Han Mo, Ozdenizci Ozan, Wang Ye, Koike-Akino Toshiaki, Erdogmus Deniz
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:422-425. doi: 10.1109/EMBC44109.2020.9175233.
Recent developments in wearable sensors demonstrate promising results for monitoring physiological status in effective and comfortable ways. One major challenge of physiological status assessment is the problem of transfer learning caused by the domain inconsistency of biosignals across users or different recording sessions from the same user. We propose an adversarial inference approach for transfer learning to extract disentangled nuisance-robust representations from physiological biosignal data in stress status level assessment. We exploit the trade-off between task-related features and person-discriminative information by using both an adversary network and a nuisance network to jointly manipulate and disentangle the learned latent representations by the encoder, which are then input to a discriminative classifier. Results on cross-subjects transfer evaluations demonstrate the benefits of the proposed adversarial framework, and thus show its capabilities to adapt to a broader range of subjects. Finally we highlight that our proposed adversarial transfer learning approach is also applicable to other deep feature learning frameworks.
可穿戴传感器的最新进展显示出以有效且舒适的方式监测生理状态的良好前景。生理状态评估的一个主要挑战是生物信号在不同用户之间或同一用户的不同记录时段存在领域不一致性所导致的迁移学习问题。我们提出一种用于迁移学习的对抗推理方法，以便在压力状态水平评估中从生理生物信号数据中提取解缠的抗干扰表示。我们通过使用对抗网络和干扰网络来利用任务相关特征和个体判别信息之间的权衡，从而联合操纵和解缠编码器学习到的潜在表示，然后将其输入到判别分类器中。跨主体迁移评估的结果证明了所提出的对抗框架的优势，从而展示了其适应更广泛主体的能力。最后，我们强调我们提出的对抗迁移学习方法也适用于其他深度特征学习框架。
