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
The continuous growth of wind energy integration on electrical networks has led many utilities to impose fault ride-through capability to wind farms. This means that wind turbines must remain connected to the system during severe fault occurrence. Regarding the existing wind farms equipped with fixed speed induction generators directly connected to the grid, fault ride-through capability is commonly assisted with dynamic compensation devices, such as DSTATCOM units. These power electronic devices are controlled for voltage regulation purposes and behave like a balanced three-phase voltage source converter since commonly used control techniques are based only on the positive sequence of both voltage and current measured at its connection point. These control techniques are suitable only when compensation devices are operated under balanced conditions and therefore its performance when facing unbalanced faults needs to be evaluated. This paper tackles with this subject and the results obtained through numerical simulations demonstrate that over voltages can arise on non faulty phases leading to the wind farm disconnection.

Abstract
This paper presents a new architecture for MASCEM, a multi-agent electricity market simulator. The main focus is the MASCEM ability to provide the means to model and simulate Virtual Power Producers (VPP). VPPs are represented as a coalition of agents, with specific characteristics and goals. VPPs can reinforce the importance of distributed generation technologies, mainly based on renewable energy sources, making them valuable in electricity markets. The new features are implemented in Prolog which is integrated in the JAVA program by using the LPA Win-Prolog Intelligence Server (IS) that provides a DLL interface between Win-Prolog and other applications. ©2009 IEEE.

Abstract
The Adaptive Object-Model (AOM) architectural pattern has been significantly documented in literature, but there is not yet enough documentation explaining how to design and build a full AOMbased system. A AOM framework would need to address an additional number of issues that go well beyond individual software patterns. In this paper, we propose a design for a AOM framework that addresses several issues of building AOM-based systems, namely: integrity, runtime co-evolution, persistency, user-interface generation, communication and concurrency. We borrow concepts from distributed version-control systems. We show how applications based on a concrete realization of this framework, called Oghma, helps to avoid a traditional two-level domain classification, reduces accidental complexity, and directly exposes confined model evolution to the end-user.

Abstract
This paper presents an artificial neural network approach for short-term wind power forecasting in Portugal. The increased integration of wind power into the electric grid, as nowadays occurs in Portugal, poses new challenges due to its intermittency and volatility. Hence, good forecasting tools play a key role in tackling these challenges. The accuracy of the wind power forecasting attained with the proposed approach is evaluated, reporting the numerical results from a real-world case study. © 2009 IEEE.

Abstract
Presently power system operation produces huge volumes of data that is still treated in a very limited way. Knowledge discovery and machine learning can make use of these data resulting in relevant knowledge with very positive impact. In the context of competitive electricity markets these data is of even higher value making clear the trend to make data mining techniques application in power systems more relevant. This paper presents two cases based on real data, showing the importance of the use of data mining for supporting demand response and for supporting player strategic behavior.