Adversarial Domain Adaptation for Cross-user Activity Recognition Using Diffusion-based Noise-centred Learning

TL;DR

A novel framework, termed Diffusion-based Noise-centered Adversarial Learning Domain Adaptation (Diff-Noise-Adv-DA), designed to address challenges in HAR models by leveraging generative diffusion modeling and adversarial learning techniques.

Abstract

Human Activity Recognition (HAR) plays a crucial role in various applications such as human-computer interaction and healthcare monitoring. However, challenges persist in HAR models due to the data distribution differences between training and real-world data distributions, particularly evident in cross-user scenarios. This paper introduces a novel framework, termed Diffusion-based Noise-centered Adversarial Learning Domain Adaptation (Diff-Noise-Adv-DA), designed to address these challenges by leveraging generative diffusion modeling and adversarial learning techniques. Traditional HAR models often struggle with the diversity of user behaviors and sensor data distributions. Diff-Noise-Adv-DA innovatively integrates the inherent noise within diffusion models, harnessing its latent information to enhance domain adaptation. Specifically, the framework transforms noise into a critical carrier of activity and domain class information, facilitating robust classification across different user domains. Experimental evaluations demonstrate the effectiveness of Diff-Noise-Adv-DA in improving HAR model performance across different users, surpassing traditional domain adaptation methods. The framework not only mitigates distribution mismatches but also enhances data quality through noise-based denoising techniques.

Figures (10)

• Figure 1: The design of DNA-DA.
• Figure 2: The overview of the DNA-DA method.
• Figure 3: The network architecture of the noise generator.
• Figure 4: The network architecture of the noise predictor.
• Figure 5: Cross-user data distribution distance of activities in OPPT dataset.