A New Method for Detection of ECG Signal Integrated with Neural Network for Classification of Disease Condition

Designing a system capable of automatic identification of cardiac arrhythmias from recorded ECG signals is considerably important for clinical diagnosis and treatment. In this paper, we present a new method based on extension of second order derivative to recognize QRS domains, we detect ECG signal domains consist of PQRST, and then by using the extracted information, design a feed-forward Neural Network (NN) to identify and classify cardiac arrhythmias, healthy and unhealthy people. The proposed method compared to several methods. Results indicate the accuracy of classification and detection of PQRST peaks that is better than the other methods. The proposed method has been hig