Descripción
|
|
---|---|
Network failures are still one of the main causes of distributed systems? lack of reliability. To overcome this problem we present an improvement over a failure prediction system, based on Elastic Net Logistic Regression and the application of rare events prediction techniques, able to work with sparse, high dimensional datasets. Specifically, we prove its stability, fine tune its hyperparameter and improve its industrial utility by showing that, with a slight change in dataset creation, it can also predict the location of a failure, a key asset when trying to take a proactive approach to failure management. | |
Internacional
|
Si |
Nombre congreso
|
International Conference on Artificial Intelligence and Soft Computing (ICAISC 2015) |
Tipo de participación
|
960 |
Lugar del congreso
|
Zakopane (Polonia) |
Revisores
|
Si |
ISBN o ISSN
|
978-3-319-19369-4 |
DOI
|
10.1007/978-3-319-19369-4_63 |
Fecha inicio congreso
|
14/06/2015 |
Fecha fin congreso
|
18/06/2015 |
Desde la página
|
714 |
Hasta la página
|
726 |
Título de las actas
|
Artificial intelligent and soft computing. 14th International Conference, ICAISC 2015, Zakopane, Poland, June 14-18, 2015, Proceedings, Part II |