Vasko Jordan L, Aume Laura, Tamrakar Sanjay, Colachis Samuel C Iv, Dunlap Collin F, Rich Adam, Meyers Eric C, Gabrieli David, Friedenberg David A
Battelle Memorial Institute, Columbus, OH, United States.
Department of Biomedical Engineering, The Ohio State University, Columbus, OH, United States.
Front Neurosci. 2022 Apr 28;16:858377. doi: 10.3389/fnins.2022.858377. eCollection 2022.
For brain-computer interfaces (BCIs) to be viable for long-term daily usage, they must be able to quickly identify and adapt to signal disruptions. Furthermore, the detection and mitigation steps need to occur automatically and without the need for user intervention while also being computationally tractable for the low-power hardware that will be used in a deployed BCI system. Here, we focus on disruptions that are likely to occur during chronic use that cause some recording channels to fail but leave the remaining channels unaffected. In these cases, the algorithm that translates recorded neural activity into actions, the neural decoder, should seamlessly identify and adjust to the altered neural signals with minimal inconvenience to the user. First, we introduce an adapted statistical process control (SPC) method that automatically identifies disrupted channels so that both decoding algorithms can be adjusted, and technicians can be alerted. Next, after identifying corrupted channels, we demonstrate the automated and rapid removal of channels from a neural network decoder using a masking approach that does not change the decoding architecture, making it amenable for transfer learning. Finally, using transfer and unsupervised learning techniques, we update the model weights to adjust for the corrupted channels without requiring the user to collect additional calibration data. We demonstrate with both real and simulated neural data that our approach can maintain high-performance while simultaneously minimizing computation time and data storage requirements. This framework is invisible to the user but can dramatically increase BCI robustness and usability.
为了使脑机接口（BCI）能够长期适用于日常使用，它们必须能够快速识别并适应信号中断。此外，检测和缓解步骤需要自动进行，无需用户干预，同时对于将在已部署的BCI系统中使用的低功耗硬件而言，计算上也要易于处理。在此，我们关注慢性使用期间可能发生的中断情况，这些中断会导致一些记录通道失效，但其余通道不受影响。在这些情况下，将记录的神经活动转化为动作的算法，即神经解码器，应该能够无缝识别并调整改变后的神经信号，同时给用户带来最小的不便。首先，我们引入一种经过改进的统计过程控制（SPC）方法，该方法能自动识别中断通道，以便调整解码算法并提醒技术人员。接下来，在识别出损坏的通道后，我们展示了如何使用一种不改变解码架构的掩码方法，从神经网络解码器中自动快速移除通道，这使得它适用于迁移学习。最后，我们使用迁移学习和无监督学习技术，更新模型权重以针对损坏的通道进行调整，而无需用户收集额外的校准数据。我们通过真实和模拟神经数据证明，我们的方法能够在保持高性能的同时，显著减少计算时间和数据存储需求。这个框架对用户是不可见的，但可以显著提高BCI的鲁棒性和可用性。
