Search

Serious games are computer games with specific purposes, such as: training, learning, valuation etc. These games connect the fun of common videogames with features like decision making, assessment systems and educational planning in order to create an engaging learning environment. So these aspects create endless possibilities of use in those games and attract attention from other areas of knowledge. Therefore, the design process becomes increasingly complex and involves multidisciplinary teams. This paper presents an interdisciplinary study conducted to define an approach based on communication for the development of a serious game for dentistry, specifically oral health in babies. We intend to evaluate what is the best approach to be applied to the script of the game in order to define the good way to present the content. In this paper, the “communication approach” term joins features such as: game play, game design, interaction, narrative, story genre and script. In this project, it was necessary to evaluate which Planejamento de um Serious game Voltado para Saude Bucal em Bebes 160 RITA • Volume 18 • Numero 1 • 2011 communication approach is appropriate in a serious game aimed at mothers. We developed two prototypes to test different communication approaches. At the end of the test stage, the mothers answered a form to evaluate the most appropriate communication approach. The data were analyzed through absolute and percentage values. Finally we decided adopt a Playful Approach, because the mothers felt more encouraged to finalize this application compare

Student dropout is one of the main problems faced by distance learning courses. One of the major challenges for researchers is to develop methods to predict the behavior of students so that teachers and tutors are able to identify at-risk students as early as possible and provide assistance before they drop out or fail in their courses. Machine Learning models have been used to predict or classify students in these settings. However, while these models have shown promising results in several settings, they usually attain these results using attributes that are not immediately transferable to other courses or platforms. In this paper, we provide a methodology to classify students using only interaction counts from each student. We evaluate this methodology on a data set from two majors based on the Moodle platform. We run experiments consisting of training and evaluating three machine learning models (Support Vector Machines, Naive Bayes and Adaboost decision trees) under different scenarios. We provide evidences that patterns from interaction counts can provide useful information for classifying at-risk students. This classification allows the customization of the activities presented to at-risk students (automatically or through tutors) as an attempt to avoid students drop out.

The scheduling of tasks in a parallel program is an NP-complete problem, where scheduling tasks over multiple processing units requires an effective strategy to maximize the exploitation of the parallel hardware. Several studies focus on the scheduling of parallel programs described into DAGs (Directed Acyclic Graphs). However, this representation does not describe a multithreaded program suitably. This paper shows the structure and semantics of a DCG, an abstraction which describes a multithreaded program, and proposes standards to map structures found in DAGs into segments of a DCG. A graph grammar has been developed to perform the proposed transformation and case studies using DAGs found in the literature validate the transformation process. Besides the automatic translation and precise definition of the mapping, the use of a formal language also allowed the verification of the existence and uniqueness of the out coming model.

Coordination is one of the key issues in cooperative multiagent systems and it also plays an essential role in disaster management. Task allocation is an important phase of the coordination problem, since the decomposition of the objective into tasks is the most natural way to organize work among agents. In this paper, we propose a hybrid task allocation approach that considers the existence of both local and global information in order to coordinate the agents in the RoboCup Rescue. Moreover, we present a comparative analysis between the results obtained by the agents that use the proposed approach and ones obtained by the sample agents provided within the RoboCup Rescue simulator, that follow a decentralized and greedy approach.

The availability of large and complex data sets has shifted the focus of pattern recognition towards developing techniques that can efficiently handle these types of data sets. For example, Multiple Classifier Systems claim their ability in reducing the error and complexity of classification by partitioning the data space and combining classifiers predictions. However, it is not an easy task to generate several partitions and moreover to use them in an efficient manner. Another difficult aspect is related to the exchange of training data in different formats among systems to combine classifiers of different and heterogeneous systems. This paper presents a model and structure of training samples based on XML (eXtensible Markup Language) to facilitate the partitioning and exchange among different image classification system. The main contribution is to apply the flexibility of XML that addresses interoperability and communication among heterogeneous systems in partitioning data sets as well as to facilitate interchange of such sets among image processing and pattern recognition systems.

Casting digital-controlled light over real object surfaces, thus creating new textures and special effects, brings to designers and engineers an endless spectrum of possibilities and innovation for their projects. This technology, called Spatial Augmented Reality, can be considered as a kind of "virtual material" that can be manipulated by designers in augmented environments. In order to achieve more knowledge on the use of this technology, we have developed AR X-Ray, a spatial augmented reality tool. Through the use of a portable projector a Virtual X-Ray is emitted over real walls, allowing visual exploration of internal details of buildings (such as pipes and ducts). This paper presents the design, implementaion and results of this project. Some details regarding solutions for technical problems are also discussed, as following: projector tracking, proper registration of synthetic information over real objects and the development of a shader that manipulates the transparency of textures to allow the user to view what is behind objects.

Data gloves are devices equipped with sensors that capture the movements of the hand of the user in order to select or manipulate objects in a virtual world. Data gloves were introduced three decades ago and since then have been used in many 3D interaction techniques. However, good data gloves are too expensive and only a few of them can perceive the full set of hand movements. In this paper we describe the design of an image-based data glove (IBDG) prototype suitable for finger sensible applications, like virtual objects manipulation and interaction approaches. The proposed device uses a camera to track visual markers at finger tips, and a software module to compute the position of each finger tip and its joints in real-time. To evaluate our concept, we have built a prototype and tested it with 15 volunteers. We also discuss how to improve the engineering of the prototype, how to turn it into a low cost interaction device, as well as other relevant issues about this original concept.

Neste artigo propomos um modelo multifractal de tráfego baseado em uma cascata multiplicativa que apresenta diferentes distribuições para os multiplicadores em cada estágio da cascata. Neste modelo, os multiplicadores são obtidos através da estimação de suas densidades de probabilidade com o uso dos métodos de Kernel e Aceitação/Rejeição aplicados a tráfego real de redes. Com o intuito de validar o modelo, realizamos análises estatísticas e do comportamento de fila dos processos de tráfego gerados segundo o modelo proposto. Verificamos também o desempenho do modelo em capturar as características dos traços reais de tráfego em comparação à outros modelos multifractais., In this paper we propose a multifractal traffic model that is based on a multiplicative cascade presenting specific multiplier distributions in each cascade stage. In the proposed model, the multipliers are obtained through the estimate of their probability densities found in real network traffic by using Kernel and Acceptance/Rejection methods. Statistical analysis and queueing behavior study were carried out for the model validation. Furthermore, we verify the model performance in capturing the traffic trace characteristics in comparison to other multifractal models.

Several problems involve the classification of data into categories, also called classes. Given a dataset containing data whose classes are known, Machine Learning algorithms can be employed for the induction of a classifier able to predictthe class of new data from the same domain, performing the desired discrimination. Some learning techniques are originally conceived for the solution of problems with only two classes, also named binary problems. However, several problems requirethe discrimination of examples into more than two categories or classes. This paper surveys strategies for the generalization of binary classifiers to problems with more than two classes, known as multiclass problems. The focus is on strategies that decompose the original multiclass problem into multiple binary subtasks, whose outputs are combined to obtain the final classification., Diversos problemas envolvem a classificação de dados em categorias, também denominadas classes. A partir de um conjunto de dados cujas classes são conhecidas, algoritmos de Aprendizado de Máquina podem ser utilizados na induçãode um classificador capaz de predizer a classe de novos dados do mesmo domínio, realizando assim a discriminação desejada. Algumas técnicas de aprendizado são originalmenteconcebidas para a solução de problemas com apenas duas classes, também denominados binários. Entretanto, diversos problemas requerem a discriminação dos dados em mais que duas categorias ou classes. Neste artigo é apresentada uma revisão de estratégias para a generalização de técnicas de aprendizado binárias para a solução de problemas com mais que duas classes, intitulados multiclasses. O foco é em estratégias que decompõem o problema multiclasses original em múltiplos subproblemas binários, cujas saídas são combinadas na obtenção da classificação final.

We present in this paper the development process and the evaluation procedure of a Brazilian Portuguese discourse parser called DiZer. Based on Rhetorical Structure Theory, DiZer is a symbolic cue phrase-based analyzer that makes use of discourse templates learned from a corpus of scientific texts to identify and build the discourse structure of texts. DiZer evaluation shows satisfactory results for scientific and news texts, even tough it was not designed for the latter, which demonstrates DiZer portability., Apresentamos neste artigo o processo de desenvolvimento e avaliação de um analisador discursivo automático para o português brasileiro. Seguindo a Teoria de Estruturação Retórica, o DiZer é um sistema simbólico baseado na ocorrência de marcadores textuais, fazendo uso de templates discursivos extraídos de um corpus de textos científicos para identificar a construir a estrutura discursiva de textos. A avaliação do DiZer mostra resultados satisfatórios para textos científicos e jornalísticos, apesar do sistema não ter sido delineado para o gênero jornalístico, o que demonstra a portabilidade do sistema.