With Motor-Imagery (MI) Brain--Machine Interfaces (BMIs) we may control machines by merely thinking of performing a motor action. Practical use cases require a wearable solution where the classification of the brain signals is done locally near the sensor using machine learning models embedded on energy-efficient microcontroller units (MCUs), for assured privacy, user comfort, and long-term usage. In this work, we provide practical insights on the accuracy-cost tradeoff for embedded BMI solutions. Our proposed Multispectral Riemannian Classifier reaches 75.1% accuracy on 4-class MI task. We further scale down the model by quantizing it to mixed-precision representations with a minimal accuracy loss of 1%, which is still 3.2% more accurate than the state-of-the-art embedded convolutional neural network. We implement the model on a low-power MCU with parallel processing units taking only 33.39ms and consuming 1.304mJ per classification.
@article{arxiv.2102.11221,
title = {Mixed-Precision Quantization and Parallel Implementation of Multispectral Riemannian Classification for Brain--Machine Interfaces},
author = {Xiaying Wang and Tibor Schneider and Michael Hersche and Lukas Cavigelli and Luca Benini},
journal= {arXiv preprint arXiv:2102.11221},
year = {2021}
}