Classification of Fiber Optics Anomalies Using Transforms Ensemble, Adaptive Smoothing Based on the Standardized Variable Distances Learning Algorithm and Convolutional Neural Networks

Abstract

Convolutional neural networks (CNN) have been applied to the classification of different types of anomalies in optical networks. On the other side, the more challenging problem of the evaluation of the severity of a specific anomaly has been scarcely investigated. This letter proposes a hybrid machine learning/convolutional neural networks (CNN) approach, where the presence of noise is mitigated by a preprocessing step based on an adaptive smoothing algorithm and an ensemble of transforms to generate a feature space given in input to a CNN. The approach is applied to a recent public dataset with sensor data collected from a real fiber optical network for the fiber bending anomaly, where it is shown to outperform the direct application of CNN on the original sensor data in the time domain.