Department of Neuroscience and Biomedical Engineering NBE, Aalto University School of Science, P.O. Box 12200, FI-00076, Aalto, Finland.
Aalto Neuroimaging, MEG Core, Aalto University School of Science, Espoo, Finland.
Sci Rep. 2018 Jul 4;8(1):10087. doi: 10.1038/s41598-018-28295-z.
Long calibration time hinders the feasibility of brain-computer interfaces (BCI). If other subjects' data were used for training the classifier, BCI-based neurofeedback practice could start without the initial calibration. Here, we compare methods for inter-subject decoding of left- vs. right-hand motor imagery (MI) from MEG and EEG. Six methods were tested on data involving MEG and EEG measurements of healthy participants. Inter-subject decoders were trained on subjects showing good within-subject accuracy, and tested on all subjects, including poor performers. Three methods were based on Common Spatial Patterns (CSP), and three others on logistic regression with l - or l -norm regularization. The decoding accuracy was evaluated using (1) MI and (2) passive movements (PM) for training, separately for MEG and EEG. With MI training, the best accuracies across subjects (mean 70.6% for MEG, 67.7% for EEG) were obtained using multi-task learning (MTL) with logistic regression and l-norm regularization. MEG yielded slightly better average accuracies than EEG. With PM training, none of the inter-subject methods yielded above chance level (58.7%) accuracy. In conclusion, MTL and training with other subject's MI is efficient for inter-subject decoding of MI. Passive movements of other subjects are likely suboptimal for training the MI classifiers.
校准时间长会阻碍脑机接口（BCI）的可行性。如果使用其他受试者的数据来训练分类器，那么无需初始校准就可以开始基于 BCI 的神经反馈实践。在这里，我们比较了从 MEG 和 EEG 解码左、右手运动想象（MI）的跨受试者方法。在涉及健康参与者的 MEG 和 EEG 测量数据上测试了六种方法。跨受试者解码器是在具有良好的受试者内准确性的受试者上进行训练的，并在所有受试者上进行了测试，包括表现不佳的受试者。三种方法基于公共空间模式（CSP），另外三种方法基于逻辑回归和 l-或 l-范数正则化。使用（1）MI 和（2）PM 分别对 MEG 和 EEG 进行训练，评估了解码准确性。对于 MI 训练，使用逻辑回归和 l-范数正则化的多任务学习（MTL）获得了跨受试者的最佳准确性（MEG 平均准确率为 70.6%，EEG 平均准确率为 67.7%）。MEG 的平均准确率略高于 EEG。对于 PM 训练，没有一种跨受试者方法的准确率超过机会水平（58.7%）。总之，MTL 和使用其他受试者的 MI 进行训练对于 MI 的跨受试者解码是有效的。其他受试者的被动运动可能不适合训练 MI 分类器。
