A binary convolutional neural network deployed on an FPGA achieved 97.3% accuracy for classifying Ventricular Ectopic Beats with a dynamic power dissipation of only 10.5-μW.
A novel bCNN algorithm deployed on an FPGA fabric provides highly accurate and energy-efficient classification of ventricular ectopic beats for wearable edge AI devices.
Wearable Artificial Intelligence-of-Things (AIoT) requires edge devices to be resource and energy-efficient. In this paper, we design and implement an efficient binary convolutional neural network (bCNN) algorithm utilizing function-merging and block-reuse techniques to classify between Ventricular and non-Ventricular Ectopic Beat images. We deploy our model into a low-resource low-power field programmable gate array (FPGA) fabric. Our model achieves a classification accuracy of 97.3%, sensitivity of 91.3%, specificity of 98.1%, precision of 86.7%, and F1-score of 88.9%, along with dynamic power dissipation of only 10.5-μW.
Wong et al. (Fri,) conducted a other in Ventricular Ectopic Beat. Binary convolutional neural network (bCNN) algorithm was evaluated on Classification accuracy. A binary convolutional neural network deployed on an FPGA achieved 97.3% accuracy for classifying Ventricular Ectopic Beats with a dynamic power dissipation of only 10.5-μW.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: