Multiclass ECG Signal Analysis Using Global Average-Based 2-D Convolutional Neural Network Modeling

Cardiovascular diseases have been reported to be the leading cause of mortality across globe. Among such diseases, Myocardial Infarction (MI), also known as “heart attack”, is main interest among researchers, its early diagnosis can prevent life threatening cardiac conditions and potentially save human lives. Analyzing Electrocardiogram (ECG) provide valuable diagnostic information detect different types arrhythmia. Real-time ECG monitoring systems with advanced machine learning methods about health status in real-time improved user’s experience. However, put a burden on portable wearable devices due their high computing requirements. We present an improved, less complex Convolutional Neural Network (CNN)-based classifier model that identifies multiple arrhythmia using two-dimensional image wave real-time. The proposed presented three-layer signal analysis adopted devices. designed, implemented, simulated CNN network Matlab. hardware implementation method validate adaptability systems. European ST-T database recorded single lead L3 used achieved accuracy 99.23%, outperforming most existing solutions.