Gaussian Mixture Models and Relaxation Labeling for Online Evaluation of Training in Virtual Reality Simulators
Ronei Marcos de Moraes · 2003
Abstract ⎯ Several approaches for evaluation of online or offline training in simulators based on virtual reality have been proposed. However great part of these approaches has a high complexity and it demands large computational structure, what is very expensive. An online evaluator must have low complexity algorithm to do not compromise the performance of simulator. We propose a new approach to online evaluation of training in simulators based on virtual reality. This approach uses Gaussian Mixture Models and Relaxation Labeling (GMM-RL) for modeling and classification of the simulation in pre-defined classes of training. This method provides the use of continuous variables without lost of information. So, it solves the problem of low complexity in online evaluators without compromise performance of the simulator and with good evaluation accuracy. Systems based on this approach can be applied in virtual reality simulators for training in several areas.