Probabilistic Neural Network for the Automatic Detection of QRS-complexes in ECG using Slope

This paper presents the application of Probabilistic Neural Networks (PNN) for the classification automatic detection of QRS-complexes in Electrocardiogram (ECG). Raw ECG signal contains the power line interference and baseline wander. This can be removed by using Digital filtering techniques. For the QRS-detection, Probabilistic Neural Networks is used as pattern classifier. MATLAB is applied to implement the proposed algorithm. The performance of the algorithm is validated using each lead of the 12-lead simultaneously recorded ECGs from the dataset-3 of the CSE multi-lead measurement library. The QRScomplexes detection rate of 99.23% is achieved. The percentage of false positive is 1.03% and false negative is 0.77%. The overall results obtained of the PNN in terms of the detection rate performance in comparison to the other methods reported in literature. The proposed algorithm shows the effectiveness for QRS-detection. Keywords— Detection, Electrocardiogram (ECG), Morphologies of QRS-complexes, Probabilistic Neural Networks (PNN), QRS-complexes.