Electrocardiographic Signal Classification with Evolutionary Artificial Neural Networks

摘要: This work presents an evolutionary ANN classifier system as heart beat classification algorithm suitable for implementation on the PhysioNet/Computing in Cardiology Challenge 2011 [14], whose aim is to develop efficient able run within a mobile phone, that can provide useful feedback process of acquiring diagnostically 12-lead Electrocardiography (ECG) recording. The method used such problem apply very powerful natural computing analysis tool, namely neural networks, based joint evolution topology and connection weights together with novel similarity-based crossover. The focuses discerning between usable unusable electrocardiograms tele-medically acquired from embedded devices. A prepropcessing Discrete Fourier Trasform has been applied before approach order extract ECG feature dataset frequency domain. Finally, series tests carried out evaluate performance accuracy challenge.