Figures & data
Figure 1. Fifty randomly selected heartbeat signals for (a) Class N, (b) Class L, (c) Class R, (d) Class V, (e) Class A.
![Figure 1. Fifty randomly selected heartbeat signals for (a) Class N, (b) Class L, (c) Class R, (d) Class V, (e) Class A.](/cms/asset/44554f5b-8024-4194-a146-26b84630562c/uaai_a_1501910_f0001_oc.jpg)
Table 1. Heartbeat classes given by the MIT-BIH database along with the regrouping defined by the AAMI standard.
Figure 2. Example of CNN architecture (Mathworks online resource, Citation2017).
![Figure 2. Example of CNN architecture (Mathworks online resource, Citation2017).](/cms/asset/f3efa815-6124-45ab-82e9-a63af330c292/uaai_a_1501910_f0002_b.gif)
Figure 3. Visualization of the parameter setup at i-th ReLU and k-th ADD (Yang and Ramanan Citation2015).
![Figure 3. Visualization of the parameter setup at i-th ReLU and k-th ADD (Yang and Ramanan Citation2015).](/cms/asset/f2bbc1c0-9e49-4034-b16d-3f57ea44e85d/uaai_a_1501910_f0003_b.gif)
Table 2. Summary of the training and testing heartbeat samples.
Table 3. The details of back-bone CNN architecture of DAG-CNN model.
Table 4. Different heartbeat types classification result.
Table 5. Four heartbeat types classification metrics compared to the state-of-the-art (percentage, %).
Table 6. SVEB and VEB Classification metrics compared to the state-of-the (percentage, %).