Guided-GAN: Adversarial Representation Learning for Activity Recognition with Wearables
This work addresses the tedious and costly data annotation problem in ubiquitous computing for HAR, offering an incremental improvement over existing unsupervised approaches.
The paper tackles the problem of reducing annotation costs in human activity recognition (HAR) with wearable sensors by proposing Guided-GAN, an unsupervised generative adversarial network framework for learning feature representations. The results show that Guided-GAN outperforms existing unsupervised methods and approaches the performance of fully supervised representations on three classification benchmarks.
Human activity recognition (HAR) is an important research field in ubiquitous computing where the acquisition of large-scale labeled sensor data is tedious, labor-intensive and time consuming. State-of-the-art unsupervised remedies investigated to alleviate the burdens of data annotations in HAR mainly explore training autoencoder frameworks. In this paper: we explore generative adversarial network (GAN) paradigms to learn unsupervised feature representations from wearable sensor data; and design a new GAN framework-Geometrically-Guided GAN or Guided-GAN-for the task. To demonstrate the effectiveness of our formulation, we evaluate the features learned by Guided-GAN in an unsupervised manner on three downstream classification benchmarks. Our results demonstrate Guided-GAN to outperform existing unsupervised approaches whilst closely approaching the performance with fully supervised learned representations. The proposed approach paves the way to bridge the gap between unsupervised and supervised human activity recognition whilst helping to reduce the cost of human data annotation tasks.