Few-Shot Optimization for Sensor Data Using Large Language Models: A Case Study on Fatigue Detection
Sensors · 2025
DOI: 10.3390/s25113324 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Elsen Ronando und 1 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, 2-4 Hibikino, Wakamatsu Ward, Kitakyushu 808-0135, Japan. Hauptthemen laut MEDLINE: Fatigue. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: This research was funded by the JST-Mirai Program, Creation of Care Weather Forecasting 1001 Services in the Nursing and Medical Field, Japan., JST-Mirai Program, Creation of Care Weather Forecasting Services in the Nursing and Medical Field.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, 2-4 Hibikino, Wakamatsu Ward, Kitakyushu 808-0135, Japan.
- Department of Informatics, Universitas 17 Agustus 1945 Surabaya, Semolowaru No. 45, Kota Surabaya 60118, Indonesia.
ORCID-Profile: Elsen Ronando, Sozo Inoue
Förderung
- This research was funded by the JST-Mirai Program, Creation of Care Weather Forecasting 1001 Services in the Nursing and Medical Field, Japan.
- JST-Mirai Program, Creation of Care Weather Forecasting Services in the Nursing and Medical Field
Zitieren
APA
Ronando, E., & Inoue, S. (2025). Few-Shot Optimization for Sensor Data Using Large Language Models: A Case Study on Fatigue Detection. Sensors. https://doi.org/10.3390/s25113324
Vancouver
Ronando E, Inoue S. Few-Shot Optimization for Sensor Data Using Large Language Models: A Case Study on Fatigue Detection. Sensors. 2025. doi:10.3390/s25113324
BibTeX
@article{Ronando2025,
author = {Ronando, Elsen and Inoue, Sozo},
title = {Few-Shot Optimization for Sensor Data Using Large Language Models: A Case Study on Fatigue Detection},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25113324}
}
EUVIMED