The present study aimed to use the proposed system to measure and analyze brain waves of users to allow intelligent upper limb rehabilitation and to optimize the system using a genetic algorithm. The study used EPOC Neuroheadset for Emotiv with EEG electrodes attached as a non-invasive method for measuring brain waves. The brain waves were measured according to the EEG 10-20 standard electrode layout, which allows measurement of signals from each spot where electrodes are attached based on EEG characteristics. The measured data were added in a database. In the intelligent neuro-fuzzy model, wave transform was used for extracting brain wave characteristics according to user intentions and to eliminate noise from the signals in an effort to increase reliability. Moreover, to construct the option rules of the neuro-fuzzy system, FCM technique and optimal cluster evaluation method were used. Furthermore, the asymmetric Gaussian membership function was used to improve performance, whereas SD and WF divided into left and right sides were used to express the chromosomes. Optimal EEG electrode locations were found, and comparative analysis was performed on the differences based on membership function, number of clusters, and number of learning generations, learning algorithm, and wavelet settings. The performance evaluation results showed that the optimal EEG electrode locations were F7, F8, FC5, and FC6, whereas the accuracy of learning and test data of user-intention recognition was found to be 94.2% and 92.3%, respectively, which suggests that the proposed system can be used to recognize user intention for specific behavior. The system proposed in the present study can allow continued rehabilitation exercise in everyday living according to user intentions, which is expected to help improve the user's willingness to participate in rehabilitation and his or her quality of life.

中文翻译：

---

基于BCI的智能上肢康复机器人系统的设计与实现

本研究旨在使用所提出的系统来测量和分析用户的脑电波，以实现智能上肢康复，并使用遗传算法优化系统。该研究使用 EPOC Neuroheadset for Emotiv 连接 EEG 电极作为测量脑电波的非侵入性方法。脑电波是根据 EEG 10-20 标准电极布局测量的，该布局允许根据 EEG 特征测量来自每个电极连接点的信号。测量数据被添加到数据库中。在智能神经模糊模型中，波变换用于根据用户意图提取脑电波特征并消除信号中的噪声，以提高可靠性。此外，为了构建神经模糊系统的选择规则，采用FCM技术和最优聚类评价方法。此外，不对称高斯隶属函数用于提高性能，而SD和WF分为左右两侧用于表达染色体。找到最佳EEG电极位置，并根据隶属函数、聚类数、学习代数、学习算法、小波设置等因素对差异进行比较分析。性能评估结果表明，最佳脑电电极位置为 F7、F8、FC5 和 FC6，而用户意图识别的学习和测试数据的准确率分别为 94.2% 和 92.3%，这表明提出的系统可用于识别用户对特定行为的意图。