Electrical and Computer Engineering Department, University of Pittsburgh, Pittsburgh, PA, USA.
Biomed Eng Online. 2020 Apr 16;19(1):23. doi: 10.1186/s12938-020-00765-4.
Generally, brain-computer interfaces (BCIs) require calibration before usage to ensure efficient performance. Therefore, each BCI user has to attend a certain number of calibration sessions to be able to use the system. However, such calibration requirements may be difficult to fulfill especially for patients with disabilities. In this paper, we introduce a probabilistic transfer learning approach to reduce the calibration requirements of our EEG-fTCD hybrid BCI designed using motor imagery (MI) and flickering mental rotation (MR)/word generation (WG) paradigms. The proposed approach identifies the top similar datasets from previous BCI users to a small training dataset collected from a current BCI user and uses these datasets to augment the training data of the current BCI user. To achieve such an aim, EEG and fTCD feature vectors of each trial were projected into scalar scores using support vector machines. EEG and fTCD class conditional distributions were learnt separately using the scores of each class. Bhattacharyya distance was used to identify similarities between class conditional distributions obtained using training trials of the current BCI user and those obtained using trials of previous users.
Experimental results showed that the performance obtained using the proposed transfer learning approach outperforms the performance obtained without transfer learning for both MI and flickering MR/WG paradigms. In particular, it was found that the calibration requirements can be reduced by at least 60.43% for the MI paradigm, while at most a reduction of 17.31% can be achieved for the MR/WG paradigm.
Data collected using the MI paradigm show better generalization across subjects.
通常，脑机接口（BCI）在使用前需要进行校准，以确保其高效性能。因此，每个 BCI 用户都必须参加一定数量的校准会话，才能使用该系统。然而，对于残疾患者来说，这样的校准要求可能很难满足。在本文中，我们介绍了一种概率迁移学习方法，以降低我们使用运动想象（MI）和闪烁心理旋转（MR）/单词生成（WG）范式设计的 EEG-fTCD 混合 BCI 的校准要求。该方法从以前的 BCI 用户中识别出与当前 BCI 用户的小训练数据集最相似的顶级数据集，并使用这些数据集来扩充当前 BCI 用户的训练数据。为了实现这一目标，使用支持向量机将每个试验的 EEG 和 fTCD 特征向量投影到标量分数中。使用每个类的分数分别学习 EEG 和 fTCD 类条件分布。使用当前 BCI 用户的训练试验和以前用户的试验获得的类条件分布之间的 Bhattacharyya 距离来识别相似性。
实验结果表明，与没有迁移学习相比，使用所提出的迁移学习方法获得的性能在 MI 和闪烁 MR/WG 范式下都有所提高。特别是，发现 MI 范式的校准要求可以至少减少 60.43%，而对于 MR/WG 范式，最多可以减少 17.31%。
使用 MI 范式收集的数据在跨受试者方面具有更好的泛化能力。
