Large Language Model-Guided Semantic Alignment for Human Activity Recognition

TL;DR

LanHAR utilizes Large Language Models to generate semantic interpretations of sensor data and labels, effectively addressing dataset heterogeneity and improving human activity recognition across datasets and new activities.

Contribution

This paper introduces LanHAR, a novel LLM-guided semantic alignment approach for HAR that enhances cross-dataset transferability and new activity recognition.

Findings

Outperforms state-of-the-art methods on five datasets

Effectively bridges cross-dataset heterogeneity

Enables recognition of new activities with high accuracy

Abstract

Human Activity Recognition (HAR) using Inertial Measurement Unit (IMU) sensors is critical for applications in healthcare, safety, and industrial production. However, variations in activity patterns, device types, and sensor placements create distribution gaps across datasets, reducing the performance of HAR models. To address this, we propose LanHAR, a novel system that leverages Large Language Models (LLMs) to generate semantic interpretations of sensor readings and activity labels for cross-dataset HAR. This approach not only mitigates cross-dataset heterogeneity but also enhances the recognition of new activities. LanHAR employs an iterative re-generation method to produce high-quality semantic interpretations with LLMs and a two-stage training framework that bridges the semantic interpretations of sensor readings and activity labels. This ultimately leads to a lightweight sensor encoder suitable for mobile deployment, enabling any sensor reading to be mapped into the semantic interpretation space. Experiments on five public datasets demonstrate that our approach significantly outperforms state-of-the-art methods in both cross-dataset HAR and new activity recognition. The source code is publicly available at https://github.com/DASHLab/LanHAR.