Arrhytmias Classification using Data Fusion and Particle Swarm Optimization

Computer analysis of electrocardiogram (ECG) data has proven to be an important method to detect cardiac arrhythmias, so that can be of great assistance to the experts in detecting cardiac abnormalities. In this study, we purpose to develop a system to aid in the diagnosis of anomalies cardiac signals. This system is based on data fusion and architected by using the multi-agents system for ECG classification. Therefore, the proposed system helps doctors to quickly and precisely diagnose a heart disease by examining only the class of the ECG beats. In order to achieve the goal of real-time classification, the data used are divided into two datasets: the training set for the unsupervised learning of the classifier and the testing set for the real-time classification. This system is tested on a MITBIH arrhythmia database.