Review of various feature extraction approaches for ERG signal analysis: Advantages and drawbacks
1 Al-Sharia Department, University of Baghdad, Baghdad, Iraq.
2 Medical Devices Technology Engineering, Alsalam University College, Baghdad, Iraq.
3 Department of Computer Engineering, College of Engineering, Al-Iraqia University, Baghdad, Iraq.
4 Department of Electrical Engineering, College of Engineering, Al-Iraqia University, Baghdad, Iraq.
Review Article
Global Journal of Engineering and Technology Advances, 2023, 16(03), 172–178.
Article DOI: 10.30574/gjeta.2023.16.3.0178
Publication history:
Received on 16 July 2023; revised on 14 August 2023; accepted on 16 August 2023
Abstract:
This article presents a comprehensive examination of various techniques used to extract features from Electroretinogram (ERG) signals for analysis purposes. ERG signals are crucial in the diagnosis and study of retinal diseases. The accurate extraction of informative features from ERG signals is vital for understanding retinal function and identifying abnormalities. This review specifically focuses on different methods employed for feature extraction in ERG signal analysis, highlighting their respective advantages and disadvantages. The article explores a range of established methods, namely time-domain, frequency-domain, time-frequency domain analysis, and machine learning delves into the difficulties and constraints linked to these strategies, such as signal noise, artifacts, and computational complexity. Its objective is to offer a thorough evaluation of the merits and drawbacks of diverse feature extraction techniques, with the aim of aiding researchers and clinicians in their selection of suitable methods for the analysis of ERG signals.
Keywords:
Electroretinogram; Time-domain analysis; Frequency-domain analysis; Time-frequency analysis; Machine learning.
Full text article in PDF:
Copyright information:
Copyright © 2023 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0