<![CDATA[Cardiovascular diseases (CVDs) remain the leading cause of mortality globally, accounting for approximately 17.9 million deaths annually. Among these, arrhythmias represent a significant concern due to their potential to lead to severe cardiac events. Traditional methods for detecting arrhythmias often require specialized equipment and healthcare facilities, which may not be readily accessible, especially in remote areas. This paper proposes the development of a portable electrocardiogram (ECG) device integrated with an Artificial Neural Network (ANN) using the Backpropagation algorithm to classify arrhythmias, thereby facilitating early detection and management. Arrhythmia is a heart condition characterized by an irregular heartbeat, where the heart may beat faster or slower than normal. Classification of arrhythmia can assist patients in monitoring their heart condition without needing to visit the hospital. This final project implements the Artificial Neural Network (ANN) method due to its ability to perform fast and accurate classifications. Prior to classification, feature extraction is carried out to detect the R wave interval, T wave interval, and the differences between the R and T wave intervals. The classification results are then displayed through a graphical user interface (GUI). The development of this ANN-based arrhythmia signal classification tool aims to help patients detect heart abnormalities at an early stage, potentially preventing the condition from worsening. Testing was conducted on 11 individuals, with 9 identified as having normal heart signals and 2 diagnosed with arrhythmia. When compared to a simulator, the classification system achieved 100% accuracy.]]>
Copyrights © 2026
