arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.07918cs.HCcs.AI
收藏

使用跳跃连接的脑信号的主体无关分类

Subject-Independent Classification of Brain Signals using Skip Connections

Korea University(高丽大学)

Soowon Kim, Ji-Won Lee, Young-Eun Lee, Seo-Hyun Lee

摘要:

在人类语言的大脑信号解码研究的活跃研究领域中,可以发现新形式的人与人之间交流的未开发潜力。脑机接口系统可以使用脑电图信号来实现,因为它造成更小的临床风险并且可以使用便携式仪器来获取。脑机接口系统最有趣的任务之一是从原始脑电图信号中解码单词。在脑机接口可以被新用户使用之前,当前基于脑电图的脑机接口研究通常需要对象特定的适应阶段。相比之下,受试者独立的情况是非常需要的,因为它允许将经过良好训练的模型应用于新用户,而很少或没有预校准。重点是创建一个有效的解码器,可以采用自适应在独立于主体的情况下,根据这一关键特性。我们的建议是显式地在卷积层之间应用跳过连接,以实现层之间的互信息流。为此,我们在层之间添加跳过连接,允许互信息在整个层中流动。然后,编码器的输出通过全连接层,最终表示13个类的概率。在这项研究中,公开的讲话被用来记录脑电图数据的16名参与者。实验结果表明,当存在跳跃连接时,分类性能得到显著提高。

英文摘要:

Untapped potential for new forms of human-to-human communication can be found in the active research field of studies on the decoding of brain signals of human speech. A brain-computer interface system can be implemented using electroencephalogram signals because it poses more less clinical risk and can be acquired using portable instruments. One of the most interesting tasks for the brain-computer interface system is decoding words from the raw electroencephalogram signals. Before a brain-computer interface may be used by a new user, current electroencephalogram-based brain-computer interface research typically necessitates a subject-specific adaption stage. In contrast, the subject-independent situation is one that is highly desired since it allows a well-trained model to be applied to new users with little or no precalibration. The emphasis is on creating an efficient decoder that may be employed adaptively in subject-independent circumstances in light of this crucial characteristic. Our proposal is to explicitly apply skip connections between convolutional layers to enable the flow of mutual information between layers. To do this, we add skip connections between layers, allowing the mutual information to flow throughout the layers. The output of the encoder is then passed through the fully-connected layer to finally represent the probabilities of the 13 classes. In this study, overt speech was used to record the electroencephalogram data of 16 participants. The results show that when the skip connection is present, the classification performance improves notably.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑