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 article 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.
Highlights
In recent years, the drastic increase in ageing population has increased the burden on the already over-stretched health and social care systems
Rosales and Ye [36] propose to a 2-staged domain adaptation where semantics similarity is employed to perform linear transformation of sensor features from one domain to another domain and a variational autoencoder (VAE) is used for fine alignment between transferred features and source features
Effectiveness – How accurately shift-GAN can recognise activities in the target dataset, compared with stateof-the-art domain adaptation techniques? We will perform ablation analysis to assess the contribution of Kernel Mean Matching (KMM), and as well as stability and convergence analysis on bidirectional generative adversarial networks (Bi-GAN) working on sensor data
Summary
The drastic increase in ageing population has increased the burden on the already over-stretched health and social care systems. Domain adaptation techniques have been increasingly applied to HAR applications; for example on accelerometer data, much effort has been devoted to transferring activity knowledge learned on one sensor position (e.g., arm) to another position (e.g., leg) [4], [6], [20]. These techniques often work well as they assume that the source and target. We propose shift-GAN as a general unsupervised domain adaptation technique to enable activity transfer across heterogeneous datasets, including accelerometer and binary sensors. The results have demonstrated the superior performance of shift-GAN over the state-of-the-art techniques in these experiments
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
