Real-life Human Activity Recognition Based on Accelerometer Data from Smartphone Sensors Using CNN-BiGRU Model
Issued Date
2026-01-01
Resource Type
Scopus ID
2-s2.0-105037004945
Journal Title
11th International Conference on Digital Arts Media and Technology and 9th Ecti Northern Section Conference on Electrical Electronics Computer and Telecommunications Engineering Ecti Damt and Ncon 2026
Start Page
688
End Page
693
Rights Holder(s)
SCOPUS
Bibliographic Citation
11th International Conference on Digital Arts Media and Technology and 9th Ecti Northern Section Conference on Electrical Electronics Computer and Telecommunications Engineering Ecti Damt and Ncon 2026 (2026) , 688-693
Suggested Citation
Mekruksavanich S., Fan Y., Hnoohom N., Jitpattanakul A. Real-life Human Activity Recognition Based on Accelerometer Data from Smartphone Sensors Using CNN-BiGRU Model. 11th International Conference on Digital Arts Media and Technology and 9th Ecti Northern Section Conference on Electrical Electronics Computer and Telecommunications Engineering Ecti Damt and Ncon 2026 (2026) , 688-693. 693. doi:10.1109/ECTIDAMTNCON67592.2026.11460018 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/116516
Title
Real-life Human Activity Recognition Based on Accelerometer Data from Smartphone Sensors Using CNN-BiGRU Model
Author(s)
Corresponding Author(s)
Other Contributor(s)
Abstract
Human activity recognition using smartphone sensors is essential for health monitoring and context-aware applications. This study presents a hybrid deep learning model that combines convolutional neural networks (CNNs) and bidirectional gated recurrent units (BiGRUs) to recognize daily activities from tri-axial accelerometer data. The proposed approach is evaluated on the Real-Life Human Activity Recognition (RL-HAR) dataset, which includes data from 19 participants performing four everyday activities under real-world conditions. Raw sensor signals are pre-processed using noise filtering and overlapping sliding-window segmentation. The CNN component extracts spatial features, while the BiGRU component captures bidirectional temporal dependencies. Experimental results from subject-independent 5-fold cross-validation demonstrate that the proposed CNN-BiGRU model achieves 95.84% accuracy and 95.65% F1-score, outperforming both CNN-only and recurrent baseline models.