• Jaya tiwari
• C.P gautam

ECG is the most common and 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 develop 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. An electrocardiogram (ECG) is an important diagnostic tool for the assessment of cardiac arrhythmias in clinical routine. In this process, we introduce the a deep learning based convolution neural network framework, which is previously trained on a general signal data set is transferred to carry out automatic ECG arrhythmia diagnostics by classifying patient ECG’s into corresponding cardiac conditions. The Main focus of this process is to implement a simple, reliable and easily applicable deep learning technique for the classification of the selected two different cardiac categories conditions. The results demonstrated that the transferred deep learning classification cascaded with a conventional SVM were able to obtain very high performance rates. all this work has been performed by MATLAB simulation

SVM, NN, RF,KNN,CNN,ECG

"Heart Disease Prediction using Data Mining Technique", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 3, page no.1870-1875, March-2020, Available :http://www.jetir.org/papers/JETIR2003267.pdf

"Heart Disease Prediction using Data Mining Technique", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 3, page no. pp1870-1875, March-2020, Available at : http://www.jetir.org/papers/JETIR2003267.pdf