Pre-, In-, and Post-Processing Class Imbalance Mitigation Techniques for Failure Detection in Optical Networks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918106565181440 |
|---|---|
| author | Ali, Yousuf Moiz Prilepsky, Jaroslaw E. Sambo, Nicola Pedro, João Hosseini, Mohammad M. Napoli, Antonio Turitsyn, Sergei K. Freire, Pedro |
| author_facet | Ali, Yousuf Moiz Prilepsky, Jaroslaw E. Sambo, Nicola Pedro, João Hosseini, Mohammad M. Napoli, Antonio Turitsyn, Sergei K. Freire, Pedro |
| contents | We compare pre-, in-, and post-processing techniques for class imbalance mitigation in optical network failure detection. Threshold Adjustment achieves the highest F1 gain (15.3%), while Random Under-sampling (RUS) offers the fastest inference, highlighting a key performance-complexity trade-off. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21119 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pre-, In-, and Post-Processing Class Imbalance Mitigation Techniques for Failure Detection in Optical Networks Ali, Yousuf Moiz Prilepsky, Jaroslaw E. Sambo, Nicola Pedro, João Hosseini, Mohammad M. Napoli, Antonio Turitsyn, Sergei K. Freire, Pedro Machine Learning Signal Processing Optics We compare pre-, in-, and post-processing techniques for class imbalance mitigation in optical network failure detection. Threshold Adjustment achieves the highest F1 gain (15.3%), while Random Under-sampling (RUS) offers the fastest inference, highlighting a key performance-complexity trade-off. |
| title | Pre-, In-, and Post-Processing Class Imbalance Mitigation Techniques for Failure Detection in Optical Networks |
| topic | Machine Learning Signal Processing Optics |
| url | https://arxiv.org/abs/2507.21119 |