Few-Shot Optimization for Sensor Data Using Large Language Models: A Case Study on Fatigue Detection

In this paper, we propose a novel few-shot optimization with Hybrid Euclidean Distance with Large Language Models (HED-LM) to improve example selection for sensor-based classification tasks. While few-shot prompting enables efficient inference with limited labeled data, its performance largely depen...

Full description

Saved in:
Bibliographic Details
Published inSensors (Basel, Switzerland) Vol. 25; no. 11; p. 3324
Main Authors Ronando, Elsen, Inoue, Sozo
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.06.2025
MDPI
Subjects
accelerometer
Accelerometers
Analysis
Case studies
example selection
Fatigue
fatigue detection
few-shot prompting
Graph representations
Language
Large language models
large language models (LLMs)
Machine learning
Methods
Optimization
Physiological aspects
Rankings
Semantics
sensor data
Sensors
United States
California
Online AccessGet full text

Cover

More Information
Summary:In this paper, we propose a novel few-shot optimization with Hybrid Euclidean Distance with Large Language Models (HED-LM) to improve example selection for sensor-based classification tasks. While few-shot prompting enables efficient inference with limited labeled data, its performance largely depends on the quality of selected examples. HED-LM addresses this challenge through a hybrid selection pipeline that filters candidate examples based on Euclidean distance and re-ranks them using contextual relevance scored by large language models (LLMs). To validate its effectiveness, we apply HED-LM to a fatigue detection task using accelerometer data characterized by overlapping patterns and high inter-subject variability. Unlike simpler tasks such as activity recognition, fatigue detection demands more nuanced example selection due to subtle differences in physiological signals. Our experiments show that HED-LM achieves a mean macro F1-score of 69.13 ± 10.71%, outperforming both random selection (59.30 ± 10.13%) and distance-only filtering (67.61 ± 11.39%). These represent relative improvements of 16.6% and 2.3%, respectively. The results confirm that combining numerical similarity with contextual relevance improves the robustness of few-shot prompting. Overall, HED-LM offers a practical solution to improve performance in real-world sensor-based learning tasks and shows potential for broader applications in healthcare monitoring, human activity recognition, and industrial safety scenarios.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
These authors contributed equally to this work.
ISSN:1424-8220
1424-8220
DOI:10.3390/s25113324