[Similarity measures between vague sets and their application to electrocardiogram auto-recognition]

Area of Science:

• Computer Science
• Artificial Intelligence
• Biomedical Engineering

Background:

• Similarity measures are crucial for Vague set applications.
• Electrocardiogram (ECG) analysis requires accurate automated recognition.
• Existing methods may lack the precision needed for clinical applications.

Purpose of the Study:

• To introduce novel similarity measures for Vague sets.
• To apply these measures to automated ECG recognition.
• To enhance the diagnostic accuracy of ECG analysis.

Main Methods:

• Developed new similarity measures based on Huang Guoshun's Vague set research.
• Extracted characteristic signal parameters from the MIT-BIH ECG database.
• Utilized a Backpropagation (BP) neural network for signal analysis and classification.

Main Results:

• The proposed similarity measures were successfully applied to ECG data.
• Characteristic parameters extracted from ECG signals were effectively analyzed.
• Achieved a high recognition accuracy of 99.04% for ECG samples.

Conclusions:

• The new Vague set similarity measures are effective for ECG auto-recognition.
• The integration of Vague sets, characteristic parameters, and BP neural networks offers a robust approach.
• This method significantly improves the accuracy and potential clinical utility of automated ECG analysis.