Adaptation to a brain-computer interface of transfer learning using event-related potentials obtained under different measurement conditions
Adaptation to a brain-computer interface of transfer learning using event-related potentials obtained under different measurement conditions
复制标题
使用不同测量条件下获得的事件相关电位适应迁移学习的脑机接口
DOI：
10.1109/scisisis55246.2022.10001900
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
T.Fukami
中科院分区：
文献类型：
--
作者：
H.Sato;A.Yoshida;B.Ishikawa;T.Fukami
事件相关电位（ERP）被广泛应用于基于脑电图（EEG）的脑机接口（BCI）中。由于ERPs随年龄、个体差异和任务难度而变化，因此识别有用的特征具有挑战性。近年来，可以通过学习获取特征的深度学习已被用于识别这些特征。然而，深度学习需要大量的BCI数据，并且数据收集可能很困难。因此，我们试图验证BCI的适用性，以转移学习的基础上，从临床检查中获得的大量数据。ERP的组成部分取决于测量条件;因此，它们降低了迁移学习的性能。因此，我们提出使用延迟校正来沿时间轴沿着移位波形来提高性能。我们用从临床听觉oddball范式获得的5600个响应训练EEGNet。在BCI实验中，12名受试者输入显示器上显示的四个字符之一。深度学习的使用导致性能比基于P300振幅的传统方法高出约10%。此外，当使用潜伏期校正时，观察到准确度提高约5%。
Event-related potentials (ERPs) are widely used in electroencephalogram (EEG)-based brain-computer interfaces (BCIs). Because ERPs vary with age, individual differences, and task difficulty, identifying useful features is challenging. In recent years, deep learning, in which features can be acquired via learning, has been used to identify such features. However, a large amount of BCI data is required for deep learning, and data collection can be difficult. Therefore, we attempted to verify the applicability of BCI to transfer learning based on a considerable amount of data obtained from clinical examinations. The components of an ERP vary depending on measurement conditions; therefore, they degrade the performance of transfer learning. Thus, we proposed to improve performance using latency correction to shift waveforms along the time axis. We trained EEGNet with 5600 responses obtained from a clinical auditory oddball paradigm. In the BCI experiment, 12 subjects input one of the four characters presented on a display. The use of deep learning resulted in an approximately 10% higher performance than the conventional method based on the P300 amplitude. Furthermore, an improvement of approximately 5% in accuracy was observed when latency correction was used.