Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/149868
Title: Detection of single channel signal under noise floor using machine learning
Authors: Tay, Shaun
Keywords: Engineering::Electrical and electronic engineering::Wireless communication systems
Issue Date: 2021
Publisher: Nanyang Technological University
Source: Tay, S. (2021). Detection of single channel signal under noise floor using machine learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/149868
Abstract: The detection of digital signals under the noise floor has remain a challenge in digital communication systems. As the signal-to-noise ratio (SNR) falls below 0 dB, the detection of digital signals becomes increasingly challenging with false alarms also being a problem. The noise floor consists of the unwanted signals that are added up in the signal, and determines the lowest possible signal level that digital communication systems can operate in. Additive white gaussian noise (AWGN) will be taken into account along with various other fading channels such as Rayleigh and Rician fading. All simulation will be done on MATLAB software. This report aims to achieve detection of signals in negative SNR (in dB), comparing deep learning against other methods. In this report, the benefits deep learning is able to offer in comparison to the other methods would be compared. Existing methods such as energy detection, cyclo- stationary detection would be compared to deep learning methods. Though only cyclo-stationary detection as well as deep learning methods would be discussed in detail.
URI: https://hdl.handle.net/10356/149868
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP Final Draft Report - Shaun Tay.pdf
  Restricted Access
3.16 MBAdobe PDFView/Open

Page view(s)

87
Updated on May 16, 2022

Download(s)

10
Updated on May 16, 2022

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.