Key result
Novel CNN accelerator chip demonstrates high accuracy and low power for abnormal heartbeat detection.
Why the study?
A very-large-scale integration implementation of a CNN inference for abnormal heartbeat detection was proposed to achieve high-speed, small-area, and high-accuracy arrhythmia detection.
A novel VLSI implementation of a CNN accelerator provides a high-speed, low-power, and highly accurate hardware solution for automated arrhythmia detection.
May enable efficient wearable arrhythmia detection; leaves open clinical validation before practice adoption.
In this study, a very‐large‐scale integration implementation of a convolutional neural network (CNN) inference for abnormal heartbeat detection was proposed. Four‐lead electrocardiogram signals were used to detect abnormal heartbeat conditions, such as premature ventricular complex. 1D CNNs and fully connected layers were utilised in the proposed chip to achieve high‐speed, small‐area, and high‐accuracy arrhythmia detection. The proposed chip was implemented using a 90‐nm complementary metal‐oxide‐semiconductor process and operated at 125 MHz with a core area. The power consumption was at high‐speed operation frequency (125 MHz) and at for low‐power applications. The detection accuracy was based on the MIT‐BIH arrhythmia database. Consequently, the properties of high speed, low power, small area, and high accuracy were established in the proposed accelerator chip.
No takes yet. Share an insight, caveat, or question.
Chen et al. (2020) studied Abnormal heartbeat conditions (arrhythmia). Convolutional neural network (CNN) accelerator chip was evaluated on Arrhythmia detection accuracy. A proposed convolutional neural network accelerator chip for abnormal heartbeat detection established properties of high speed, low power, small area, and high accuracy.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: