Electromyography Signal Analysis for the Detection of TMJ Disorder Using Classification Models and Multivariate Analysis

Temporomandibular joint (TMJ) disorder is a wide term that encompasses variety of disorders with varying etiologies. The purpose this study was to analyses electromyographic signals wavelet transform for the diagnostic methods which help in TMJ issues patients who visited Dental Centre. Due increasing importance electromyography diagnosing muscular disorders, such as temporomandibular disorder, it has been widely used. Through various techniques, discrete and power spectral density, possible identify minimize noise signals, can be very useful diagnosis disorder. This paper presents an algorithm combines features multivariate analysis order detect Support vector machine model giving better performance terms training, testing time accuracy 93% compared other models. Multivariate shows significant difference feature variable chosen.