Guardado en:
Detalles Bibliográficos
Autores principales: Li, Zechen, Deldari, Shohreh, Chen, Linyao, Xue, Hao, Salim, Flora D.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.10624
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918129309843456
author Li, Zechen
Deldari, Shohreh
Chen, Linyao
Xue, Hao
Salim, Flora D.
author_facet Li, Zechen
Deldari, Shohreh
Chen, Linyao
Xue, Hao
Salim, Flora D.
contents We introduce SensorLLM, a two-stage framework that enables Large Language Models (LLMs) to perform human activity recognition (HAR) from sensor time-series data. Despite their strong reasoning and generalization capabilities, LLMs remain underutilized for motion sensor data due to the lack of semantic context in time-series, computational constraints, and challenges in processing numerical inputs. SensorLLM addresses these limitations through a Sensor-Language Alignment stage, where the model aligns sensor inputs with trend descriptions. Special tokens are introduced to mark channel boundaries. This alignment enables LLMs to capture numerical variations, channel-specific features, and data of varying durations, without requiring human annotations. In the subsequent Task-Aware Tuning stage, we refine the model for HAR classification, achieving performance that matches or surpasses state-of-the-art methods. Our results demonstrate that SensorLLM evolves into an effective sensor learner, reasoner, and classifier through human-intuitive Sensor-Language Alignment, generalizing across diverse HAR datasets. We believe this work establishes a foundation for future research on time-series and text alignment, paving the way for foundation models in sensor data analysis. Our codes are available at https://github.com/zechenli03/SensorLLM.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10624
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition
Li, Zechen
Deldari, Shohreh
Chen, Linyao
Xue, Hao
Salim, Flora D.
Computation and Language
We introduce SensorLLM, a two-stage framework that enables Large Language Models (LLMs) to perform human activity recognition (HAR) from sensor time-series data. Despite their strong reasoning and generalization capabilities, LLMs remain underutilized for motion sensor data due to the lack of semantic context in time-series, computational constraints, and challenges in processing numerical inputs. SensorLLM addresses these limitations through a Sensor-Language Alignment stage, where the model aligns sensor inputs with trend descriptions. Special tokens are introduced to mark channel boundaries. This alignment enables LLMs to capture numerical variations, channel-specific features, and data of varying durations, without requiring human annotations. In the subsequent Task-Aware Tuning stage, we refine the model for HAR classification, achieving performance that matches or surpasses state-of-the-art methods. Our results demonstrate that SensorLLM evolves into an effective sensor learner, reasoner, and classifier through human-intuitive Sensor-Language Alignment, generalizing across diverse HAR datasets. We believe this work establishes a foundation for future research on time-series and text alignment, paving the way for foundation models in sensor data analysis. Our codes are available at https://github.com/zechenli03/SensorLLM.
title SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition
topic Computation and Language
url https://arxiv.org/abs/2410.10624