用健康人脑电特征实现中风手康复的实时脑机接口
A Real-Time BCI for Stroke Hand Rehabilitation Using Latent EEG Features from Healthy Subjects
- 用健康人脑电数据训练模型提取单次试次特征
- 实时分类准确率达60%至86%，离线最高89.3%
- 低成本便携系统，适合居家神经康复使用
本研究提出一种实时、便携的脑-机接口（BCI）系统，用于中风患者的手部康复。系统结合低成本3D打印机械外骨骼与嵌入式控制器，将脑电信号转化为手部动作。采用14通道Emotiv EPOC+头戴设备采集EEG信号，通过监督卷积自编码器（CAE）从单次试次数据中提取有意义的潜在特征。模型基于公开健康人群数据集WAY-EEG-GAL训练，并调整电极布局以匹配Emotiv设备。在多种分类器中，Ada Boost表现最优，离线测试准确率89.3%，F1分数0.89。系统在5名健康受试者上进行实时测试，分类准确率介于60%至86%之间。整个流程——脑电采集、信号处理、分类与机器人控制——部署于NVIDIA Jetson Nano平台并配有实时图形界面。结果表明该系统具备作为低成本、独立运行的居家神经康复解决方案的潜力。
原文摘要 · Abstract (English)
This study presents a real-time, portable brain-computer interface (BCI) system designed to support hand rehabilitation for stroke patients. The system combines a low cost 3D-printed robotic exoskeleton with an embedded controller that converts brain signals into physical hand movements. EEG signals are recorded using a 14-channel Emotiv EPOC+ headset and processed through a supervised convolutional autoencoder (CAE) to extract meaningful latent features from single-trial data. The model is trained on publicly available EEG data from healthy individuals (WAY-EEG-GAL dataset), with electrode mapping adapted to match the Emotiv headset layout. Among several tested classifiers, Ada Boost achieved the highest accuracy (89.3%) and F1-score (0.89) in offline evaluations. The system was also tested in real time on five healthy subjects, achieving classification accuracies between 60% and 86%. The complete pipeline - EEG acquisition, signal processing, classification, and robotic control - is deployed on an NVIDIA Jetson Nano platform with a real-time graphical interface. These results demonstrate the system's potential as a low-cost, standalone solution for home-based neurorehabilitation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。