Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China; Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen 518055, China; Shenzhen Engineering Laboratory of Neural Rehabilitation Technology, Shenzhen 518055, China.
School of ICT, Sirindhorn International Institute of Technology, Thammasat University, Thailand.
Comput Methods Programs Biomed. 2021 Jul;206:106121. doi: 10.1016/j.cmpb.2021.106121. Epub 2021 Apr 21.
Recognition of motor intention based on electroencephalogram (EEG) signals has attracted considerable research interest in the field of pattern recognition due to its notable application of non-muscular communication and control for those with severe motor disabilities. In analysis of EEG data, achieving a higher classification performance is dependent on the appropriate representation of EEG features which is mostly characterized by one unique frequency before applying a learning model. Neglecting other frequencies of EEG signals could deteriorate the recognition performance of the model because each frequency has its unique advantages. Motivated by this idea, we propose to obtain distinguishable features with different frequencies by introducing an integrated deep learning model to accurately classify multiple classes of upper limb movement intentions.
The proposed model is a combination of long short-term memory (LSTM) and stacked autoencoder (SAE). To validate the method, four high-level amputees were recruited to perform five motor intention tasks. The acquired EEG signals were first preprocessed before exploring the consequence of input representation on the performance of LSTM-SAE by feeding four frequency bands related to the tasks into the model. The learning model was further improved by t-distributed stochastic neighbor embedding (t-SNE) to eliminate feature redundancy, and to enhance the motor intention recognition.
The experimental results of the classification performance showed that the proposed model achieves an average performance of 99.01% for accuracy, 99.10% for precision, 99.09% for recall, 99.09% for f1_score, 99.77% for specificity, and 99.0% for Cohen's kappa, across multi-subject and multi-class scenarios. Further evaluation with 2-dimensional t-SNE revealed that the signal decomposition has a distinct multi-class separability in the feature space.
This study demonstrated the predominance of the proposed model in its ability to accurately classify upper limb movements from multiple classes of EEG signals, and its potential application in the development of a more intuitive and naturalistic prosthetic control.
基于脑电图（EEG）信号的运动意图识别由于其在严重运动障碍患者非肌肉交流和控制方面的显著应用，在模式识别领域引起了相当多的研究兴趣。在 EEG 数据分析中，实现更高的分类性能取决于 EEG 特征的适当表示，这主要表现在应用学习模型之前具有一个独特的频率。忽略 EEG 信号的其他频率可能会降低模型的识别性能，因为每个频率都有其独特的优势。受此启发，我们提出通过引入集成深度学习模型来获得具有不同频率的可区分特征，以准确分类多种上肢运动意图。
所提出的模型是长短期记忆（LSTM）和堆叠自动编码器（SAE）的组合。为了验证该方法，招募了四名高级上肢截肢者来执行五项运动意图任务。在通过将与任务相关的四个频带馈送到模型中，探索输入表示对 LSTM-SAE 性能的影响之前，首先对获得的 EEG 信号进行预处理。通过 t 分布随机邻居嵌入（t-SNE）进一步改进学习模型，以消除特征冗余并增强运动意图识别。
分类性能的实验结果表明，所提出的模型在多主体和多类场景下，平均准确率为 99.01%，精度为 99.10%，召回率为 99.09%，f1 得分为 99.09%，特异性为 99.77%，Cohen 的kappa 为 99.0%。进一步的二维 t-SNE 评估表明，信号分解在特征空间中具有明显的多类可分离性。
本研究表明，所提出的模型在准确分类多种 EEG 信号的上肢运动方面具有优势，并且在开发更直观和自然的假肢控制方面具有潜在应用。
