Real-Time Motion Artifact Removal in fNIRS with Denoising Autoencoder at the Edge

Functional near-infrared spectroscopy (fNIRS) can be used to measure cortical hemodynamics, with advantages such as non-invasiveness, high spatial resolution, wearability, ease of use and relatively low cost. These features make it potentially suitable for translational applications such as brain-computer interface (BCI), neurofeedback, and personalized healthcare. However, fNIRS signals are susceptible to motion artifacts (MAs), which can obscure physiological information. Herein, we propose to deploy a denoising autoencoder (DAE) network on an STM32 microcontroller for real-time multichannel MA removal at the edge. The DAE model was trained on fNIRS data augmented with simulated MAs. It was deployed on the edge device without any performance degradation, outperforming the conventional wavelet-based methods. With an inference time of 38 ms, this implementation is well-suited for real-time processing of multi-channel fNIRS data. Additionally, the low memory usage and CPU workload of the model make it ideal for deployment on diverse microcontroller platforms. This work holds the potential to enable the wider applications of wearable fNIRS in practice.