ELEMENTARY IDENTIFICATION OF A GNATHOSONIC CLASSIFICATION USING AN AUTOREGRESSIVE MODEL

This was an investigation to determine the feasibility of an autoregre ssive (AR) model for establishing characteristic parameters from recor ded occlusal sounds and develop their classification. Thirty four norm al subjects with intact natural dentitions were selected for the study . The subjects' occlusal sounds from both sides of their faces respect ively were sampled, and the gnathosonic classification (Class A, B and C) was established by observing the original recorded wave pattern an d measuring the duration. Then, a 20 order AR model was calculated wit h the collected data, and the AR model coefficients were found to be s imilar to the indices of Bayes' discriminatory analysis. The total con formation rates of the modelled left and right occlusal sounds to the classification, estimated by Bayes' discriminant functions were 97.06% and 88.24% respectively. AR coefficients representing the characteris tics of human occlusal sounds can be helpful in their classification a nd allow computer diagnosis of occlusal disorders.