Han Mo, Ozdenizci Özan, Wang Ye, Koike-Akino Toshiaki, Erdoğmuş Deniz
Cognitive Systems Laboratory, Department of Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA.
Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA 02139, USA.
IEEE Signal Process Lett. 2020;27:1565-1569. doi: 10.1109/lsp.2020.3020215. Epub 2020 Aug 31.
Recent developments in biosignal processing have enabled users to exploit their physiological status for manipulating devices in a reliable and safe manner. One major challenge of physiological sensing lies in the variability of biosignals across different users and tasks. To address this issue, we propose an adversarial feature extractor for transfer learning to exploit disentangled universal representations. We consider the trade-off between task-relevant features and user-discriminative information by introducing additional adversary and nuisance networks in order to manipulate the latent representations such that the learned feature extractor is applicable to unknown users and various tasks. Results on cross-subject transfer evaluations exhibit the benefits of the proposed framework, with up to 8.8% improvement in average accuracy of classification, and demonstrate adaptability to a broader range of subjects.
生物信号处理领域的最新进展使用户能够以可靠且安全的方式利用自身生理状态来操控设备。生理传感面临的一个主要挑战在于生物信号在不同用户和任务之间存在变异性。为解决这一问题，我们提出一种用于迁移学习的对抗特征提取器，以利用解缠的通用表示。我们通过引入额外的对抗网络和干扰网络来考虑任务相关特征与用户判别信息之间的权衡，从而操控潜在表示，使学习到的特征提取器适用于未知用户和各种任务。跨主体迁移评估的结果展示了所提出框架的优势，分类平均准确率提高了8.8%，并证明了其对更广泛主体的适应性。
