EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimizing IoT Video Data: Dimensionality Reduction for Efficient Deep Learning on Edge Computing

David Ortiz-Perez, Pablo Ruiz-Ponce, David Mulero-Pérez, Manuel Benavent-Lledo, Javier Rodriguez-Juan, Hugo Hernandez-Lopez, Anatoli Iarovikov, Srdjan Krco, Daliborka Nedic, Dejan Vukobratovic, Jose Garcia-Rodriguez

Future Internet · 21.01.2025 · 17 (2) · 53

DOI: 10.3390/fi17020053 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Future Internet, online erschienen am 21.01.2025. Verfasst von David Ortiz-Perez und 10 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Regional Development Fund (ERDF), Spanish Ministry of Digital Processing and by the European Union NextGeneration EU, three Spanish national and two regional grants for PhD studies.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid loss of biodiversity significantly impacts birds’ environments and behaviors, highlighting the importance of analyzing bird behavior for ecological insights. With the growing adoption of Machine Learning (ML) algorithms in the Internet of Things (IoT) domain, edge computing has become essential to ensure data privacy and enable real-time predictions by processing high-dimensional data, such as video streams, efficiently. This paper introduces a set of dimensionality reduction techniques tailored for video sequences based on cutting-edge methods for this data representation. These methods drastically compress video data, reducing bandwidth and storage requirements while enabling the creation of compact ML models with faster inference speeds. Comprehensive experiments on bird behavior classification in rural environments demonstrate the effectiveness of the proposed techniques. The experiments incorporate state-of-the-art deep learning techniques, including pre-trained video vision models, Autoencoders, and single-frame feature extraction. These methods demonstrated superior performance to the baseline, achieving up to a 6000-fold reduction in data size while reaching a classification accuracy of 60.7% on the Visual WetlandBirds Dataset and obtaining state-of-the-art performance on this dataset. These findings underline the potential of using dimensionality reduction to enhance the scalability and efficiency of bird behavior analysis.

Förderung

  • European Regional Development Fund (ERDF)
  • Spanish Ministry of Digital Processing and by the European Union NextGeneration EU
  • three Spanish national and two regional grants for PhD studies

Zitieren

APA

Ortiz-Perez, D., Ruiz-Ponce, P., Mulero-Pérez, D., Benavent-Lledo, M., Rodriguez-Juan, J., Hernandez-Lopez, H., Iarovikov, A., Krco, S., Nedic, D., Vukobratovic, D., & Garcia-Rodriguez, J. (2025). Optimizing IoT Video Data: Dimensionality Reduction for Efficient Deep Learning on Edge Computing. Future Internet, 17(2), 53. https://doi.org/10.3390/fi17020053

Vancouver

Ortiz-Perez D, Ruiz-Ponce P, Mulero-Pérez D, Benavent-Lledo M, Rodriguez-Juan J, Hernandez-Lopez H, et al. Optimizing IoT Video Data: Dimensionality Reduction for Efficient Deep Learning on Edge Computing. Future Internet. 2025;17(2):53. doi:10.3390/fi17020053

BibTeX
@article{OrtizPerez2025,
  author = {Ortiz-Perez, David and Ruiz-Ponce, Pablo and Mulero-Pérez, David and Benavent-Lledo, Manuel and Rodriguez-Juan, Javier and Hernandez-Lopez, Hugo and Iarovikov, Anatoli and Krco, Srdjan and Nedic, Daliborka and Vukobratovic, Dejan and Garcia-Rodriguez, Jose},
  title = {Optimizing IoT Video Data: Dimensionality Reduction for Efficient Deep Learning on Edge Computing},
  journal = {Future Internet},
  year = {2025},
  volume = {17},
  number = {2},
  pages = {53},
  doi = {10.3390/fi17020053}
}
Kostenlos starten →