SitLLM: Large Language Models for Sitting Posture Health Understanding via Pressure Sensor Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Jian, Zhao, Fufangchen, Zhang, Yiyang, Yan, Danfeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911157719138304
author Gao, Jian
Zhao, Fufangchen
Zhang, Yiyang
Yan, Danfeng
author_facet Gao, Jian
Zhao, Fufangchen
Zhang, Yiyang
Yan, Danfeng
contents Poor sitting posture is a critical yet often overlooked factor contributing to long-term musculoskeletal disorders and physiological dysfunctions. Existing sitting posture monitoring systems, although leveraging visual, IMU, or pressure-based modalities, often suffer from coarse-grained recognition and lack the semantic expressiveness necessary for personalized feedback. In this paper, we propose \textbf{SitLLM}, a lightweight multimodal framework that integrates flexible pressure sensing with large language models (LLMs) to enable fine-grained posture understanding and personalized health-oriented response generation. SitLLM comprises three key components: (1) a \textit{Gaussian-Robust Sensor Embedding Module} that partitions pressure maps into spatial patches and injects local noise perturbations for robust feature extraction; (2) a \textit{Prompt-Driven Cross-Modal Alignment Module} that reprograms sensor embeddings into the LLM's semantic space via multi-head cross-attention using the pre-trained vocabulary embeddings; and (3) a \textit{Multi-Context Prompt Module} that fuses feature-level, structure-level, statistical-level, and semantic-level contextual information to guide instruction comprehension.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12994
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SitLLM: Large Language Models for Sitting Posture Health Understanding via Pressure Sensor Data
Gao, Jian
Zhao, Fufangchen
Zhang, Yiyang
Yan, Danfeng
Computation and Language
Poor sitting posture is a critical yet often overlooked factor contributing to long-term musculoskeletal disorders and physiological dysfunctions. Existing sitting posture monitoring systems, although leveraging visual, IMU, or pressure-based modalities, often suffer from coarse-grained recognition and lack the semantic expressiveness necessary for personalized feedback. In this paper, we propose \textbf{SitLLM}, a lightweight multimodal framework that integrates flexible pressure sensing with large language models (LLMs) to enable fine-grained posture understanding and personalized health-oriented response generation. SitLLM comprises three key components: (1) a \textit{Gaussian-Robust Sensor Embedding Module} that partitions pressure maps into spatial patches and injects local noise perturbations for robust feature extraction; (2) a \textit{Prompt-Driven Cross-Modal Alignment Module} that reprograms sensor embeddings into the LLM's semantic space via multi-head cross-attention using the pre-trained vocabulary embeddings; and (3) a \textit{Multi-Context Prompt Module} that fuses feature-level, structure-level, statistical-level, and semantic-level contextual information to guide instruction comprehension.
title SitLLM: Large Language Models for Sitting Posture Health Understanding via Pressure Sensor Data
topic Computation and Language
url https://arxiv.org/abs/2509.12994