Research Article
A New Approach to Diagnose Parkinson’s Disease Using a Structural Cooccurrence Matrix for a Similarity Analysis
Table 1
Results from the best classifiers and combinations.
| | Meander | Spiral | M/S | Acc (%) | Acc (%) | Acc (%) |
| Bayes | | | | | 72.77 ± 9.91 | 69.57 ± 11.07 | 65.95 ± 2.05 | | 75.11 ± 3.99 | 76.36 ± 4.26 | 68.38 ± 2.18 | | 77.72 ± 4.27 | 82.01 ± 5.53 | 71.39 ± 2.39 | OPF | | | | | 75.54 ± 3.76 | 69.73 ± 3.63 | 64.28 ± 2.05 | | 68.59 ± 3.76 | 70.49 ± 3.63 | 61.13 ± 2.57 | | 77.50 ± 2.75 | 75.71 ± 4.39 | 67.21 ± 1.98 | SVM | | | | | 80.05 ± 1.80 | 78.04 ± 2.74 | 67.63 ± 2.73 | | 75.00 ± 2.90 | 78.04 ± 2.85 | 65.30 ± 2.92 | | 82.23 ± 3.02 | 85.54 ± 3.62 | 74.13 ± 2.27 |
|
|