Abstract
In clinical practice, high-resolution computed tomography (HRCT) is a reference in the diagnosis, quantification, and follow-up of lung emphysema. In this study, differential lacunarity analysis was applied to HRCT images of the chest in order to quantify the texture of healthy and emphysematous regions of the lung parenchyma. The used approach to compute lacunarity is a multiscale technique that takes advantage of the extensive scale used in the acquisition of CT images. The results show that the extracted features are discriminatory of the considered lung patterns, being suitable to integrate clinical applications for the characterization of disease patterns in HRCT images.

Abstract
The analysis and interpretation of high-resolution computed tomography (HRCT) images of the chest in the presence of interstitial lung disease (ILD) is a time-consuming task which requires experience. In this paper, a computer-aided diagnosis (CAD) scheme is proposed to assist radiologists in the differentiation of lung patterns associated with ILD and healthy lung parenchyma. Regions of interest were described by a set of texture attributes extracted using differential lacunarity (DLac) and classical methods of statistical texture analysis. The proposed strategy to compute DLac allowed a multiscale texture analysis, while maintaining sensitivity to small details. Support Vector Machines were employed to distinguish between lung patterns. Training and model selection were performed over a stratified 10-fold cross-validation (CV). Dimensional reduction was made based on stepwise regression (F-test, p value < 0.01) during CV. An accuracy of 95.8 +/- 2.2% in the differentiation of normal lung pattern from ILD patterns and an overall accuracy of 94.5 +/- 2.1% in a multiclass scenario revealed the potential of the proposed CAD in clinical practice. Experimental results showed that the performance of the CAD was improved by combining multiscale DLac with classical statistical texture analysis.

Abstract
In communication systems, transient faults will eventually occur. Thus, some mechanism is necessary to handle them and achieve appropriate levels of reliability, particularly in safety-critical systems. One possibility is to rely on temporal redundancy, i.e., using message retransmissions. General requirements for such a mechanism would include a parsimonious use of extra bandwidth while guaranteeing the schedulability of the message set. In this paper we propose using on-line traffic scheduling together with scheduling servers to recover message errors in time-triggered systems on Controller Area Network (CAN), taking advantage of the Flexible Time-Triggered CAN protocol. This novel mechanism is shown to offer a desired error recovery latency using much less extra bandwidth than typical approaches used in time-triggered systems. In this paper we present this novel error recovery mechanism, including a thorough characterization as well as configuration guidelines, namely concerning how to choose the server parameters (type, period and capacity). The correctness of the proposed approach and its superior performance are validated with simulation using several communication benchmarks available in the literature.

Abstract
The objective of the project presented in this paper is to stimulate and evaluate the executive function in Parkinson's patients. This project is being developed in partnership with the Coimbra Hospital and Universitary Centre and the private social solidarity institution CASPAE. It aims to answer specific needs identified in the neurology service during the medical appointments. A common test to assess executive function is the Trail Making Test (TMT). This test is done on paper during the medical appointments for the diagnosis and follow-up of patients with the executive function diminished, such as Parkinson's disease patients. The way the TMT is done poses some problems that led to the development of an application for smartphones and tablets, with Android OS. This application has two operating modes: "Appointment", and "Train". The "Appointment Mode" makes the realization, reading, and the organization of the tests results easier. The "Train Mode" allows that patients improve their executive function performing tests that are randomly generated on your own smartphone.

Abstract
Assistive technology enables people to achieve independence in the accomplishment of their daily tasks and enhance their quality of life. Visual information is the basis for most navigational tasks, so visually impaired individuals are at disadvantage due to the lack of information or given insufficient information about their surrounding environment. With the recent advances in inclusive technology it is possible to extend the support given to people with visual disabilities during their mobility. In this context we propose a new algorithm to recognize landmarks suitably placed on sidewalks. The proposed algorithm uses a combination of Peano-Hilbert Space Filling Curves for dimension reduction of image data and Ensemble Empirical Mode Decomposition (EEMD) to pre-process the image, resulting on a fast and efficient recognition method and revealing a promising solution.

Abstract
High-resolution computed tomography (HRCT) became an essential tool in detection, characterization and follow-up of lung diseases. In this paper we focus on lung emphysema, a long-term and progressive disease characterized by the destruction of lung tissue. The lung patterns are represented by different features vectors, extracted from statistical texture analysis methods (spatial gray level dependence, gray level run length method and gray level difference method). Support vector machine (SVM) was trained to discriminate regions of healthy lung tissue from emphysematous regions. The SVM model optimization was performed in the training dataset through a cross validation methodology, along a grid search. Three usual kernel functions were tested in each of the features sets. This study highlights the importance of the kernel choice and parameters tuning to obtain models that allow high level performance of the SVM classifier.