Unsupervised domain adaptation in activity recognition: a GAN-based approach

Andrea Rosales Sanabria, Franco Zambonelli, Juan Ye*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

4 Downloads (Pure)

Abstract

Sensor-based human activity recognition (HAR) is having a significant impact in a wide range of applications in smart city, smart home, and personal healthcare. Such wide deployment of HAR systems often faces the annotation-scarcity challenge; that is, most of the HAR techniques, especially the deep learning techniques, require a large number of training data while annotating sensor data is very time- and effort-consuming. Unsupervised domain adaptation has been successfully applied to tackle this challenge, where the activity knowledge from a well-annotated domain can be transferred to a new, unlabelled domain. However, these existing techniques do not perform well on highly heterogeneous domains. This paper proposes shift-GAN that integrate bidirectional generative adversarial networks (Bi-GAN) and kernel mean matching (KMM) in an innovative way to learn intrinsic, robust feature transfer between two heterogeneous domains. Bi-GAN consists of two GANs that are bound by a cyclic constraint, which enables more effective feature transfer than a classic, single GAN model. KMM is a powerful non-parametric technique to correct covariate shift, which further improves feature space alignment. Through a series of comprehensive, empirical evaluations, shift-GAN has not only achieved its superior performance over 10 state-of-the-art domain adaptation techniques but also demonstrated its effectiveness in learning activity-independent, intrinsic feature mappings between two domains, robustness to sensor noise, and less sensitivity to training data.
Original languageEnglish
Pages (from-to)19421-19438
Number of pages18
JournalIEEE Access
Volume9
DOIs
Publication statusPublished - 22 Jan 2021

Keywords

  • Human activity recognition
  • Domain adaptation
  • Ensemble learning
  • Generative adversarial networks
  • Covariate shift
  • Kernal mean matching

Fingerprint

Dive into the research topics of 'Unsupervised domain adaptation in activity recognition: a GAN-based approach'. Together they form a unique fingerprint.

Cite this