• SHARU PRIYA S
• Mr.JAYAKUMAR D

The analysis of electrocardiogram (ECG) data categorization is crucial for the systematic identification of coronary artery disease. It is common to divide the two steps of feature extraction and pattern categorization into two segments. Recent studies have found that deep neural networks are more adept than experienced cardiologists at detecting cardiac arrhythmia. These networks were taught on huge amounts of data. Recent developments in artificial intelligence are to blame for this. Deep convolutional neural networks are used in this study's technique for classifying ECG rhythms (CNN). For the CNN to identify and eventually generalize the different ECG arrhythmia types, as data provided, the wavelengths of the different kinds of arrhythmia were employed. The classification results show that the suggested CNN model, when trained and tested on ECG samples MIT-BIH arrhythmia collection, with a median level of precision of 99.9%. The most precise and effective tool is the classification. Additionally, a CNN model and a deep neural network model were contrasted. According to comparative statistics, the superior to the existing classifier was able to obtain a 90.93% mean accuracy. It is thus demonstrated the CNN classifier under consideration, which uses import ECG spectral images, may improve categorization accuracy without additional human which was before of the ECG data.

"ECG Image Analysis For Arrhythmia Disease Using Deep Learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 9, page no.b697-b701, September-2023, Available :http://www.jetir.org/papers/JETIR2309175.pdf

"ECG Image Analysis For Arrhythmia Disease Using Deep Learning ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 9, page no. ppb697-b701, September-2023, Available at : http://www.jetir.org/papers/JETIR2309175.pdf