Abstract:
Electrocardiogram (ECG) signal is informative as well as non-invasive clinical
tool to diagnose cardiac diseases of human heart. However, the diagnosis
requires professionals’ clarification and is also time-consuming. To make the
diagnosis proficient, a novel convolutional neural network (CNN) has been
proposed for automatic arrhythmia detection. In this work, the ECG data
collected from the MIT-BIH database have been preprocessed, and segmented in
short ECG segments of 60 s. Then, all these segments have been transformed
into scalogram images obtained from time-frequency analysis using continuous
wavelet transform (CWT). Finally, these scalogram images have been exploited
as an input for our designed CNN classifier to classify cardiac arrhythmia. In this
approach, the overall accuracy, sensitivity, and specificity are 99.39%, 98.79%,
and 100% respectively. Proposed CNN model has significant advantages, and it
can be used to differentiate the healthy and arrhythmic patients effectively.
