EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid Deep Learning Models for Free-Living Imbalanced Human Activity Recognition: Comparative Study

Aditya Heru Prathama, Joy Milliaan, Ghandy

Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) · 06.04.2026 · 10 (2) · 289-297

DOI: 10.29207/resti.v10i2.6936 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), online erschienen am 06.04.2026. Verfasst von Aditya Heru Prathama und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents a comparative evaluation of three hybrid deep learning models for human activity recognition (HAR) in free-living and highly imbalanced conditions: 1DCNN-ResBLSTM-Attention (Model A), Attention-Mechanism-Based Deep Learning Feature Combination (Model B), and Time-Reversal-1DCNN-ResLSTM-Attention (Model C). Each architecture integrates convolutional layers for feature extraction, recurrent networks for temporal modeling, and attention mechanisms to enhance relevant representations. The HARTH v2.0 dataset, comprising 31 subjects and 15 activity classes under strong class imbalance, is used for evaluation. Results show that soft labeling consistently improves performance by better capturing transitional uncertainty in windowed sensor data. Model A achieves the highest accuracy (96.21%) and macro-averaged F1-score (88.17%), followed by Model C with comparable performance at lower computational cost, while Model B underperforms on minority classes due to limitations of spectrogram-based representations. Across all models, persistent confusion is observed among activities with similar motion patterns, such as walking, standing, and shuffling, indicating intrinsic ambiguity in sensor signals. This study provides a controlled and standardized comparison of hybrid architectures under realistic conditions, revealing both performance trade-offs and shared limitations. The findings highlight the importance of modeling uncertainty and temporal context for improving robustness, particularly transitional and underrepresented activities.

Zitieren

APA

Prathama, A. H., Milliaan, J., & Ghandy (2026). Hybrid Deep Learning Models for Free-Living Imbalanced Human Activity Recognition: Comparative Study. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 10(2), 289-297. https://doi.org/10.29207/resti.v10i2.6936

Vancouver

Prathama AH, Milliaan J, Ghandy. Hybrid Deep Learning Models for Free-Living Imbalanced Human Activity Recognition: Comparative Study. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi). 2026;10(2):289-297. doi:10.29207/resti.v10i2.6936

BibTeX
@article{Prathama2026,
  author = {Prathama, Aditya Heru and Milliaan, Joy and Ghandy},
  title = {Hybrid Deep Learning Models for Free-Living Imbalanced Human Activity Recognition: Comparative Study},
  journal = {Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)},
  year = {2026},
  volume = {10},
  number = {2},
  pages = {289--297},
  doi = {10.29207/resti.v10i2.6936}
}
Kostenlos starten →