QRS-Complex detection via Spiking Neural Networks

Cardiovascular diseases are the leading cause of death world wide. Close monitoring of high-risk patient plays a major role in preventing premature cardiac death. To be able to maximize the monitoring time, this work implements a Spiking Neural Network (SNN) to analyze an Electrocardiogram (ECG). A proof-of-concept model has been developed, which is capable of detecting QRS-Complexes in an Send- On-Delta-Sampled ECG signal with an average accuracy of over 90%, while being much more power effi cient than traditional artifi cial neuronal networks.