Research Article
Damage Identification of Prefabricated Reinforced Concrete Box Culvert Based on Improved Fuzzy Clustering Algorithm and Acoustic Emission Parameters
Table 8
Data set noise calculation results.
| | Calculation method | Data set | The amount of total data | The amount of noise point calculation | The amount of noise accurate calculation | Accuracy (%) |
| | G-DFCM | Iris + Balance-scale | 180 | 30 | 30 | 100.00 | | Glass + Cmc | 244 | 32 | 30 | 93.75 |
| | DBSCAN | Iris + Balance-scale | 180 | 39 | 30 | 76.92 | | Glass + Cmc | 244 | 32 | 32 | 52.63 |
| | FCM | Iris + Balance-scale | 180 | —1 | — | — | | Glass + Cmc | 244 | — | — | — |
| | STING | Iris + Balance-scale | 180 | —2 | — | — | | Glass + Cmc | 244 | — | — | — |
|
|
1FCM algorithm cannot identify noise. 2The STING algorithm is not suitable for high-dimensional data.
|
