Multi-Scale Hybrid Attention Temporal Network for Motionless Activity Using Smartphone Inertial Sensors
Technologies · 30.04.2026 · 14 (5) · 272
DOI: 10.3390/technologies14050272 ↗Kurz gefasst
Fachartikel in der Zeitschrift Technologies, online erschienen am 30.04.2026. Verfasst von Sakorn Mekruksavanich und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Phayao, Thailand Science Research and Innovation, National Science, Research and Innovation Fund.
Abstract (Originalsprache)
Wearable sensor-based human activity recognition (HAR) has gained growing significance in healthcare monitoring and assisted living systems. Although considerable advances have been made in classifying dynamic movements, stationary activities—such as sleeping, driving, and watching TV—remain difficult to distinguish owing to their weak sensor signatures and limited discriminative cues. This paper presents the multi-scale hybrid attention temporal network (MHAT-Net), a deep learning framework whose key architectural novelty lies in the parallel (non-sequential) dual-pathway temporal modeling: a BiGRU branch and a transformer encoder branch operate simultaneously on the same spatially encoded representation, combined via a learnable attention-based fusion module. This design targets the underexplored problem of distinguishing stationary activities from weak inertial sensor signatures. The architecture is built upon three integrated components: (1) a multi-branch CNN with kernel sizes three, five, and seven combined with channel attention for adaptive spatial feature extraction across multiple temporal scales; (2) parallel bidirectional gated recurrent unit (BiGRU) and transformer encoder pathways for jointly capturing short-range sequential patterns and long-range temporal correlations; and (3) an attention-driven fusion module that adaptively weights the outputs of both temporal branches. The model was assessed on a publicly available benchmark comprising three motionless activity categories collected from 25 participants via smartphone sensors. In 5-fold cross-validation, MHAT-Net attained 97.42% (±4.69%) accuracy with accelerometer data and 92.31% (±0.31%) with gyroscope data, substantially exceeding the accuracies of five baseline architectures: CNN, LSTM, BiLSTM, GRU, and BiGRU. Ablation experiments identified multi-scale spatial feature extraction as the most influential module (2.21–2.47% contribution), followed by the hybrid temporal modeling components. Cross-modality analysis confirmed that accelerometer signals yielded richer discriminative content for stationary activities, while MHAT-Net sustained consistent performance across both sensor types. The proposed integration of multi-scale spatial encoding, hybrid temporal modeling, and multi-level attention gives MHAT-Net the ability to reliably detect subtle activity-specific patterns, establishing a new benchmark in wearable sensor-based recognition for comprehensive daily behavior monitoring.
Förderung
- University of Phayao
- Thailand Science Research and Innovation
- National Science, Research and Innovation Fund
- King Mongkut’s University of Technology North Bangkok
Zitieren
APA
Mekruksavanich, S., & Jitpattanakul, A. (2026). Multi-Scale Hybrid Attention Temporal Network for Motionless Activity Using Smartphone Inertial Sensors. Technologies, 14(5), 272. https://doi.org/10.3390/technologies14050272
Vancouver
Mekruksavanich S, Jitpattanakul A. Multi-Scale Hybrid Attention Temporal Network for Motionless Activity Using Smartphone Inertial Sensors. Technologies. 2026;14(5):272. doi:10.3390/technologies14050272
BibTeX
@article{Mekruksavanich2026,
author = {Mekruksavanich, Sakorn and Jitpattanakul, Anuchit},
title = {Multi-Scale Hybrid Attention Temporal Network for Motionless Activity Using Smartphone Inertial Sensors},
journal = {Technologies},
year = {2026},
volume = {14},
number = {5},
pages = {272},
doi = {10.3390/technologies14050272}
}
EUVIMED