Szczegóły publikacji
Opis bibliograficzny
Sample weighting methods for compensating class imbalance in elephant flow classification / Piotr JURKIEWICZ, Robert WÓJCIK, Jerzy DOMŻAŁ // IEEE Access [Dokument elektroniczny]. — Czasopismo elektroniczne ; ISSN 2169-3536. — 2024 — vol. 12, s. 188122-188136. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 188135-188136, Abstr. — Publikacja dostępna online od: 2024-12-12
Autorzy (3)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 157338 |
|---|---|
| Data dodania do BaDAP | 2025-02-06 |
| Tekst źródłowy | URL |
| DOI | 10.1109/ACCESS.2024.3516508 |
| Rok publikacji | 2024 |
| Typ publikacji | artykuł w czasopiśmie |
| Otwarty dostęp |  |
| Creative Commons | |
| Czasopismo/seria | IEEE Access |
Abstract
Accurately identifying and classifying elephant flows is crucial in many network traffic management applications. However, the inherent class imbalance between elephant and mouse flows presents a challenge for machine learning models, often leading to poor classification accuracy. This paper compares various sample weighting techniques to compensate this imbalance during model training. We evaluate recommended approaches, as well as propose novel methods based on roots, powers, and logarithms of flow size. Analysis reveals that one of our proposed methods based on square root weighting significantly outperforms standard class balancing, offering up to 72% gains in flow operations reduction metric across multiple algorithms. These findings provide valuable insights for researchers and practitioners working on flow classification problem, contributing to more efficient network traffic management systems.
