A flexible bio-affective gaming interface
Affective bio-feedback can be an important instrument to enhance the game experience. Several studies have provided evidence of the usefulness of physiological signals for affective gaming. However, due to discrepancies in the findings of psychology studies, the pattern matching models employed are limited in the number of emotions they are able to classify. This paper presents a bio-affective gaming interface (BAGI) that can be used to customize a game experience according to the player's emotional response. Its architecture offers important characteristics for gaming such as: flexibility, scalability and multi-category discrimination in real time. These features are important not only because they allow the classification with pattern matching and machine learning models but also because they make possible the reusability of previous findings and the inclusion of new models to the system. In order to prove the effectiveness of BAGI two different types of neural networks have been trained to recognize emotions. After that, they were incorporated into the system to customize in real-time the computer wallpaper, according to the emotion experienced by the user. The best results were obtained with a probabilistic neural network with accuracy results of 84.46% on the training data and 78.38% on the validation for new independent data sets.