Related Experiment Video
Updated: Jul 19, 2025
09:47
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
1.1K
Mud Ring Optimization Algorithm with Deep Learning Model for Disease Diagnosis on ECG Monitoring System
Ala Saleh Alluhaidan1, Mashael Maashi2, Munya A Arasi3
1Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia.
Sensors (Basel, Switzerland)
|August 12, 2023
Summary
A new deep learning technique uses Mud Ring Optimization (MRO) to classify electrocardiogram (ECG) signals for heart disease detection. This MROA-DLECGSC approach improves accuracy in diagnosing cardiovascular disease (CVD) from ECG data.
Area of Science:
- Biomedical Engineering
- Artificial Intelligence in Medicine
- Cardiology
Background:
- The proliferation of Internet of Things (IoT), sensing technologies, and wearables has shifted medical services towards real-time monitoring.
- Electrocardiogram (ECG) signals are crucial for noninvasive diagnosis of cardiovascular diseases (CVD).
- Increasing patient numbers and variations in ECG patterns necessitate automated diagnostic tools for accurate ECG signal classification.
Purpose of the Study:
- To introduce a novel Mud Ring Optimization with Deep Learning-based ECG Signal Classification (MROA-DLECGSC) technique.
- To develop a computer-assisted tool for accurate identification of heart disease using ECG signals.
- To enhance the performance of ECG signal classification for CVD detection.
Main Methods:
- ECG signals were preprocessed to ensure a uniform format.
- A Stacked Autoencoder Topographic Map (SAETM) was employed for ECG signal classification to detect CVDs.
- Mud Ring Optimization (MROA) was utilized as a hyperparameter optimizer to improve classification performance.
Main Results:
- The MROA-DLECGSC technique demonstrated effective recognition of heart disease through ECG signal analysis.
- The SAETM approach successfully classified ECG signals for CVD identification.
- Hyperparameter optimization using MROA led to enhanced overall performance of the classification model.
- Experimental results on a benchmark database showed superior performance of MROA-DLECGSC compared to existing algorithms.
Conclusions:
- The MROA-DLECGSC technique offers a promising approach for automated ECG signal classification in diagnosing cardiovascular diseases.
- The integration of MROA for hyperparameter tuning significantly boosts the accuracy and efficiency of deep learning models for CVD detection.
- This study highlights the potential of advanced AI techniques in real-time medical diagnostics, addressing the challenges posed by large patient populations and signal variability.
