Continuous Heartbeat Monitoring Using Evolvable Block-based Neural Networks

This paper presents continuous heartbeat monitoring using evolvable block-based neural networks (BbNNs). An evolutionary algorithm is used to optimize the structure and weights of BbNN simultaneously. A BbNN, trained with the Hermite transform coefficients and a time interval between the two neighboring R peaks of ECG signal, promises a patient-specific heartbeat monitoring system. BbNNs reconfigure the structure and internal weights to cope with individual differences and the changes in physical conditions. Simulation results using the MIT-BIH Arrhythmia database demonstrate a high accuracy of 98.7% on average for the classification of ventricular ectopic beats (VEBs), being a substantial improvement over conventional techniques.