Sleep Quality Prediction from Lifelog Data Using LLM-based Imputation
  • Hyun, JongYeol
  • Byun, YuChul
  • Bak, Dongkeun
Citations

SCOPUS

0

초록

This study proposes a methodology to enhance the classification performance of traditional machine learning models for lifelog data analysis by leveraging Large Language Models (LLMs) for missing value imputation. The reasoning capabilities of LLMs are used throughout the imputation process, and the resulting features are fed into an ensemble-based predictor. In our evaluation, the proposed approach improved classification accuracy on lifelog data compared with conventional methods.

키워드

LifelogLLMMachine Learning EnsembleMissing Value ImputationSleepSleep QualityStress Level
제목
Sleep Quality Prediction from Lifelog Data Using LLM-based Imputation
저자
Hyun, JongYeolByun, YuChulBak, Dongkeun
DOI
10.1109/ICTC66702.2025.11388019
발행일
2025
유형
Conference Paper
저널명
International Conference on ICT Convergence
페이지
1721 ~ 1726