ECG beat classification using Ant Colony Optimization for Continuous Domains

In this study, a naturally inspired optimization algorithm, Ant Colony Optimization for Continuous Domains (ACO
_R
), is used to classify six types of ECG beats including, Normal Beat (N), Premature Ventricular Contraction (PVC), Fusion of Ventricular and Normal Beat (F), Artrial Premature Beat (A), Right Bundle Branch Block Beat (R) and Fusion of Paced and Normal Beat (f). A radial basis function neural network is evolved for classification with the training set obtained from MIT-BIH arrhythmia database by using Ant Colony Optimization for Continuous Domains. Training set includes 50 feature vectors for each class. The results are then compared with the classical radial basis function training methods such as Orthogonal Least Square Algorithm and the K-Means algorithm. It is observed that the proposed method can classify ECG beats with a smaller size of network without making any concession on classification performance when compared to the classical methods.