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.

Abstract
Computed tomography (CT) can contribute to the early detection of lung diseases like emphysema, a chronic and progressive disease. Texture-based methods can be explored to classify regions of interest (ROI's) into emphysematous areas and normal areas. In this work we evaluated the importance of a set of parameters in the classification of lung CT images, such as the size of the ROIs, the quantization level, and textural features used in classification. A support vector machine was used as classifier. The performance of the designed classifier was evaluated using a 10-fold cross validation method and the results compared based on overall accuracy, sensibility and specificity. This study shows that textural features have a good discriminatory power in the classification of lung emphysema in CT images.

Abstract
The purpose of the described system is to aid radiologists on their daily routine in the task of analyzing HRCT lung images and to contribute to a more accurate and fast diagnosis. We developed a framework - Study Lung Tool-with the objective of gather information from radiologists, in a systematic way. Using Study Lung Tool framework, the radiologist analyzes HRCT scans, outlines regions of typical pattern and characterizes the patterns. A database of typical patterns associated with common pulmonary diseases was created. The information gathered can be a valuable teaching tool to every one that intends to understand HRCT lung parenchyma. The proposed system discriminates between normal and abnormal patterns of lung parenchyma based on statistical texture analysis extracted from HRCT lung scans. An overall accuracy of 89,2%, a sensitivity of 92,7% and a specificity of 83,6% were achieved.

Abstract
In this paper is presented a project -CAD Lung System- whose objective is to help radiologists in their daily routine, in the HRCT images analysis of lung parenchyma. A database of abnormal lung patterns and their reliable classification is a determinant part of the system. We developed a framework -Study Lung Tool- with the objective of gather information from radiologist, in a systematic way. Using this framework, the radiologist analyses HRCT scans, outlines regions of typical pattern and characterizes the pattern. This framework can also be used as a learning tool through the observation of the HRCT scans previously characterized by experts.

Abstract
Distributed Embedded Systems are subject to transient communication faults that need being detected and mitigated in safety-critical scopes. This paper addresses error recovery in time-triggered systems based on the Controller Area Network (CAN). It extends a recent work that proposed using online traffic scheduling, combined with servers, to implement dynamic message retransmissions. In particular, we provide a schedulability analysis that considers the interference of the error-recovery server in the time-triggered traffic, as well as a methodology to compute the worst-case response time of messages affected by errors. We also present a comparison with related error-recovery methods that confirms the superiority of the proposed method. © 2013 IEEE.

Abstract
Distributed systems rely in communication networks, typically a bus, in order to exchange messages and fulfill their goals. However, message transmission is subject to interferences that ultimately can lead to message corruption. In systems where a high-reliability is sought, error recovery mechanisms can be deployed in order to give the required reliability level, and this can be done in the spatial or temporal domain. In the scope of the FTT paradigm, and applied to the FTT-CAN protocol, the authors have previously presented a time domain recovery method using message retransmissions controlled by a server. In this article we assess the impact of different scheduling policies for the server, presenting a qualitative evaluation of the alternatives, complemented by a simulation study, in order to verify their advantages and weak points.