TY - GEN
T1 - Real-life Human Activity Recognition Based on Accelerometer Data from Smartphone Sensors Using CNN-BiGRU Model
AU - Mekruksavanich, Sakorn
AU - Fan, Yongliang
AU - Hnoohom, Narit
AU - Jitpattanakul, Anuchit
N1 - Publisher Copyright:
© 2026 IEEE.
PY - 2026
Y1 - 2026
N2 - 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.
AB - 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.
KW - CNN-BiGRU
KW - accelerometer
KW - deep learning
KW - human activity recognition
KW - real-life activities
KW - smartphone sensors
UR - https://www.scopus.com/pages/publications/105037004945
U2 - 10.1109/ECTIDAMTNCON67592.2026.11460018
DO - 10.1109/ECTIDAMTNCON67592.2026.11460018
M3 - Conference contribution
AN - SCOPUS:105037004945
T3 - 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
SP - 688
EP - 693
BT - 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
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 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
Y2 - 4 February 2026 through 7 February 2026
ER -