目的:基于运动想象范式的脑机接口(BMI)为步态过程中的外骨骼控制提供了一种直观的方法。然而,由于准确性限制和对错误激活的敏感性,它们的临床适用性仍然很困难。提出的改进包括将BMI与基于检测错误相关电位(ErrP)的方法集成在一起,以自我调整错误命令,不仅提高系统精度,还有它的可用性。当前研究的目的是用下肢外骨骼表征步态开始时的ErrP,以减少BMI系统中的错误启动。此外,这项研究对于确定哪种类型的反馈很有价值,触觉,视觉,或视觉触觉,在唤起和检测ErrP方面达到最佳性能。
方法:研究的初始阶段集中在步态开始时检测ErrP,以提高基于运动图像(BMI-MI)的异步BMI控制下肢外骨骼的效率。最初,一个实验方案被设计用来在步态开始时唤起ErrP,使用三种不同的刺激:触觉,视觉,和视觉触觉。然后利用迭代选择过程在时域和频域中表征ErrP,并微调各种参数,包括电极分布,特征组合,和分类器。采用具有6个受试者的通用分类器来配置用于检测ErrP并减少错误开始的集成分类系统。
结果:配置有选定参数的合奏系统可产生72.60%±10.23的错误开始平均校正,突出了其校正功效。触觉反馈成为最有效的刺激,在两种训练类型中都优于视觉和视觉触觉反馈。
结论:结果表明,当将ErrP与BMI-MI整合时,减少错误启动的前景很有希望,采用触觉反馈。因此,增强了系统的安全性。随后,进一步的研究工作将集中在检测步态停止运动过程中的潜在错误,为了限制不希望的停止。
OBJECTIVE: Brain-Machine Interfaces (BMIs) based on a motor imagination paradigm provide an intuitive approach for the exoskeleton control during gait. However, their clinical applicability remains difficulted by accuracy limitations and sensitivity to false activations. A proposed improvement involves integrating the BMI with methods based on detecting Error Related Potentials (ErrP) to self-tune erroneous commands and enhance not only the system accuracy, but also its usability. The aim of the current research is to characterize the ErrP at the beginning of the gait with a lower limb exoskeleton to reduce the false starts in the BMI system. Furthermore, this study is valuable for determining which type of feedback, Tactile, Visual, or Visuo-Tactile, achieves the best performance in evoking and detecting the ErrP.
METHODS: The initial phase of the research concentrates on detecting ErrP at the beginning of gait to improve the efficiency of an asynchronous BMI based on motor imagery (BMI-MI) to control a lower limb exoskeleton. Initially, an experimental protocol is designed to evoke ErrP at the start of gait, employing three different stimuli: Tactile, Visual, and Visuo-Tactile. An iterative selection process is then utilized to characterize ErrP in both time and frequency domains and fine-tune various parameters, including electrode distribution, feature combinations, and classifiers. A generic classifier with 6 subjects is employed to configure an ensemble classification system for detecting ErrP and reducing the false starts.
RESULTS: The ensembled system configured with the selected parameters yields an average correction of false starts of 72.60 % ± 10.23, highlighting its corrective efficacy. Tactile feedback emerges as the most effective stimulus, outperforming Visual and Visuo-Tactile feedback in both training types.
CONCLUSIONS: The results suggest promising prospects for reducing the false starts when integrating ErrP with BMI-MI, employing Tactile feedback. Consequently, the security of the system is enhanced. Subsequent, further research efforts will focus on detecting error potential during movement for gait stop, in order to limit undesired stops.