Recognition of sports and daily activities through deep learning and convolutional block attention
Issued Date
2024-01-01
Resource Type
eISSN
23765992
Scopus ID
2-s2.0-85196775142
Journal Title
PeerJ Computer Science
Volume
10
Rights Holder(s)
SCOPUS
Bibliographic Citation
PeerJ Computer Science Vol.10 (2024)
Suggested Citation
Mekruksavanich S., Phaphan W., Hnoohom N., Jitpattanakul A. Recognition of sports and daily activities through deep learning and convolutional block attention. PeerJ Computer Science Vol.10 (2024). doi:10.7717/PEERJ-CS.2100 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/99371
Title
Recognition of sports and daily activities through deep learning and convolutional block attention
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
Portable devices like accelerometers and physiological trackers capture movement and biometric data relevant to sports. This study uses data from wearable sensors to investigate deep learning techniques for recognizing human behaviors associated with sports and fitness. The proposed CNN-BiGRU-CBAM model, a unique hybrid architecture, combines convolutional neural networks (CNNs), bidirectional gated recurrent unit networks (BiGRUs), and convolutional block attention modules (CBAMs) for accurate activity recognition. CNN layers extract spatial patterns, BiGRU captures temporal context, andCBAMfocuses on informative BiGRU features, enabling precise activity pattern identification. The novelty lies in seamlessly integrating these components to learn spatial and temporal relationships, prioritizing significant features for activity detection. The model and baseline deep learning models were trained on the UCI-DSA dataset, evaluating with 5-fold cross-validation, including multi-class classification accuracy, precision, recall, and F1-score. The CNN-BiGRU-CBAM model outperformed baseline models like CNN, LSTM, BiLSTM, GRU, and BiGRU, achieving state-of-the-art results with 99.10% accuracy and F1-score across all activity classes. This breakthrough enables accurate identification of sports and everyday activities using simplified wearables and advanced deep learning techniques, facilitating athlete monitoring, technique feedback, and injury risk detection. The proposed model's design and thorough evaluation significantly advance human activity recognition for sports and fitness.