论文标题
基于EEGNET的精确电机象征脑计算机界面，用于低功率边缘计算
An Accurate EEGNet-based Motor-Imagery Brain-Computer Interface for Low-Power Edge Computing
论文作者
论文摘要
本文介绍了精确且可靠的嵌入式运动象征脑计算机界面（MI-BCI）。提出的基于EEGNET的新型模型与低功率微控制器单元（MCUS）（例如ARM Cortex-M系列）的内存足迹和计算资源的要求匹配。此外，该论文介绍了一组方法，包括时间下采样，频道选择和分类窗口的缩小，以进一步缩小模型，以减少准确性降解的放松内存需求。 Physionet EEG运动/图像数据集的实验结果表明，标准EEGNET在全球验证中的2-，3和4类MI任务上的分类准确性达到82.43％，75.07％和65.07％，超过了2.-ART（SOA）的卷积Neural网络（SOA）（SOA）卷积（SOA）（cnn）的2.5％和2.5％，5.5％和5％。我们的新方法以0.31％的精度损失可忽略不计，并减少7.6倍的记忆足迹损失，而准确度降低为2.51％，而减少了15倍。缩放型号用于运营最小型号的商业皮层MCU，每次推断，每次推理，摄入4.28mj的MCU，以及在中型型号中，适用于44ms和18.1mj的Cortex-M7，可用于中型型号，启用完全自动驾驶，可耐磨，可耐磨和准确的低功率BCI。
This paper presents an accurate and robust embedded motor-imagery brain-computer interface (MI-BCI). The proposed novel model, based on EEGNet, matches the requirements of memory footprint and computational resources of low-power microcontroller units (MCUs), such as the ARM Cortex-M family. Furthermore, the paper presents a set of methods, including temporal downsampling, channel selection, and narrowing of the classification window, to further scale down the model to relax memory requirements with negligible accuracy degradation. Experimental results on the Physionet EEG Motor Movement/Imagery Dataset show that standard EEGNet achieves 82.43%, 75.07%, and 65.07% classification accuracy on 2-, 3-, and 4-class MI tasks in global validation, outperforming the state-of-the-art (SoA) convolutional neural network (CNN) by 2.05%, 5.25%, and 5.48%. Our novel method further scales down the standard EEGNet at a negligible accuracy loss of 0.31% with 7.6x memory footprint reduction and a small accuracy loss of 2.51% with 15x reduction. The scaled models are deployed on a commercial Cortex-M4F MCU taking 101ms and consuming 4.28mJ per inference for operating the smallest model, and on a Cortex-M7 with 44ms and 18.1mJ per inference for the medium-sized model, enabling a fully autonomous, wearable, and accurate low-power BCI.
