EUL’s student Zelaci’s work has been published in one of the most prestigious engineering journals
European University of Lefke (EUL) Faculty of Engineering Department of Electrical and Electronics Engineering Undergraduate student made a precious publication on the subject of “Generative adversarial neural networks for modelling Photonic crystal fibre based Surface Plasmon Resonance sensor”. This work was carried out by Mr. Zelaci within the scope of the final year graduation project under the supervision of his supervisors. This was an interdisciplinary project where, electromagnetics (optics) and artificial neural network theories was combined. Therefore, Computer and Electrical Engineering department lecturer’s collaborative supervision was provided.
The article is published in one of the most prestigious Engineering Publisher the International Electrical and Electronic Engineering Association (IEEE) Journal of Lightwave Technology. The journal Impact factor is 4.3 and is also co-sponsored by another prestigious publisher The Optical Society of America (OSA).
In the project, Generative adversarial neural network system architecture is proposed for modelling Photonic crystal fibre based Surface Plasmon Resonance sensor. The experimental analysis suggested that the proposed model not only accurately predicts the losses even with limited amounts of data but also neural networks can be used to improve existing methods in the literature.
The most vital advantage of using this method instead of numerical simulation is the speed factor. In the experiments, it is shown that the proposed methods work few orders of magnitude faster than the traditional simulation method. This type of sensor models is favourable in both chemical and biological sensing applications.
Mr. Zelaci stated that the proposed Neural Network architecture can be adapted to various optical sensor models in the literature.