Automatic Arrhythmia Detection Based on the Probabilistic Neural Network with FPGA Implementation

This paper presents a prototype implementation of arrhythmia classification using Probabilistic neural network (PNN). Arrhythmia is an irregular heartbeat, resulting in severe heart problems if not diagnosed early. Therefore, accurate and robust vital task for cardiac patients. The ECG has been performed PNN into eight classes unique combination six features: rate, spectral entropy, 4th order autoregressive coefficients. In addition, FPGA proposed to the complete system classification. Artix-7 board used easy fast execution As result, average accuracy found be 98.27%, time consumed 17 seconds.