• Ch.Rani
• A.Bharat
• B.Bhavana
• Ch.Meghana
• K.Naga Prakash

This study introduces a novel approach to arrhythmia detection using a diverse dataset obtained from Kaggle. The dataset encompasses six distinct arrhythmia classes: 'Flutter Waves', 'Murmur', 'Normal Sinus Rhythm', 'Q Wave', 'Sinus Arrest', and 'Ventricular Premature Depolarization'. Through the utilization of advanced image processing techniques and machine learning algorithms, our ResNet50 model achieves a notable accuracy of 92 in precisely categorizing arrhythmia patterns. This study is important because of what it can do. to advance early diagnosis and intervention for cardiac arrhythmias, thereby contributing to enhanced patient outcomes and healthcare management. This innovative methodology demonstrates promising prospects for the development of automated arrhythmia detection systems in clinical practice.

Resnet-50, Convolution neural Network (CNN), Feature Extraction, Hybrid model, Deep Learning

"ARRHYTHMIA DETECTION BASED ON ECG USING RESNET MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.i347-i354, April-2024, Available :http://www.jetir.org/papers/JETIR2404843.pdf

"ARRHYTHMIA DETECTION BASED ON ECG USING RESNET MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppi347-i354, April-2024, Available at : http://www.jetir.org/papers/JETIR2404843.pdf