RNN-Based Heartbeat Sound Analysis With Django Integration

Authors: Sri Mira P, Professor Dr. P. Sujatha, Head, Assistant Professor Dr.M.Sakthivanitha

Abstract: This research work presents an innovative approach to heartbeat audio classification using Recurrent Neural Networks (RNNs) integrated with the Django framework. The primary aim is to develop an efficient and accurate system for classifying heartbeat sounds to aid in the early detection and diagnosis of cardiac conditions. The system leverages RNNs, which are particularly suited for processing sequential data, to analyze and classify heartbeat audio recordings. The Django framework facilitates seamless integration, providing a robust and scalable web application for data management, model deployment, prediction. The RNN model is trained on a diverse dataset of heartbeat audio recordings, enabling it to recognize various cardiac anomalies. The proposed system demonstrates high accuracy and reliability, making it a valuable tool for healthcare professionals. Additionally, the integration with Django ensures that the system can be easily accessed and utilized in clinical settings, promoting widespread adoption and improving patient outcomes.