Research Article
Improving Accuracy and Simplifying Training in Fingerprinting-Based Indoor Location Algorithms at Room Level
Table 2
Relative accuracy by algorithm based on the number of WAPs when training with all locations (part I).
| #WAPs |
ADTree |
BFTree | Decision Stump | FT | J-48 |
| 40 | 95.83 ± 5.59 | 95.00 ± 4.08 | 95.00 ± 5.53 | 97.50 ± 3.82 | 95.83 ± 5.59 |
| 5 | 85.83 ± 9.17 | 85.83 ± 10.57 | 86.67 ± 6.67 | 79.17 ± 11.33 | 87.50 ± 10.03 |
| 8 | 90.00 ± 8.16 | 88.33 ± 8.50 | 87.50 ± 10.03 | 88.33 ± 13.02 | 85.83 ± 7.50 |
| 10 | 96.67 ± 4.08 | 95.00 ± 6.67 | 92.50 ± 7.86 | 97.50 ± 3.82 | 93.33 ± 6.24 |
| 16 | 95.83 ± 4.17 | 95.83 ± 5.59 | 92.50 ± 7.86 | 96.67 ± 5.53 | 93.33 ± 6.24 |
| 20 | 95.83 ± 5.59 | 94.17 ± 5.34 | 92.50 ± 7.86 | 97.50 ± 3.82 | 93.33 ± 6.24 |
| 32 | 95.83 ± 5.59 | 94.17 ± 5.34 | 92.50 ± 7.86 | 95.83 ± 5.59 | 94.17 ± 5.34 |
|
|