Table 2.
Proposed classification results of human gait recognition on the TUM GAID dataset.
| Classifier | Class-based accuracy (%) | Mean accuracy (%) | ||
|---|---|---|---|---|
| Normal walk | Walk with a bag | Walk with shoes | ||
| LightweightDeep-ELM | 99.64 | 98.52 | 97.65 | 98.60 |
| LightweightDeep-SVM | 98.58 | 96.92 | 96.25 | 97.25 |
| LightweightDeep-FKNN | 98.63 | 96.21 | 95.37 | 96.73 |
| LightweightDeep-EBT | 98.12 | 96.82 | 95.80 | 96.91 |
| LightweightDeep-DT | 97.52 | 96.03 | 95.24 | 96.26 |
Bold values indicate the best values.