| 寿萧凯,蔡世波,都明宇.基于EEG的Cbi-BPNN模型在线预测“坐-站-走”姿态变换研究[J].高技术通讯(中文),2026,36(6):611~622 |
| 基于EEG的Cbi-BPNN模型在线预测“坐-站-走”姿态变换研究 |
| Online prediction of sit-stand-walk posture transformation by EEG-based Cbi-BPNN model |
| |
| DOI：10. 3772 / j. issn. 1002 - 0470. 2026. 06. 007 |
| 中文关键词: 运动准备电位； 在线预测； “坐-站-走”姿态变换； 共空间模式； 反向传播神经网络 |
| 英文关键词: readiness potential, online prediction, sit-stand-walk posture transformation, common spatial pattern, back propagation neural network |
| 基金项目: |
| 作者 | 单位 | | 寿萧凯 | （浙江工业大学机械工程学院杭州 310023） | | 蔡世波 | | | 都明宇 | |
|
| 摘要点击次数: 73 |
| 全文下载次数: 64 |
| 中文摘要: |
| 本文目的是提出一种“坐-站-走”姿态变换在线预测方法，为更好地控制下肢康复机器人提供理论支撑。首先，通过滤波、动态基线校正等方法对脑电信号进行在线预处理；然后，使用定向共空间模式（directional common spatial pattern, DCSP）、相关系数（correlation coefficent, CC）、曲线拟合（curve fitting, CF）、希尔伯特-黄变换（Hilbert-Huang transform, HHT）、离散小波变换（discrete wavelet transform, DWT）等方法在线提取多维度特征；最后，设计了一种级联式反向传播神经网络（cascaded by two back propagation neural network，Cbi-BPNN）模型进行“坐-站-走”姿态变换在线预测。本文招募8名受试者在特定范式下分别开展“坐-站-走”姿态变换脑电信号采集实验和在线预测系统验证实验，对比了8种姿态变换预测特征组合以及5种分类模型。实验结果表明，使用DCSP-CC-CF-HHT-DWT混合特征的姿态变换预测模型的离线分类准确率最高为76.09%，该模型可以在实际运动前200 ms左右实现在线预测，最高准确率为65.00 %。 |
| 英文摘要: |
| The purpose of this paper is to put forward an online prediction method for ‘sit-stand-walk’ posture transformation, which can provides theoretical support for better control of lower limb rehabilitation robot. Firstly, the electroencephalogram(EEG) signals were preprocessed online by filtering and the dynamic baseline correction method. Secondly, the multi-dimensional features were extracted online using the improved directional common spatial pattern (DCSP), correlation coefficient (CC) calculation, curve fitting (CF), Hilbert-Huang transform (HHT)and discrete wavelet transform (DWT). Finally, the sit-stand-walk posture transformation was predicted online by the model which is cascaded by two back-propagation neural network (Cbi-BPNN). In this paper, eight subjects were recruited to carry out the sit-stand-walk posture transformation EEG signals acquisition experiment and the verification experiment of the online prediction system. Eight feature combinations and five classification models for posture transformation prediction were also compared. The experimental results show that using the hybrid features of DCSP-CC-CF-HHT-DWT as the inputs of the posture transformation prediction model can obtain the highest offline accuracy of 76.09%.The model can predict human posture transformation about 200 ms before the actual movement with the highest online accuracy of 65.00%. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|
