dc.contributor.author | Masete, Ishak Moit | |
dc.date.accessioned | 2023-10-19T06:08:40Z | |
dc.date.available | 2023-10-19T06:08:40Z | |
dc.date.issued | 2023-10-18 | |
dc.identifier.citation | Masete, Ishak Moit. (2023). AI Enabled Modulation Identification in Fiber Optic Networks. (Unpublished undergraduate dissertation) Makerere University; Kampala, Uganda. | en_US |
dc.identifier.uri | http://hdl.handle.net/20.500.12281/16690 | |
dc.description | A research report submitted to the College of Engineering, Design, Art, and Technology in partial fulfillment of the requirement for the award of the degree of Bachelor of Science in Telecommunication Engineering of Makerere University. | en_US |
dc.description.abstract | Fiber optic communication systems have transformed telecommunications by enabling high-speed data transmission over long distances. Accurate identification of modulation formats is crucial for their success. Elastic Optical Networks (EONs) offer a flexible infrastructure for high-capacity communication and optimize resources based on demand. Machine Learning (ML) is a promising approach for network-data analysis and automated network self-configuration. ML techniques address the growing complexity of optical networks caused by adjustable parameters and coherent technologies.
In this project, the performance of CNN, ANN, and LSTM models was evaluated for Modulation Format Identification (MFI) in fiber optic communication systems. The models were trained on IQ Data, Amplitude histogram data, and Eye diagrams generated from simulated networks of different modulation formats. The evaluation aimed to determine the most suitable model for accurately identifying modulation formats in optical networks. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Makerere University | en_US |
dc.subject | AI Enabled Modulation | en_US |
dc.subject | Fiber Optic Networks | en_US |
dc.subject | Neural Networks | en_US |
dc.title | AI Enabled Modulation Identification in Fiber Optic Networks | en_US |
dc.type | Thesis | en_US |