Online Training Evaluation in Virtual Reality Simulatorsusing Possibilistic Networks

1 Ronei Marcos de Moraes, Department of Statistics, Federal University of Paraíba. Cidade Universitária s/n, Castelo Branco, João Pessoa-PB. 58.051-900. Brazil. [email protected] 2 Liliane dos Santos Machado, Department of Informatics, Federal University of Paraíba. Cidade Universitária s/n, Castelo Branco, João Pessoa-PB, Brazil. 58.051-900. [email protected] Abstract  Systems based on virtual reality are used in training many areas of human activities. In general, these kinds of training are performed to know the user's skills. An user is immersed into a virtual world to have realistic training and realistic interactions with that world, as he/she should made in real tasks. An online evaluation system allows to the user improve his learning because it can identify, immediately after the training, where he committed mistakes or presented low efficiency. In this paper, it was used an approach to online training evaluation based on a Possibilistic Networks. Those networks were used to model and classification of simulation in N pre-defined classes. Possibilistic Networks are a generalization of probabilistic networks, when fuzzy sets are used.