A novel 1-D convolutional neural network achieved an overall accuracy of 95.52% for classifying 15 heartbeat types on the MIT-BIH database and 95.70% for 7 types on the INCART database.
A novel 1-D convolutional neural network demonstrates high accuracy (>95%) for automated heartbeat classification using standard ECG databases.
This paper puts forward a 1-D convolutional neural network (CNN) that exploits a novel analysis of the correlation between the two leads of the noisy electrocardiogram (ECG) to classify heartbeats. The proposed method is one-dimensional, enabling complex structures while maintaining a reasonable computational complexity. It is based on the combination of elementary handcrafted time domain features, frequency domain features through spectrograms and the use of autoregressive modeling. On the MIT-BIH database, a 95.52% overall accuracy is obtained by classifying 15 types, whereas a 95.70% overall accuracy is reached when classifying 7 types from the INCART database.
Tanoh et al. (Fri,) conducted a other in ECG classification. 1-D CCANet (1-D convolutional neural network) was evaluated on Overall accuracy for classifying heartbeats. A novel 1-D convolutional neural network achieved an overall accuracy of 95.52% for classifying 15 heartbeat types on the MIT-BIH database and 95.70% for 7 types on the INCART database.