Unsupervised Domain Adaptation by Causal Learning for Biometric Signal based HCI

Biometric signal based human-computer interface (HCI) has attracted increasing attention due to its wide application in healthcare, entertainment, neurocomputing, and so on. In recent years, deep learning approaches have made great progress on biometric processing. However, the state-of-the-art (SOTA) still suffer from model degradation across subjects or sessions. this work, we propose a novel unsupervised domain adaptation approach for HCI via causal representation learning. Specifically, three kinds of interventions signals (i.e., subjects, sessions, trials) can be selected generalize models intervention. proposed approach, generative is trained producing intervened features that are subsequently used transferable relations with modes. Experiments EEG-based emotion recognition task sEMG-based gesture conducted confirm superiority our approach. An improvement +0.21% inter-subject achieved using Besides, inter-session recognition, achieves improvements +1.47%, +3.36%, +1.71% +1.01% sEMG datasets including CSL-HDEMG, CapgMyo DB-b, 3DC Ninapro DB6, respectively. The also works inter-trial an average +0.66% databases achieved. These experimental results show compared SOTA methods HCIs signal.