Paper Title
ECG Anomaly Detection and Classification of 1-D ECG Signals
Abstract
Collection and processing ECG data leads to the identification, recognition and prediction of diseases by
extracting and analyzing the basic features of physical data. This study presents an end-to-end intelligence for abnormal
detection and classification of raw one-dimensional (1D) electrocardiogram (ECG) signals to evaluate the performance of
the Heart. Raw ECG data is collected first and then analyzed in depth for abnormal detection. A deep learning-based autoencoder
(AE) algorithm is used for undetectable detection of one-dimensional ECG time series signals. The application
process then identifies this through a multi-tag algorithm. Improving negative features are compiled from large and diverse
data sets to improve classification accuracy and model stability.
Keywords - ECG, Deep Learning, Python, Disease Detection, LSTM, Auto-Encoder