Related Experiment Video
Updated: Jun 25, 2025
08:59
Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
Published on: October 28, 2018
7.1K
Gershgorin circle theorem-based feature extraction for biomedical signal analysis
Sahaj A Patel1, Rachel June Smith1, Abidin Yildirim1
1Department of Electrical and Computer Engineering, University of Alabama at Birmingham, Birmingham, AL, United States.
Frontiers in Neuroinformatics
|May 31, 2024
Summary
A novel Gershgorin Circle Feature Extraction (GCFE) method enhances biomedical signal analysis by efficiently extracting features from graph networks. GCFE demonstrates superior accuracy and computational efficiency compared to existing techniques.
Area of Science:
- Biomedical Signal Processing
- Graph Theory Applications
- Machine Learning in Healthcare
Background:
- Graph theory is increasingly used for biomedical signal analysis, transforming signals into graph networks.
- High dimensionality of graph matrices leads to significant computational demands, necessitating efficient feature extraction.
- Existing methods struggle with computational efficiency and accuracy in complex biomedical signal analysis.
Purpose of the Study:
- Introduce a new, computationally efficient feature extraction technique for biomedical signals.
- Apply the Gershgorin Circle theorem to create the Gershgorin Circle Feature Extraction (GCFE) method.
- Evaluate GCFE's performance against established methods using diverse biomedical datasets.
Main Methods:
- Developed the Gershgorin Circle Feature Extraction (GCFE) technique utilizing a modified weighted Laplacian matrix from visibility graphs.
- Applied GCFE to classify neural spikes and distinguish seizure from non-seizure events in EEG data.
- Compared GCFE's efficacy against two visibility graphs and seven other feature extraction algorithms.
Main Results:
- GCFE achieved superior performance and higher accuracy compared to seven other feature extraction methods, with an average accuracy difference of 2.67%.
- The GCFE method demonstrated significant computational efficiency, outperforming other techniques.
- Consistent superior performance across all experimental datasets highlights GCFE's robustness.
Conclusions:
- GCFE offers a computationally efficient and accurate approach for biomedical signal classification.
- The method shows promise for real-time applications, particularly in analyzing signals like EKG.
- GCFE represents a significant advancement in feature extraction for complex biomedical data analysis.
