A NEW CLASS OF ASSESSMENT METHODOLOGIES IN MEDICAL TRAINING BASED ON COMBINING CLASSIFIERS

Abstract

Researches on training assessment for simulators based on Virtual Reality have less than 20 years old. By the use of simulators is possible to know users' performance during the training to analyze if they are prepared to perform the procedure in real situations. Basically, a Single User's Assessment System (SUAS) must continuously monitor all user interactions on VR environment and compare their performance with predefined expert's classes of performance to recognize user’s level of training. In spite of the several methodologies proposed as kernel for SUAS, most of them are based on single classifiers. In this paper is discussed a new class of methodologies for SUAS based on Combining Classifiers.

Index Terms - Medical Training, Users' Assessment, Virtual Reality, Combining Classifiers.