Combination of multiple diagnosis systems in Self-Healing networks

作者：

Highlights：

• An improved hybrid ensemble method to combine any kind of classifier is proposed.

• No need for the standalone classifiers to first assess incoming cases under test.

• It is based on the statistical modeling of the baseline classifiers’ behavior.

• It is applied in LTE root cause analysis.

• The method has been tested in a live network scenario.

摘要

•An improved hybrid ensemble method to combine any kind of classifier is proposed.•No need for the standalone classifiers to first assess incoming cases under test.•It is based on the statistical modeling of the baseline classifiers’ behavior.•It is applied in LTE root cause analysis.•The method has been tested in a live network scenario.

论文关键词：LTE,Self-healing,Root cause analysis,Self-organizing networks (SON),Hybrid ensemble classifier,Automatic fault identification

论文评审过程：Received 8 January 2016, Revised 20 July 2016, Accepted 21 July 2016, Available online 22 July 2016, Version of Record 27 July 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.07.030