Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/18371
Title: Weak sinusoidal signal extraction from white noise using convolutional neural network
Authors: Kozlenko, Mykola
Козленко, Микола Іванович
Keywords: digital communications
modulation
manipulation keying
demodulation
detection
bit error rate
machine learning
deep learning
convolutional neural network
JT65
Issue Date: 29-Nov-2023
Publisher: Vasyl Stefanyk Precarpathian National University
Citation: M. Kozlenko, "Weak sinusoidal signal extraction from white noise using convolutional neural network," 2023 2nd International Conference on Innovative Solutions in Software Engineering (ICISSE), Vasyl Stefanyk Precarpathian National University, Ivano-Frankivsk, Ukraine, Nov. 29-30, 2023, doi: 10.5281/zenodo.10467333
Abstract: A great number of analog and digital data communications schemes use the sinusoidal waveform as a basic elementary signal, including the spread spectrum data exchange techniques. Detection of the presence of the sinusoidal waveform in a mixture of signal and noise is a common task, regardless the specific modulation scheme. This paper presents the machine learning-based approach for detection of the sinusoidal wave. It presents the structure of the convolutional neural network, as well as the performance metrics for the sinusoidal signals detection. The paper provides an assessment of the overall accuracy for the binary signals. It reports the overall accuracy value of 0.93 for the sinusoidal signal detection in the presence of additive white Gaussian noise at the signal-to-noise ratio value of −20 dB for a balanced dataset.
URI: https://doi.org/10.5281/zenodo.10467333
https://zenodo.org/records/10467333
http://hdl.handle.net/123456789/18371
ISBN: 978-966-640-549-7
Appears in Collections:Статті та тези (ФМІ)

Files in This Item:
File Description SizeFormat 
2023_ICISSE_paper_77_final.pdf356.3 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.