Deep Adversarial Learning with Activity-Based User Discrimination Task for Human Activity Recognition

TL;DR

This paper introduces a novel adversarial deep learning framework for human activity recognition that effectively handles inter-person variability, outperforming previous methods on multiple datasets.

Contribution

The paper proposes a new adversarial activity-based discrimination task that improves HAR accuracy by addressing inter-person variability in a deep learning framework.

Findings

Outperforms previous methods on three HAR datasets

Discrimination task yields better classification results

Effective in handling inter-person variability

Abstract

We present a new adversarial deep learning framework for the problem of human activity recognition (HAR) using inertial sensors worn by people. Our framework incorporates a novel adversarial activity-based discrimination task that addresses inter-person variability-i.e., the fact that different people perform the same activity in different ways. Overall, our proposed framework outperforms previous approaches on three HAR datasets using a leave-one-(person)-out cross-validation (LOOCV) benchmark. Additional results demonstrate that our discrimination task yields better classification results compared to previous tasks within the same adversarial framework.