Frequency estimation from noisy signals based on deep learning

• Main Author: Tay, Audrey Bao Yi
• Other Authors: Teh Kah Chan
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/167173
• Institution: Nanyang Technological University

Frequency estimation is used everywhere as it is one of the main issues in the field of signal processing and communications. It is an important topic because various fields in the world use this. Currently, many researchers are using traditional methods in finding the frequency estimation of a signal, which can still give accurate and reliable results. In recent years, deep learning has gained recognition and people are starting to incorporate deep learning into their research as it is known to have a higher accuracy and speed. It also can process large amount of data which makes it very powerful when dealing with unstructured data. This project aims to understand the various methods that have been used to estimate the frequency of signals, followed by the study of deep learning algorithms available. The main objective of this project is to incorporate deep learning into finding the frequency estimation of a noisy signal. This is done by studying the behaviour of DNN which displays the phenomenon of F-principle, where it captures the low frequency first then the high frequency. This algorithm is then tested on noisy signal to estimate the frequency of the signal.