A Measurement of Heart Rate in 12 lead ECG by an Entropic Method Using Artificial Neural Network

Minakshi Chaudhary, Er. D.V. Saini, Er. Sukhvinder Kaur

Abstract: Application of Artificial Neural Network is used for measurement of heart rate in 12 lead ECG (Electrocardiogram) using combined entropic methods. The ECG signal is filtered using Digital filtering techniques to remove power line interference and base line wander. The K-means algorithm is used as a classifier for detection of QRS and non-QRS complexes in ECG. Both algorithms performed highly effectively with using standard CSE ECG database. The Artificial Neural Network is used for detection of QRS complexes. The effectiveness of the method has been demonstrated by its accuracy rate of 99.79 %. The method has certain limitations as well thus giving FP and FN of 0.068 % and 0.002 % respectively. Over all this method is found to be most effective one.

Keywords: ANN Artificial neural network, FN False negative, FP False positive, EBPANN Error Back Propagation ANN