Abstract
This paper presents the architecture that supports the collaborative model ACEM (Advanced Collaborative Educational Model) to assist educators in the collaborative design of learning activities, supported by a high-level graphical tool. ACEM embraces the research areas of Computer Supported Cooperative Work (CSCW) and Learning Design (LD). Some facilities are considered in order to implement the online interactions between educators, namely a shared whiteboard and a conversation room. A workflow descriptive model of the educators' teamwork is also introduced.

Abstract
Brain Computer Interfaces (BCI) enables interaction between users and hardware systems, through the recognition of brainwave activity. However, the current BCI systems still have a very low accuracy on the recognition of facial expressions and thoughts. This makes it very difficult to use these devices to enable safe and robust commands of complex devices such as an Intelligent Wheelchair. This paper presents an approach to expand the use of a brain computer interface for driving an intelligent wheelchair by patients suffering from cerebral palsy. The approach was based on appropriate signal preprocessing based on Hjorth parameters, a forward approach for variable selection and several data mining algorithms for classification such as naive Bayes, neural networks and support vector machines. Experiments were performed using 30 individuals suffering from IV and V degrees of cerebral palsy on the Gross Motor Function (GMF) measure. The results achieved showed that the preprocessing and variable selection methods were effective enabling to improve the results of a commercial BCI product by 57%. With the developed system it was also possible for users to perform a circuit in a simulated environment using just facial expressions and thoughts.

Abstract
A soccer game can be seen as a confrontation between two teams of agents where each player, communicating with his teammates, try to interpret in the best way as possible the game situations, achieving its main goals. Today the most important factors in a soccer clubs life and in its coach success are the game results they achieve. They represent the success of the club and in many cases the coachs future. Because of that club coaches usually use automated tools to measure their teams performance all over a soccer competition. Based only in Cartesian coordinates and in a sequential time frame analysis, this research work presents an automatic tool capable to calculate many technical aspects in a soccer match. For the validation tool process, games of simulation 2d RoboCup international competition were used. The results achieved were quite satisfactory. In what concerns to the set of statistics collected more than 92% of the total events were detected and only for the shot event this number dropped to between 74% and 85%. The future work will be concerned in incorporating this project with a real time tracking system and increasing the number of technical aspects calculated by the system. © 2010 IEEE.

Abstract
Machine Learning (ML) and Knowledge Discovery (KD) are research areas with several different applications but that share a common objective of acquiring more and new information from data. This paper presents an application of several ML techniques in the identification of the opponent team and also on the classification of robotic soccer formations in the context of RoboCup international robotic soccer competition. RoboCup international project includes several distinct leagues were teams composed by different types of real or simulated robots play soccer games following a set of pre-established rules. The simulated 2D league uses simulated robots encouraging research on artificial intelligence methodologies like high-level coordination and machine learning techniques. The experimental tests performed, using four distinct datasets, enabled us to conclude that the Support Vector Machines (SVM) technique has higher accuracy than the k-Nearest Neighbor, Neural Networks and Kernel Naïve Bayes in terms of adaptation to a new kind of data. Also, the experimental results enable to conclude that using the Principal Component Analysis SVM achieves worse results than using simpler methods that have as primary assumption the distance between samples, like k-NN. © 2010 IEEE.

Abstract

Abstract
The present paper describes a Distributed Surveillance System that has the ability to detect, track and snapshot subjects moving around in a certain space. The system is composed by several surveillance agents and a central surveillance agent which communicates with them and process data. The surveillance agents are composed by a camera and a computer with wireless communication. The central surveillance agent runs on a computer also with wireless communication. In order to support the communication between the two types of agents, was created a language called VigilLANG. This language allows a high-level communication interface between the several surveillance agents and the central surveillance agent. The proposed surveillance system performs robust image segmentation providing the user images with the relevant information; provides robust subject detection and identification; supports expansion; etc. The system is totally configurable through the definition of new surveillance policies and may be easily expanded through the addition of new surveillance agents. The system was validated by performing a vast set of experiments, achieving very good results in the detection and position estimation of the subjects under surveillance.