Deep Generative Domain Adaptation with Temporal Relation Knowledge for Cross-User Activity Recognition

arXiv:2403.14682v1 Announce Type: cross
Abstract: In human activity recognition (HAR), the assumption that training and testing data are independent and identically distributed (i.i.d.) often fails, particularly in cross-user scenarios where data distributions vary significantly. This discrepancy highlights the limitations of conventional domain adaptation methods in HAR, which typically overlook the inherent temporal relations in time-series data. To bridge this gap, our study introduces a Conditional Variational Autoencoder with Universal Sequence Mapping (CVAE-USM) approach, which addresses the unique challenges of time-series …

abstract arxiv cs.ai cs.cv cs.hc cs.lg data distributed domain domain adaptation generative highlights human independent knowledge limitations recognition temporal testing training type