Key result
Efficient 1-D CNN hardware achieves ~99% accuracy in classifying five ECG beat classes.
Why the study?
Wearable healthcare devices with diagnostic capability face challenges balancing limited hardware resources with high diagnostic accuracy.
The proposed hardware architecture for 1-D CNNs enables highly accurate and resource-efficient ECG classification suitable for wearable healthcare devices.
Enables high-accuracy on-device ECG classification in wearables; leaves open prospective clinical validation of 1-D CNN hardware.
Nowadays, with the increasing shortage of traditional medical resources, the existing portable monitoring healthcare device is no longer satisfactory. Thus, wearable healthcare device with diagnostic capability is becoming much more desirable. However, the design of wearable healthcare device faces the challenge of limited hardware resource and high diagnostic accuracy. In this paper, an efficient hardware architecture is proposed to implement a 1-D CNN with global average pooling (GAP) specially for embedded electrocardiogram (ECG) classification. The GAP is implemented by substituting division into shifting operation without extra computing resource consumption and it can largely reduce the parameters of the network. The fully pipelined processing unit (PU) array is designed to increase computing efficiency. A sign bit based dynamic activation strategy is developed for removing redundant multiplications and resource consumption of ReLU. The proposed efficient hardware architecture is implemented on Xilinx Zynq ZC706 board and achieves an average performance of 25.7 GOP/s under 200-MHz with resource consumption of 1538 LUT, which makes resource efficiency improved by more than 3× compared with non-optimized case. The averaged classification accuracy of five ECG beats classes is 99.10%. In brief, the proposed efficient hardware design is prospective for wearable healthcare device especially in ECG classification area.
No takes yet. Share an insight, caveat, or question.
Lu et al. (2021) studied ECG classification. 1-D CNN with global average pooling (GAP) hardware architecture vs. non-optimized case was evaluated on Classification accuracy of five ECG beats classes. The proposed 1-D CNN hardware architecture achieved an average performance of 25.7 GOP/s and an average classification accuracy of 99.10% for five ECG beats classes.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: