Spiking Reservoir Computing Model for Patient-customized ECG Monitoring

Echo state network (ESN) with leaky-integrated-and-fire (LIF) neurons is employed to address the classical electrocardiogram (ECG) beat classification problem. Due to its computational efficiency and the fact that training amounts to a simple linear regression, this supervised learning algorithm for recurrent neural network (RNN) has been variously considered as a strategy to implement useful computations not only on digital computers but also on emerging unconventional hardware platforms such as neuromorphic microchips. Here, this biological-inspired learning framework is exploited to devise an accurate patient-adaptive model that has the potential to be integrated in wearable cardiac events monitoring devices. The patient-customized network was trained and tested on ECG recordings from MIT-BIH arrhythmia database. The results of simulations showed a functional ESN with spiking neurons can provide accurate, cheap and fast patient-customized heartbeat classifier.