Table 5 The SVM classification results of Viswanathan’s database.
From: Phonemes based detection of parkinson’s disease for telehealth applications
Input parameter to SVM | Phoneme | Accuracy (%) | Sensitivity (%) | Specificity (%) |
|---|---|---|---|---|
[VTL(F1), VTL(F2), VTL(F3), VTL(F4)] | /a/ | 85.8 | 87.0 | 84.5 |
/o/ | 79.0 | 77.5 | 80.5 | |
/m/ | 87.8 | 87.5 | 88.0 | |
/a/ + /o/ | 90.0 | 90.5 | 89.5 | |
/a/ + /m/ | 96.0 | 96.5 | 95.5 | |
/o/ + /m/ | 91.3 | 91.0 | 91.5 | |
/a/ + /o/ + /m/ | 94.0 | 93.5 | 94.5 |
