Skip to content
/ LLaSA Public

Large Language and Sensor Assistant: Multimodal LLM for sensor and human activity interpretation

Notifications You must be signed in to change notification settings

BASHLab/LLaSA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Hippocratic License HL3-CL-ECO-EXTR-FFD-LAW-MEDIA-MIL-MY-SOC-SV-TAL-USTA

LLaSA: A Multimodal Large Language Model for Human Activity Analysis Using Sensor Data

LLaSA Demo

This repository hosts the code and datasets for LLaSA (Large Language and Sensor Assistant), a multimodal large language model that integrates inertial measurement units (IMUs) with natural language understanding. Built on LIMU-BERT and Llama, LLaSA is designed to interpret and respond to complex queries about human activities and motion by combining sensor data with contextual reasoning.

Key Features

1. Datasets

  • SensorCaps: A dataset of 35,960 IMU-derived activity narrations enriched with handcrafted features.
  • OpenSQA: An instruction-following dataset containing 179,727 question-answer pairs, tailored for sensor- and activity-aware contexts.

2. Model Architecture

  • LLaSA integrates IMU data with natural language processing capabilities, leveraging multimodal inputs for nuanced activity analysis.
  • Includes advanced hyperparameter tuning to optimize performance for contextual, sensor-based question-answering tasks.

3. Evaluation

  • Comprehensive evaluations, including human-led assessments, show that LLaSA outperforms GPT-3.5-Turbo and Vicuna-1.5-13b-16K in sensor-aware and context-sensitive question answering.
  • We employed a hyperparameter tuning method with GPT-assisted evaluation of question-answer pairs.

Applications

LLaSA is designed to support impactful research and practical applications in:

  • Personal Health: Monitoring activity patterns, providing actionable insights, and assisting in wellness routines.
  • Human-Computer Interaction: Context-aware assistance and enhanced user experience through activity interpretation.

Repository Contents

  • Code: Scripts for training, fine-tuning, and evaluating the LLaSA model.
  • Datasets: SensorCaps and OpenSQA Google Drive (Email address: llasa.data@gmail.com)
  • Documentation: Instructions for replicating experiments and integrating LLaSA into your projects.

About

Large Language and Sensor Assistant: Multimodal LLM for sensor and human activity interpretation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published