Table 3.
Validation and testing accuracy results for the five classification methods that used a combination of gait temporal parameters and time domain features.
| Seven Sensor Placements (Combination of Time Domain & Gait Temporal Features) | |||||
|---|---|---|---|---|---|
| Model Name | 5-Fold Cross-Validation | Testing Accuracy (%) | Average Precision | Average Recall | |
| Mean Accuracy (%) | Standard Deviation | ||||
| Random Forest | 80.87912 | 11.62656 | 84.78261 | 0.83 | 0.83 |
| Multilayer Perceptron | 71.05495 | 13.12726 | 84.78261 | 0.88 | 0.85 |
| Naïve Bayes | 88.22711 | 3.997853 | 84.78261 | 0.85 | 0.85 |
| Adaboost | 79.75092 | 8.194112 | 82.6087 | 0.85 | 0.85 |
| Decision Tree | 78.1978 | 4.665143 | 80.43478 | 0.84 | 0.80 |