Abstract: An electrocardiographic (ECG) beat classifier based on neural network and modified ant colony algorithm is created by applying modified ant colony algorithm to neural network. Using the classifier, 4 types of ECG beats in MIT/BIH arrhythmia database are classified. The result reveals that the modified neural network could improve the performance of network, effectively prevent the local optimization and increase the training speed of network .The better classification performance is obtained compared with t...