Research Article
Research on a Machine Learning-Based Method for Assessing the Safety State of Historic Buildings
Table 5
The relationship between the number of principal components extracted of KCCA and the monitoring model.
| Number of principal components | Cumulative contribution (%) | Average absolute error (mm) |
| 1 | 25.9 | 8.14 | 2 | 36.78 | 6.68 | 3 | 45.27 | 2.62 | 4 | 52.87 | 2.31 | 5 | 60.1 | 1.81 | 7 | 65.32 | 0.94 | 10 | 69.27 | 0.59 | 11 | 72.57 | 0.96 | 12 | 75.52 | 0.88 | 13 | 77.68 | 1.11 | 14 | 79.74 | 0.83 |
|
|