EUVIMEDSkopri EUVIMED
Open access · CC BY 4.0

PAR-Net: An Enhanced Dual-Stream CNN–ESN Architecture for Human Physical Activity Recognition

Imran Ullah Khan iD, Jong Weon Lee iD

Sensors · 2024

DOI: 10.3390/s24061908 ↗

At a glance

Journal article in Sensors, 2024. Written by Imran Ullah Khan and 1 co-authors. Institution: Mixed Reality and Interaction Lab, Department of Software, Sejong University, Seoul 05006, Republic of Korea. Major MEDLINE topics: Neural Networks, Computer, Machine Learning. Cited 5 times so far (Crossref); 40 references. The full text is freely available (open access, CC BY 4.0). Funded by: Ministry of Science and ICT (MSIT), Institute for Information and Communications Technology Planning and Evaluation (IITP), Korean government (MSIT).

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Physical exercise affects many facets of life, including mental health, social interaction, physical fitness, and illness prevention, among many others. Therefore, several AI-driven techniques have been developed in the literature to recognize human physical activities. However, these techniques fail to adequately learn the temporal and spatial features of the data patterns. Additionally, these techniques are unable to fully comprehend complex activity patterns over different periods, emphasizing the need for enhanced architectures to further increase accuracy by learning spatiotemporal dependencies in the data individually. Therefore, in this work, we develop an attention-enhanced dual-stream network (PAR-Net) for physical activity recognition with the ability to extract both spatial and temporal features simultaneously. The PAR-Net integrates convolutional neural networks (CNNs) and echo state networks (ESNs), followed by a self-attention mechanism for optimal feature selection. The dual-stream feature extraction mechanism enables the PAR-Net to learn spatiotemporal dependencies from actual data. Furthermore, the incorporation of a self-attention mechanism makes a substantial contribution by facilitating targeted attention on significant features, hence enhancing the identification of nuanced activity patterns. The PAR-Net was evaluated on two benchmark physical activity recognition datasets and achieved higher performance by surpassing the baselines comparatively. Additionally, a thorough ablation study was conducted to determine the best optimal model for human physical activity recognition.

Subjects

MeSH terms (MEDLINE)

Neural Networks, ComputerMachine LearningHumansHuman ActivitiesRecognition, PsychologyExercise

Author keywords

deep learningecho state networksmachine learningphysical activity recognitionskeleton data

Authors and institutions

  • Mixed Reality and Interaction Lab, Department of Software, Sejong University, Seoul 05006, Republic of Korea.

ORCID profiles: Imran Ullah Khan, Jong Weon Lee

Funding

  • Ministry of Science and ICT (MSIT)
  • Institute for Information and Communications Technology Planning and Evaluation (IITP)
  • Korean government (MSIT)

Cite

APA

Khan, I. U., & Lee, J. W. (2024). PAR-Net: An Enhanced Dual-Stream CNN–ESN Architecture for Human Physical Activity Recognition. Sensors. https://doi.org/10.3390/s24061908

Vancouver

Khan IU, Lee JW. PAR-Net: An Enhanced Dual-Stream CNN–ESN Architecture for Human Physical Activity Recognition. Sensors. 2024. doi:10.3390/s24061908

BibTeX
@article{Khan2024,
  author = {Khan, Imran Ullah and Lee, Jong Weon},
  title = {PAR-Net: An Enhanced Dual-Stream CNN–ESN Architecture for Human Physical Activity Recognition},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24061908}
}
Start for free →