Publications
Proceedings, refereed
Optical Fibre as a Sensor for Network Anomaly Detection
In ACM SIGCOMM 2020 Workshop on Optical Systems Design, 2020.Status: Accepted
Optical Fibre as a Sensor for Network Anomaly Detection
Optical fibres are the backbone of modern Information Technology infrastructure connecting billions of users through high-speed networks. With a drastic increase in the number of internet users, vulnerability and security issues in the optical fibre network become increasingly important. In this paper, we propose a detection method for early warning of anomalies in optical networks. The method is based on monitoring and analyzing changes in the state of polarization of the optical signal targeting differentiating between different physical impacts and movements of the fibre caused by e.g. eavesdropping, cut by digging and thunderstorms.
Afilliation | Communication Systems |
Project(s) | GAIA |
Publication Type | Proceedings, refereed |
Year of Publication | 2020 |
Conference Name | ACM SIGCOMM 2020 Workshop on Optical Systems Design |
Journal Article
Machine learning approach for computing optical properties of a photonic crystal fiber
Optics Express 27, no. 25 (2019).Status: Published
Machine learning approach for computing optical properties of a photonic crystal fiber
Photonic crystal fibers (PCFs) are the specialized optical waveguides that led to many interesting applications ranging from nonlinear optical signal processing to high-power fiber amplifiers. In this paper, machine learning techniques are used to compute various optical properties including effective index, effective mode area, dispersion and confinement loss for a solid-core PCF. These machine learning algorithms based on artificial neural networks are able to make accurate predictions of above-mentioned optical properties for usual parameter space of wavelength ranging from 0.5-1.8 µm, pitch from 0.8-2.0 µm, diameter by pitch from 0.6-0.9 and number of rings as 4 or 5 in a silica solid-core PCF. We demonstrate the use of simple and fast-training feed-forward artificial neural networks that predicts the output for unknown device parameters faster than conventional numerical simulation techniques. Computation runtimes required with neural networks (for training and testing) and Lumerical MODE solutions are also compared.
Afilliation | Communication Systems, Machine Learning |
Project(s) | No Simula project |
Publication Type | Journal Article |
Year of Publication | 2019 |
Journal | Optics Express |
Volume | 27 |
Issue | 25 |
Date Published | 11/2019 |
Publisher | Optical Society of America |