Real time anomaly detection in network traffic time series
Resumen:
Anomaly detection is a relevant field of study for many applications and contexts. In this paper we focus in on-line anomaly detection on unidimensional time series provided by different network operator equipments. We have implemented two detection methods, we have optimized them for on-line processing and we have adapted them for integration into a testbed of a well known Hadoop big data platform. We have analyzed the behavior of both methods for the particular datasets available but we also have applied the methods to a publicly available labeled datasets obtaining good results.
| 2018 | |
|
Anomaly detection Kalman filter Hadoop |
|
| Inglés | |
| Universidad de la República | |
| COLIBRI | |
| https://hdl.handle.net/20.500.12008/43953 | |
| Acceso abierto | |
| Licencia Creative Commons Atribución (CC - By 4.0) |
