Zhu Yisen, Ji Zhouyu, Li Shuran, Wang Haicheng, Fu Yunfa, Wang Hongtao
College of Electronics and Information Engineering, Wuyi University, Jiangmen, Guangdong 529020, P. R. China.
School of Electronic & Information Engineering and Communication Engineering, Guangzhou City University of Technology, Guangdong 510800, P. R. China.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2025 Jun 25;42(3):455-463. doi: 10.7507/1001-5515.202412051.
This paper realized a portable brain-computer interface (BCI) system tailored for smart healthcare. Through the decoding of steady-state visual evoked potential (SSVEP), this system can rapidly and accurately identify the intentions of subjects, thereby meeting the practical demands of daily medical scenarios. Firstly, an SSVEP stimulation interface and an electroencephalogram (EEG) signal acquisition software were designed, which enable the system to execute multi-target and multi-task operations while also incorporating data visualization functionality. Secondly, the EEG signals recorded from the occipital region were decomposed into eight sub-frequency bands using filter bank canonical correlation analysis (FBCCA). Subsequently, the similarity between each sub-band signal and the reference signals was computed to achieve efficient SSVEP decoding. Finally, 15 subjects were recruited to participate in the online evaluation of the system. The experimental results indicated that in real-world scenarios, the system achieved an average accuracy of 85.19% in identifying the intentions of the subjects, and an information transfer rate (ITR) of 37.52 bit/min. This system was awarded third prize in the Visual BCI Innovation Application Development competition at the 2024 World Robot Contest, validating its effectiveness. In conclusion, this study has developed a portable, multifunctional SSVEP online decoding system, providing an effective approach for human-computer interaction in smart healthcare.
本文实现了一种专为智能医疗量身定制的便携式脑机接口（BCI）系统。通过对稳态视觉诱发电位（SSVEP）的解码，该系统能够快速准确地识别受试者的意图，从而满足日常医疗场景的实际需求。首先，设计了一个SSVEP刺激接口和一个脑电图（EEG）信号采集软件，使系统能够执行多目标和多任务操作，同时还具备数据可视化功能。其次，利用滤波器组典型相关分析（FBCCA）将从枕叶区域记录的EEG信号分解为八个子频段。随后，计算每个子频段信号与参考信号之间的相似度，以实现高效的SSVEP解码。最后，招募了15名受试者参与该系统的在线评估。实验结果表明，在实际场景中，该系统在识别受试者意图方面的平均准确率达到85.19%，信息传输速率（ITR）为37.52比特/分钟。该系统在2024年世界机器人大会视觉BCI创新应用开发竞赛中获得三等奖，验证了其有效性。总之，本研究开发了一种便携式、多功能的SSVEP在线解码系统，为智能医疗中的人机交互提供了一种有效方法。
