The Computerized Adaptive Practice (CAP) system describes a set of algorithms for assessing player’s expertise and difficulties of in-game problems and for adapting the latter to the former. However, an effective use of CAP requires that in-game problems are designed carefully and refined over time to avoid possible barriers to learning. This study proposes a methodology and three different instruments for analyzing the problem set in CAP-enabled games. The instruments include the Guttman scale, a ranked order, and a Hasse diagram that offer analysis at different levels of granularity and complexity. The methodology proposes to use quantified difficulty measures to infer topology of the problem set. It is well-suited for serious games that emphasize practice and repetitive play. The emphasis is put on the simplicity of use and visualization of the problem space to maximally support teachers and game developers in designing and refining CAP-enabled games. Two case studies demonstrate practical applications of the proposed instruments on empirical data. Future research directions are proposed to address potential drawbacks.

Abstract. Digital game technologies are a promising way to enable training providers to reach other target groups, namely those who are not interested in traditional learning technologies. Theoretically, through using digital game technologies we are able to foster the acquisition of any competence by specifying competency structures, offering adequate problem solving support while maintaining motivation and taking personality into consideration as part of the tailored game experience. In this paper, we illustrate how this is done within the RAGE project, which aims to develop, transform, and enrich advanced technologies into self-contained gaming assets for the leisure games industry to support game studios in developing applied games easier, faster, and more cost effectively. The software assets discussed here represent a modular approach for fostering learning in applied games. These assets address four main pedagogical functions: competency structures (i.e., logical order for learning), motivation, performance support (i.e., guidance to maintain learning), and adaption to the player's personality.

Automated machine learning and predictive maintenance have both become prominent terms in recent years. Combining these two fields of research by conducting log analysis using automated machine learning techniques to fuel predictive maintenance algorithms holds multiple advantages, especially when applied in a production line setting. This approach can be used for multiple applications in the industry, e.g., in semiconductor, automotive, metal, and many other industrial applications to improve the maintenance and production costs and quality. In this paper, we investigate the possibility to create a predictive maintenance framework using only easily available log data based on a neural network framework for predictive maintenance tasks. We outline the advantages of the ALFA (AutoML for Log File Analysis) approach, which are high efficiency in combination with a low entry border for novices, among others. In a production line setting, one would also be able to cope with concept drift and even with data of a new quality in a gradual manner. In the presented production line context, we also show the superior performance of multiple neural networks over a comprehensive neural network in practice. The proposed software architecture allows not only for the automated adaption to concept drift and even data of new quality but also gives access to the current performance of the used neural networks.

No abstract

No abstract