A wavelet transform based feature extraction and classification of cardiac disorder.

Area of Science:

• Biomedical Engineering
• Artificial Intelligence in Medicine
• Signal Processing

Background:

• Electrocardiogram (ECG) signal analysis is crucial for diagnosing cardiac arrhythmias.
• Traditional methods may face challenges in accurately classifying complex ECG patterns.
• Developing robust diagnostic systems is essential for timely medical intervention.

Purpose of the Study:

• To develop and evaluate a hybrid intelligent diagnosis system for ECG signal classification.
• To utilize the Adaptive Neuro-Fuzzy Inference System (ANFIS) for enhanced arrhythmia detection.
• To assess the performance of the proposed system in identifying critical cardiac conditions.

Main Methods:

• Employing Symlet Wavelet Transform for detailed ECG signal analysis and feature extraction.
• Utilizing extracted parameters as input for the ANFIS classifier.
• Training and validating the ANFIS model on five key ECG signal types: Normal Sinus Rhythm (NSR), Atrial Fibrillation (AF), Pre-Ventricular Contraction (PVC), Ventricular Fibrillation (VF), and Ventricular Flutter (VFLU).

Main Results:

• The ANFIS model demonstrated significant recognition and classification capabilities for ECG signals.
• The proposed hybrid approach achieved a high classification accuracy of 98.24%.
• Performance evaluation confirmed the model's effectiveness in both training and classification tasks.

Conclusions:

• The developed ANFIS-based system shows considerable potential for accurate ECG signal classification.
• This hybrid approach offers an advantage in diagnosing various dangerous cardiac arrhythmias.
• The high accuracy achieved supports the clinical applicability of this intelligent diagnostic system.