<![CDATA[Atrial Fibrillation (AF) is a common cardiac arrhythmia characterized by rapid and irregular electrical activity of the atrium. AF significantly increases the risk of ischemic stroke and mortality. With the increasing prevalence of cardiovascular risk factors, early detection of AF is crucial for effective intervention. Traditional electrocardiogram (ECG)-based detection methods face limitations, especially in asymptomatic patients or those with sporadic episodes of AF. This paper proposes a novel approach using the Queen Honey Bee Migration (QHBM) algorithm to detect AF from heartbeat signals. The dataset comprises both normal and AF heartbeat signals. The data undergoes preprocessing steps, including noise reduction and feature extraction. The system then classifies the signals using the QHBM algorithm. Key features such as heart rate variability (HRV), amplitude, and RR intervals are extracted for analysis. The QHBM algorithm achieved an accuracy of 95.2%, with a precision of 96.1%, a recall of 94%, and an F1 score of 95%. It outperformed traditional classifiers such as Random Forest, Support Vector Machine (SVM), and Naive Bayes across all performance metrics. In addition, QHBM demonstrated a superior ability to distinguish between normal sinus rhythm and AF, showing a significant improvement over the conventional method. Although the results are promising, challenges remain, including data imbalance and false positive and negative classifications. Oversampling techniques and further optimization of feature selection can enhance model performance. The QHBM algorithm presents a highly effective solution for automatic and real-time AF detection, offering a promising alternative to improve cardiac health monitoring systems.]]>
Copyrights © 2025
