A Comparative Study of Validation Methods for Sensor-Based Human Activity Recognition Using Deep Learning Models
1
Issued Date
2025-01-01
Resource Type
Scopus ID
2-s2.0-105004547294
Journal Title
10th International Conference on Digital Arts, Media and Technology, DAMT 2025 and 8th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, NCON 2025
Start Page
686
End Page
691
Rights Holder(s)
SCOPUS
Bibliographic Citation
10th International Conference on Digital Arts, Media and Technology, DAMT 2025 and 8th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, NCON 2025 (2025) , 686-691
Suggested Citation
Mekruksavanich S., Hnoohom N., Phaphan W., Jitpattanakul A. A Comparative Study of Validation Methods for Sensor-Based Human Activity Recognition Using Deep Learning Models. 10th International Conference on Digital Arts, Media and Technology, DAMT 2025 and 8th ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering, NCON 2025 (2025) , 686-691. 691. doi:10.1109/ECTIDAMTNCON64748.2025.10962074 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/110136
Title
A Comparative Study of Validation Methods for Sensor-Based Human Activity Recognition Using Deep Learning Models
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
With the rise of wearable sensors and smart devices, human activity recognition (HAR) has become a vital research area in ubiquitous computing. Although many studies report high accuracy using k-fold cross-validation, these results often do not reflect actual generalization interpretation due to subject-dependent data leakage, where models test on activities from the subjects they were trained. This study compares traditional k-fold cross-validation with leave-one-subject-out (LOSO) validation using the WISDM dataset, highlighting the importance of proper validation techniques in HAR systems. We implemented and evaluated five advanced deep learning models - convolutional neural network (CNN), long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and bidirectional GRU (BiGRU) - on windowed raw sensor data. Our experiments showed significant differences between validation methods. The BiGRU model achieved 97.91% accuracy with k-fold cross-validation and 98.02% with LOSO validation, while the CNN model achieved only 92.55% and 93.44%, respectively. These results underscore the impact of both model architecture and validation approach on performance. Our findings stress the need for subject-independent validation strategies like LOSO to develop truly generalizable HAR systems.