Skip to main navigation Skip to search Skip to main content

LOL: Learning with One Lightweight Sensor-Aware Predictive Model For Sleep Quality

  • Ja Hyeob Koo
  • , Yong Ho Song
  • , Jae Hyeon Shim
  • , So Yeong Lee
  • , Young Hoon Lee
  • Seoul National University of Science and Technology (SNUST)
  • Sungkyunkwan University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This study proposes an approach to predict human sleep quality using only a machine learning model, CatBoost. Based on sensor data collected from 10 participants, the model aims to predict six target indicators related to sleep quality. To this end, four representative preprocessing techniques - Hourly Aggregation, Linear Interpolation, Explicit Zero Imputation, and Derived Feature Engineering - were tailored to the characteristics of each of the 12 sensor datasets and applied accordingly. CatBoost was chosen for its low variance and strong generalization capability, which enable robust performance without relying on complex architectures, as required in many deep learning models. Experimental results demonstrated that the proposed model achieved a macro F1-score of 0.6685, highlighting its strong predictive performance with only a CatBoost-based approach.

Original languageEnglish
Title of host publication2025 16th International Conference on Information and Communication Technology Convergence, ICTC 2025
PublisherIEEE Computer Society
Pages1697-1702
Number of pages6
ISBN (Electronic)9798331556785
DOIs
StatePublished - 2025
Event16th International Conference on Information and Communication Technology Convergence, ICTC 2025 - , Korea, Republic of
Duration: 14 Oct 202517 Oct 2025

Publication series

NameInternational Conference on ICT Convergence
ISSN (Print)2162-1233
ISSN (Electronic)2162-1241

Conference

Conference16th International Conference on Information and Communication Technology Convergence, ICTC 2025
Country/TerritoryKorea, Republic of
Period14/10/2517/10/25

Keywords

  • Catboost
  • Data preprocessing
  • Lifelog data
  • Lightweight model
  • Machine Learning

Fingerprint

Dive into the research topics of 'LOL: Learning with One Lightweight Sensor-Aware Predictive Model For Sleep Quality'. Together they form a unique fingerprint.

Cite this