Search

• Analytical games are a promising Knowledge Acquisition method. • Reliability Game data used in Bayesian Networks latent variable learning. • The work described aims at supporting multi-source fusion systems design. Knowledge Acquisition (KA) methods are of paramount importance in the design of intelligent systems. Research is ongoing to improve their effectiveness and efficiency. Analytical games appear to be a promising tool to support KA. In fact, in this paper we describe how analytical games could be used for Knowledge Engineering of Bayesian networks, through the presentation of the case study of the Reliability Game. This game has been developed with the aim of collecting data on the impact of meta-knowledge about sources of information upon human Situational Assessment in a maritime context. In this paper we describe the computational model obtained from the dataset and how the card positions, which reflect a player belief, can be easily converted in subjective probabilities and used to learn latent constructs, such as the source reliability, by applying the Expectation-Maximisation algorithm. [ABSTRACT FROM AUTHOR]

The paper deals with the hot issue of entrepreneurship education and describes the rationale behind the gamified and collaborative courses for university students conceived, developed and deployed in the framework of the eSG (stimulating entrepreneurship through Serious Games) project, funded under the EU lifelong learning (LLP) Programme. The project aims to help students becoming familiar, mainly through practice, with basic concepts of entrepreneurship and company management and to stimulate the emergence of their entrepreneurial attitudes. In the framework of the project specific courses mainly grounded on the concepts of gamification and collaboration were designed and carried out in three different partner countries: Italy, Spain and the Netherlands. The main objectives of the courses are presented in this paper and a theoretical model supporting the choice of Serious Games is shown which keeps into account usability, pedagogy and the entrepreneurship skills expressed by state of the art models. [ABSTRACT FROM AUTHOR]

There are currently a number of models, frameworks and methodologies for serious games analysis and design that provide useful interpretations of the possibilities and limitations offered by serious games. However, these tools focus mostly on high-level aspects and requirements and do not help understand how such high-level requirements can be concretely satisfied. In this paper, we present a conceptual model, called Activity Theory-based Model of Serious Games (ATMSG), that aims to fill this gap. ATMSG supports a systematic and detailed representation of educational serious games, depicting the ways that game elements are connected to each other throughout the game, and how these elements contribute to the achievement of the desired pedagogical goals. Three evaluation studies indicate that ATMSG helped participants, particularly those with gaming experience, identify and understand the roles of each component in the game and recognize the game's educational objectives. [ABSTRACT FROM AUTHOR]

Abstract: A 3D reconstruction of an urban area for Virtual Worlds (VWs) or Serious Games (SGs) requires a careful trade-off among the 3D models'' realism, weight and development time. This has led us to the definition of an algorithm – the Architectonic Style Area (ASA) algorithm – for procedural generation of buildings in an urban area, based on the concept of “architectonic likelihood”, that intends to give players the sense of being in a particular city or even specific area of a city. This has a cognitive foundation in the fact that, after a visit, a tourist typically does not remember every single palace of a city, but remembers – beside the most important monuments and buildings – its general features and its architectonic styles. The algorithm extrudes 2D maps and composes façades by statistically assembling sample images of architectonic components from the target city. Components are classified in an ontology based on the classic principles of architecture. The algorithm relies on rules that encode the semantics of the ontology. The paper describes the algorithm and the related easy-to-use visual authoring tool. It also shows the results in two different projects: a SG for the promotion of the cultural heritage and a 3D movie. Results show that the approach allows keeping the realism of every single building at good detail and of the overall scene, while dropping a huge work of image collection and processing for the textures. Comparisons are investigated with regard to state of the art urban modeling methods, highlighting the differences and possible synergies. [Copyright &y& Elsevier]