Skip to main navigation Skip to search Skip to main content

Context-Aware Dual-Stream Framework for Sleep Quality Prediction Using Multi-Modal Lifelog Data

  • Hoseong Kim
  • , Sujin Kwon
  • , Seungsu Noh
  • , Sein Cho
  • , Beomseok Oh
  • Seoul National University of Science and Technology (SNUST)
  • Sungshin Women's University
  • Hanyang University

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

Abstract

We tackle daily sleep quality prediction from multimodal smartphone and wearable lifelogs without relying on deep neural networks. We introduce a context-aware dual-stream framework that separates survey and sensor targets: surveys are modeled by a soft-voting ensemble of XGBoost, LightGBM, and CatBoost, while sensors are modeled by a single CatBoost, and the outputs are fused. The pipeline restores heart-rate gaps via IpDFT-based sinusoidal interpolation, derives GPS place semantics with DBSCAN, and integrates external weather/holiday context into day-level features. We evaluated our framework on a minute-level dataset collected from 10 participants, comprising 700 total days, using subject-independent 10-fold cross-validation. The framework achieves a macro-F1 of 0.6311, demonstrating that carefully engineered context and modality-aligned learning can outperform deep baselines while remaining compact and suitable for on-device inference.

Original languageEnglish
Title of host publication2025 16th International Conference on Information and Communication Technology Convergence, ICTC 2025
PublisherIEEE Computer Society
Pages1739-1743
Number of pages5
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

  • Context-Aware Computing
  • Feature Engineering
  • Machine Learning
  • Multimodal Time Series
  • On-Device Inference
  • Sleep Quality Prediction

Fingerprint

Dive into the research topics of 'Context-Aware Dual-Stream Framework for Sleep Quality Prediction Using Multi-Modal Lifelog Data'. Together they form a unique fingerprint.

Cite this