Liang Shuang, Li Linzhe, Zu Wei, Feng Wei, Hang Wenlong
School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, 210093, China.
School of Chemistry and Life Sciences, Nanjing University of Posts and Telecommunications, Nanjing, 210093, China.
BMC Bioinformatics. 2024 Dec 31;25(1):393. doi: 10.1186/s12859-024-06024-w.
The collection of substantial amounts of electroencephalogram (EEG) data is typically time-consuming and labor-intensive, which adversely impacts the development of decoding models with strong generalizability, particularly when the available data is limited. Utilizing sufficient EEG data from other subjects to aid in modeling the target subject presents a potential solution, commonly referred to as domain adaptation. Most current domain adaptation techniques for EEG decoding primarily focus on learning shared feature representations through domain alignment strategies. Since the domain shift cannot be completely removed, target EEG samples located near the edge of clusters are also susceptible to misclassification.
We propose a novel adaptive deep feature representation (ADFR) framework to improve the cross-subject EEG classification performance through learning transferable EEG feature representations. Specifically, we first minimize the distribution discrepancy between the source and target domains by employing maximum mean discrepancy (MMD) regularization, which aids in learning the shared feature representations. We then utilize the instance-based discriminative feature learning (IDFL) regularization to make the learned feature representations more discriminative. Finally, the entropy minimization (EM) regularization is further integrated to adjust the classifier to pass through the low-density region between clusters. The synergistic learning between above regularizations during the training process enhances EEG decoding performance across subjects.
The effectiveness of the ADFR framework was evaluated on two public motor imagery (MI)-based EEG datasets: BCI Competition III dataset 4a and BCI Competition IV dataset 2a. In terms of average accuracy, ADFR achieved improvements of 3.0% and 2.1%, respectively, over the state-of-the-art methods on these datasets.
The promising results highlight the effectiveness of the ADFR algorithm for EEG decoding and show its potential for practical applications.
收集大量脑电图（EEG）数据通常既耗时又费力，这对具有强泛化能力的解码模型的开发产生不利影响，特别是在可用数据有限的情况下。利用来自其他受试者的足够EEG数据来辅助对目标受试者进行建模是一种潜在的解决方案，通常称为域适应。当前大多数用于EEG解码的域适应技术主要集中于通过域对齐策略学习共享特征表示。由于域转移无法完全消除，位于聚类边缘附近的目标EEG样本也容易被误分类。
我们提出了一种新颖的自适应深度特征表示（ADFR）框架，通过学习可转移的EEG特征表示来提高跨受试者EEG分类性能。具体而言，我们首先通过采用最大均值差异（MMD）正则化来最小化源域和目标域之间的分布差异，这有助于学习共享特征表示。然后，我们利用基于实例的判别特征学习（IDFL）正则化使学习到的特征表示更具判别力。最后，进一步集成熵最小化（EM）正则化以调整分类器使其通过聚类之间的低密度区域。训练过程中上述正则化之间的协同学习提高了跨受试者的EEG解码性能。
在两个基于公开运动想象（MI）的EEG数据集上评估了ADFR框架的有效性：BCI竞赛III数据集4a和BCI竞赛IV数据集2a。在平均准确率方面，ADFR在这些数据集上分别比现有最先进方法提高了3.0%和2.1%。
这些有前景的结果突出了ADFR算法用于EEG解码的有效性，并显示了其在实际应用中的潜力。
