Cai Zhengbo, Li Penghai, Cheng Longlong, Yuan Ding, Li Mingji, Li Hongji
School of Integrated Circuit Science and Engineering, Tianjin University of Technology, Tianjin, 300384 People's Republic of China.
China Electronics Cloud Brain (Tianjin) Technology Co., Ltd., Tianjin, 300392 People's Republic of China.
Biomed Eng Lett. 2024 Nov 8;15(1):217-227. doi: 10.1007/s13534-024-00438-4. eCollection 2025 Jan.
Brain-computer interface (BCI) has been widely used in human-computer interaction. The introduction of artificial intelligence has further improved the performance of BCI system. In recent years, the development of BCI has gradually shifted from personal computers to embedded devices, which boasts lower power consumption and smaller size, but at the cost of limited device resources and computing speed, thus can hardly improve the support of complex algorithms. This paper proposes a heterogeneous BCI architecture based on ARM + FPGA, enabling real-time processing of electroencephalogram (EEG) signals. Adopting data quantization, layer fusion and data augmentation to optimize the compact neural network model EEGNet, and design dedicated hardware engines to accelerate the network. Experimental results show that the system achieves 93.3% classification accuracy for steady-state visual evoked potential signals, with a time delay of 0.2 ms per trail, and a power consumption of approximately (1.91 W). That is 31.5 times faster acceleration is realized at the cost of only 0.7% lower accuracy compared with the conventional processor. The results show that the BCI architecture proposed in this study has strong practicability and high research significance.
脑机接口（BCI）已在人机交互中得到广泛应用。人工智能的引入进一步提升了BCI系统的性能。近年来，BCI的发展逐渐从个人电脑转向嵌入式设备，嵌入式设备具有功耗更低、尺寸更小的优点，但代价是设备资源和计算速度有限，因此很难提升对复杂算法的支持。本文提出了一种基于ARM+FPGA的异构BCI架构，能够对脑电图（EEG）信号进行实时处理。采用数据量化、层融合和数据增强来优化紧凑型神经网络模型EEGNet，并设计专用硬件引擎来加速网络。实验结果表明，该系统对稳态视觉诱发电位信号的分类准确率达到93.3%，每次试验的时间延迟为0.2毫秒，功耗约为1.91瓦。与传统处理器相比，在精度仅降低0.7%的情况下实现了31.5倍的加速。结果表明，本研究提出的BCI架构具有很强的实用性和很高的研究意义。
