There has been some pioneering work related to the application of deep learning-based auto-encoders for anomaly detection, however, the recent state-of-the-art approaches for anomaly detection have
This study introduces a data-driven approach aiming at precise, swift detection, diagnosis, and localization of fiber anomalies, spanning from fiber cuts to optical eavesdropping attacks.
Imagine a world where the Internet doesn''t just connect but senses—detecting earthquakes, monitoring battery health, or safeguarding
In this paper, we propose a data-driven approach to accurately and quickly detect, diagnose, and localize fiber fault anomalies, including fiber cuts and optical eavesdropping attacks.
We present a thorough machine-learning framework based on real-time state-of-polarization (SOP) monitoring for robust anomaly identification in
This thesis addresses these challenges through the development of machine learning and generative modelling techniques for anomaly detection and root cause analysis in cable broadband networks.
Fiber monitoring aims at detecting anomalies in an optical layer by logging and analyzing the monitoring data. It has mainly been performed using optical time domain reflectometry (OTDR), a technique
Initially, this work presents the system components, loss analysis using attenuation in fiber optics, and ML multiclassification system for detecting various faults, including fiber
Deep learning anomaly detection is important in distributed optical fiber acoustic sensing (DAS). However, anomaly detection is more challenging than traditional learning tasks, due to the
Light Reading is the leading source of news analysis for communications industry professionals.
Mentioning: 18 - Secure and reliable data communication in optical networks is critical for high-speed Internet. However, optical fibers, serving as the data transmission medium providing connectivity to
In this paper, we introduce a multi-scale Convolutional Neural Network–Bidirectional Long Short-Term Memory (CNN-BiLSTM) deep learning model for accurate optical fiber fault detection.
The Fibre Optic Network is a broadband network which consists of optical fi-bre cables directly from the cable operator network to the subscribers home. In contrast to the HFC network which uses copper
Second, a magnetic anomaly analysis model of a finite-length submarine cable was established based on magnetic anomaly theory of finite-length horizontal cylindrical shells. The
Abstract Fibre Optics cable acts as the backbone for providing last-mile connectivity for growing internet consumption within the masses. Apart from providing long-distance network connectivity, these
Abstract Fiber optic sensors represent an innovative technology for automated measurement of cable forces which are critical in construction and operation of many civil engineering structures. This paper
However, optical fibers, serving as the data transmission medium providing connectivity to billons of users worldwide, are prone to a variety of
We propose a data driven approach for the anomaly detection and faults identification in optical networks to diagnose physical attacks such as fiber breaks and optical tapping.
This study focuses on detecting anomalies in the production of fiber optic cables, where small deviations in process parameters such as temperature, extrusion pressure, and fiber tension...
This study explores the deployment of YOLOv8s for detecting anomalies in fiber optic cables mounted on poles, with a focus on climbing activities and environmental impediments. To
We apply Machine Learning (ML) to detect and classify anomalies in optical fiber systems. Fiber optic systems are highly sensitive to external factors such as mechanical stress, vibrations, and malicious
This paper introduces an unsupervised machine learning approach, specifically an autoencoder, designed to promptly detect anomalies or unexpected patterns in optical fibers. Upon
Abstract Secure and reliable data communication in optical networks is critical for high-speed internet. We propose a data driven approach for the anomaly detection and faults identification in optical
1. Introduction Optical Time Domain Reflectometer (OTDR) technology has been a cornerstone in the field of optical fiber monitoring and fault analysis for decades. Traditional methods, such as the two
This paper proposes a deep learning model to classify common fiber optic network issues using publicly accessible OTDR statistics. Our model outperforms previous studies on accuracy detection when
Failure management of the optical network is performed by alarm monitoring, predicting equipment life, identifying equipment abnormalities, power monitoring, and identifying fiber optics
This study proposed an FD-LSTM-based approach FD-LSTM model integrating fractional order derivatives to enhance anomaly detection in fiber optic cable manufacturing.
In this paper, we investigate the use of optical fiber as a sensing medium and present three distinct scenarios involving anomaly detection through the analysis of the SOP data obtained
Contact us for competitive quotes on any of our fiber optic products
Get a Quote