Abstract
Recently there has been a growing interest by the sports' community (educators and coaches) in analyzing efficiently the performance of handball players and teams. The information collected from such analysis is used to better understand the difficulties of trainees, players or even entire teams and formulate adequate training and strategic plans. Usually this evaluation is too self contained and does not explore the many tools there are available nowadays. This paper proposes a simulation tool to tackle this problem and establishes the bases for a Handball Sport Simulator. The simulator developed has its origins on the Soccer Server simulator used on the RoboCup competition and includes the main handball game rules and player actions. This paper establishes the ground foundations for a Handball Simulator and results show that the handball rules and actions can be modeled.

Abstract
The goal of this paper is to discuss the usage of distributed architecture for the Lego NXT robots. This platform is very interesting because it provides standard hardware for configurable mounting of several sensors and actuators. The presented work characterizes sensors and actuators and identifies limitations of the stand-alone architecture. In order to maximize usefulness and go beyond the identified limitations, a distributed computing architecture was developed that allows the Lego NXT to address complex missions. The distributed architecture makes use of two different programming environments. The described architecture was tested in a sample self localization task.

Abstract
This paper intends to demonstrate the development of and easy-to-use local human-machine interface that would allow any user to control all kinds of service robots intuitively. This interface is based on the Nintedo Wii remote controller and consists of three operating modes: a steering wheel, an infra-red monitor and a movement identifier. These modes were tested on a cleaning robot and they led to very satisfactory results, proving that the Wiimote is an inexpensive and interesting way of making this kind of interfaces.

Abstract
Interactive whiteboards are gaining importance in our society, both at a business level and, especially, at an educational level. However, the products offered by the major manufacturers have a major barrier to their acquisition: very high prices. There is an urgent need to use new technologies in order to provide solutions that present the same performance levels than typical interactive whiteboards, but with a significantly reduced cost. Throughout this paper the steps taken for the development of an innovative low-cost interactive whiteboard are described. The proposed system is based on the Wii Remote command of the Nintendo Wii video-game console. This command, although very inexpensive has an infrared camera, and supports Bluetooth communication. The system control is based on a wireless device, based on infrared emitters, which supports most of the mouse events. A complete whiteboard application was also developed using Borland Delphi for Windows. This application may be used with either one or two Wiimotes and has a very simple and efficient calibration method. The application also includes viewing capabilities of some of the Wiimote characteristics, as well as a flexible Notebook to increase its range of possible uses. The results obtained through a survey conducted to a small set of whiteboard users were very positive indicators about the acceptance of the inexpensive solution proposed.

Abstract
The amount of data produced by distributed devices, such as smart devices and the IoT, is increasing continuously. The cost of transmitting data and also distributed computing power raise interest in distributed data mining (DDM). However, in a pure DDM scenario, data availability may not be enough to generate reliable models in a distributed environment. So, the ability to exchange data efficiently and effectively will become a crucial component of DDM. In this paper, we propose the concept of the Machine Learning Data Market (MLDM), a framework for the exchange of data among autonomous agents. We consider a set of learning agents in a cooperative distributed ML, where agents negotiate data to improve the models they use locally. In the proposed data market, the system's predictive accuracy is investigated, as well as the economic value of data. The question addressed in this paper is: How data exchange among the agents will improve the accuracy of the learning model. Agent budget is defined as a limitation of negotiation. We defined a multi-agent system with negotiation and assessed it against the multi-agent system baseline and the single-agent system. The proposed framework is analyzed based on the different sizes of batch data collected over time to find out how this changes the effect of the negotiation on the accuracy of the model. The results indicate that even simple negotiation among agents increases their learning accuracy.

Abstract