Artificial Neural Network Modelling and Characterization of a 3.2 to 3.8 GHz Low Noise Amplifier for Sub-6 GHz Applications

Uko, Mfonobong, Ekpo, Sunday ORCID: https://orcid.org/0000-0001-9219-3759, Elias, Fanuel, Enahoro, Sunday, Ukommi, Ubong, Unnikrishnan, Rahul, Iwok, Unwana Ubong and Inyang, Aniebiet (2024) Artificial Neural Network Modelling and Characterization of a 3.2 to 3.8 GHz Low Noise Amplifier for Sub-6 GHz Applications. In: The Third International Adaptive and Sustainable Science, Engineering and Technology Conference (ASSET 2024), 16 July 2024 - 18 July 2024, Manchester, United Kingdom. (In Press)

Accepted Version File not available for download. Available under License In Copyright. Download (1MB)

Abstract

This paper presents a novel approach to the design and characterization of Low-Noise Amplifiers (LNAs) for sub-6 GHz frequency applications, specifically targeting the 3.1 to 3.4 GHz spectrum. Utilizing Artificial Neural Networks (ANNs), the behaviour and performance characteristics of LNAs to optimize design parameters that influence gain, noise figure, and linearity is modelled. The ANN model provides a rapid and accurate prediction method, significantly enhancing the design efficiency compared to traditional simulation-based methods. Experimental results validate the ANN model’s predictions, demonstrating improved performance in terms of accuracy and design cycle time.