Convolutional-Recurrent Neural Networks on Low-Power Wearable Platforms for Cardiac Arrhythmia Detection
This work addresses the challenge of enabling clinical-grade machine learning on resource-constrained wearable devices for healthcare monitoring, but it is incremental as it adapts an existing model.
The paper tackled the problem of deploying neural networks for cardiac arrhythmia detection on low-power wearable platforms, achieving an F1 score of 0.784 with a memory footprint of 195.6KB and throughput of 33.98MOps/s.
Low-power sensing technologies, such as wearables, have emerged in the healthcare domain since they enable continuous and non-invasive monitoring of physiological signals. In order to endow such devices with clinical value, classical signal processing has encountered numerous challenges. However, data-driven methods, such as machine learning, offer attractive accuracies at the expense of being resource and memory demanding. In this paper, we focus on the inference of neural networks running in microcontrollers and low-power processors which wearable sensors and devices are generally equipped with. In particular, we adapted an existing convolutional-recurrent neural network, designed to detect and classify cardiac arrhythmias from a single-lead electrocardiogram, to the low-power embedded System-on-Chip nRF52 from Nordic Semiconductor with an ARM's Cortex-M4 processing core. We show our implementation in fixed-point precision, using the CMSIS-NN libraries, yields a drop of $F_1$ score from 0.8 to 0.784, from the original implementation, with a memory footprint of 195.6KB, and a throughput of 33.98MOps/s.