Abstract
Human pressure is pushing many of our natural resources to their limits in various regions of the world. Optimize their use is an urgent need. The management of agro-industry has been aware of that need, seeking to improve the productivity and reduce waste throughout the production process, as well by increasing the distribution efficiency of their products. Information and Communication Technologies (ICT) can support the control/management of the process inputs and outputs in various activities. This article attempts to describe a complete mushroom production chain. The information system developed by the agro-industry company studied allows to acquire, in real-time, the information about what is being produced (quantity and type of mushroom), which products are to be delivered to the different clients and which should be the planning for the next few days. © 2011 AISTI.

Abstract
Computer games are attracting increasing interest in the Artificial Intelligence (AI) research community, mainly because games involve reasoning, planning and learning [1]. One area of particular interest in the last years is the creation of adaptive game AI. Adaptive game AI is the implementation of AI in computer games that holds the ability to adapt to changing circumstances, i.e., to exhibit adaptive behavior during the play. This kind of adaptation can be created using Machine Learning techniques, such as neural networks, reinforcement learning and bioinspired methods. In order to learn online, a system needs to overcome the main difficulties imposed by games: processing time and memory requirements. Learning in a game needs to be fast and the memory available is usually not enough to store a large number of training examples to a traditional Machine Learning technique. In this context, methods for mining data streams seem to be a natural approach. Data streams are, by definition, sequences of training examples that arrive over time [2]. In the data stream scenario, algorithms are usually incremental and capable of adapting the decision model when a change in the distribution of the training examples is detected. One particularly interesting algorithm for mining data streams is the Very Fast Decision Tree (VFDT) [3]. VFDTs are incremental decision trees designed specifically to meet the data stream problem requirements. In this paper, we analyse the use of VFDTs in the task of learning in a Computer RolePlaying Game context. First, we simulate data from manually designed tactics for a Computer RolePlaying Game, based on Spronck's static tactics [4], and test the suitability of VFDT to rapid learn these tactics. Afterwards, we conduct an experiment in order to simulate a data stream of examples where changes of tactics occur over time, and analyse how VFDT and some of its variations respond to these changes in the target concept. © 2010 IEEE.

Abstract
The internet and technological advancements have revolutionized the way in which business and commerce is conducted nowadays. A lot has changed since the traditional over the counter form of trade to the electronic form of trade. The latter in which data is transferred electronically. E-businesses are beginning to examine the benefits of using Web 2.0, especially in the form of social networking sites, to collaborate with business partners and to communicate with consumers and potential employees. In order to create, possibly in the near future, a platform for selling services and typical Portuguese products, throughout this project various online companies' websites', which sell products and services, were analyzed. Other than analyze website characteristics we also tried to understand how these are sustained and how they interact with social networking services. © 2011 AISTI.

Abstract
In this article, we propose a linear parameterization (LP) for representing the friction in the tire-road interface, suitable for on-line Identification. This model was obtained by employing function approximation techniques, which results in an optimization problem to minimize the fitting error between the LP and the nonlinear Burckhardt model. Compared with others LPs proposed in the literature, the optimal LP features a reduced number of parameters and good approximation capabilities. Moreover, the proposed model can be identified though linear Identification techniques, simplifying the on-line peak friction estimation. Simulation results obtained with a vehicle simulator demonstrates the effectiveness of the proposed parameterization. © 2011 IFAC.

Abstract
Using the new trend of energy harvesting, an envisioned electromagnetic power transducer that uses human gait to produce electrical energy is presented as a solution to energize biomedical devices. Regardless of the walking speed, starting at 0.7 Hz, it is possible to store a total energy of 2.2 mJ, using two 1000 mu F capacitors as energy storage elements. Afterwards, this energy becomes available to the telemetric system through an efficient power management module. Since the end application, an implantable biomedical telemetric system, needs a total of 360 mu J to operate, the here presented power transducer is well suited for implant power needs.

Abstract
Companies today live in a context of cycles in which there is an increasingly competitive and shorter life cycles for products and services, such as requiring a deep knowledge of customers and suppliers. The electronic business is one way to structure all the processes of the organization supported by Information and Communication Technologies (ICT) that allow a direct connection with customers, business partners, employees and its own management. This paper is a reflection on whether the e-business maturity models will fit the new reality of electronic business, in which the social networks are turning into a "social business". © 2011 AISTI.