CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology (SIAT), Shenzhen, 518055, China.
Institute of Biomedical and Health Engineering, SIAT, Chinese Academy of Sciences (CAS), Shenzhen, 518055, China.
J Med Syst. 2017 Oct 28;41(12):194. doi: 10.1007/s10916-017-0843-z.
To control multiple degrees of freedom (MDoF) upper limb prostheses, pattern recognition (PR) of electromyogram (EMG) signals has been successfully applied. This technique requires amputees to provide sufficient EMG signals to decode their limb movement intentions (LMIs). However, amputees with neuromuscular disorder/high level amputation often cannot provide sufficient EMG control signals, and thus the applicability of the EMG-PR technique is limited especially to this category of amputees. As an alternative approach, electroencephalograph (EEG) signals recorded non-invasively from the brain have been utilized to decode the LMIs of humans. However, most of the existing EEG based limb movement decoding methods primarily focus on identifying limited classes of upper limb movements. In addition, investigation on EEG feature extraction methods for the decoding of multiple classes of LMIs has rarely been considered. Therefore, 32 EEG feature extraction methods (including 12 spectral domain descriptors (SDDs) and 20 time domain descriptors (TDDs)) were used to decode multiple classes of motor imagery patterns associated with different upper limb movements based on 64-channel EEG recordings. From the obtained experimental results, the best individual TDD achieved an accuracy of 67.05 ± 3.12% as against 87.03 ± 2.26% for the best SDD. By applying a linear feature combination technique, an optimal set of combined TDDs recorded an average accuracy of 90.68% while that of the SDDs achieved an accuracy of 99.55% which were significantly higher than those of the individual TDD and SDD at p < 0.05. Our findings suggest that optimal feature set combination would yield a relatively high decoding accuracy that may improve the clinical robustness of MDoF neuroprosthesis.
The study was approved by the ethics committee of Institutional Review Board of Shenzhen Institutes of Advanced Technology, and the reference number is SIAT-IRB-150515-H0077.
为了控制多自由度（MDoF）上肢假肢，已经成功应用了肌电图（EMG）信号的模式识别（PR）技术。该技术要求截肢者提供足够的 EMG 信号来解码他们的肢体运动意图（LMIs）。然而，患有神经肌肉疾病/高位截肢的截肢者往往无法提供足够的 EMG 控制信号，因此 EMG-PR 技术的适用性受到限制，尤其是对这一类截肢者。作为替代方法，已经利用从大脑中记录的脑电图（EEG）信号来解码人类的 LMIs。然而，大多数现有的基于 EEG 的肢体运动解码方法主要侧重于识别有限的上肢运动类别。此外，很少考虑用于解码多类 LMIs 的 EEG 特征提取方法的研究。因此，使用 32 种 EEG 特征提取方法（包括 12 种谱域描述符（SDD）和 20 种时域描述符（TDD）），基于 64 通道 EEG 记录，解码与不同上肢运动相关的多种运动想象模式。从获得的实验结果来看，最佳的单个 TDD 的准确性为 67.05±3.12%，而最佳的 SDD 的准确性为 87.03±2.26%。通过应用线性特征组合技术，最佳的组合 TDD 记录的平均准确率为 90.68%，而 SDD 的准确率为 99.55%，这明显高于单独的 TDD 和 SDD 的准确率，p<0.05。我们的研究结果表明，最佳特征集组合将产生相对较高的解码准确性，这可能提高 MDoF 神经假肢的临床稳健性。
本研究得到深圳先进技术研究院伦理委员会的批准，注册号为 SIAT-IRB-150515-H0077。
