Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yan, Hua, Tan, Heng, Ding, Yi, Zhou, Pengfei, Namboodiri, Vinod, Yang, Yu
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2410.00003
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912658038456320
author Yan, Hua
Tan, Heng
Ding, Yi
Zhou, Pengfei
Namboodiri, Vinod
Yang, Yu
author_facet Yan, Hua
Tan, Heng
Ding, Yi
Zhou, Pengfei
Namboodiri, Vinod
Yang, Yu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_00003
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Language Model-Guided Semantic Alignment for Human Activity Recognition
Yan, Hua
Tan, Heng
Ding, Yi
Zhou, Pengfei
Namboodiri, Vinod
Yang, Yu
Computer Vision and Pattern Recognition
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.
title Large Language Model-Guided Semantic Alignment for Human Activity Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.00003