatial resolution is maintained when compared to conventional ultrasound in contrast to other fast imaging approaches. © 2017 IEEE.

Abstract
In this work it is presented a system to help the users to maintain an active lifestyle. Our main objective is to evaluate the current mobile technologies for the development of systems to monitor the users' health and to promote a healthy lifestyle. It was developed a full system, including: an application for smartwatch; an application for smartphone; a back-end with a webservice in PHP. The application provides the functionalities to acquire the user's: heart rate; location, based on the GPS position; the number of steps; the position's elevation; etc. The back-end is used to register the data acquired and processed by the applications. The design was user centric and the development methodology was based on the agile paradigm, for which are described three development iterations.

Abstract
Portuguese Higher Education Institutions have more and more data that needs to be processed in order to get information and, therefore, Knowledge. In order to respond to this need, over time there have been several types of IS supported by ICT, which enables them to achieve these features and, at the same time, help with their daily activities. However, the continuous evolution of this technological component has led to a current high degree of complexity, from which the Information Systems Architectures emerged as means of increasing the effectiveness of its management and maintenance. Using the University of Tras-os-Montes e Alto Douro as a case study, the research team proposed a generic ISA that enabled it to have a transversal vision of its IS, allowing the validation of existence/need IS focused on Information Management and decision-making under a multidimensional perspective, i.e., geared towards the various organizational levels, since the Operational level to the Strategic level, taking into account the information needs associated with each player.