Paper Title
ECG Disease Detection & Feature Extraction by Wavelet Transformation

Abstract
ECG is the most common as well as basic test to run on patients to check any kind of anomalies in the heart. In the ECG result 10 to 20 minutes long continuous data of a patient’s heart is down sampled and printed as a 1D graph. We have developed a program which will take the continuous dataset from the ECG machine and analyses the data and extracts various features of the ECG wave. At first we decompose the data using Wavelet decomposition. Then the data is reconstructed in 4 levels which removes the noise from the signal. In the same time we detect major components of the ECG wave which is P wave, QRS complex and T wave. Then we calculate ST deviation, heart rate and extract other features such as location and amplitude of each wave in order to detect anomalies. Finally our output provides the heart status (healthy, if any disease found, if any major or minor risk) in a language that the patient can understand and also some detailed wave properties in medical term for the doctors. Keywords— Dataset of ECG Machine, Wavelet Decomposition, Removing Noise, Detecting Anomalies Etc