EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ESC-NAS: Environment Sound Classification Using Hardware-Aware Neural Architecture Search for the Edge

Dakshina Ranmal iD, Piumini Ranasinghe iD, Thivindu Paranayapa iD, Dulani Meedeniya iD, Charith Perera iD

Sensors · 09.06.2024 · 24 (12) · 3749

DOI: 10.3390/s24123749 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 09.06.2024. Verfasst von Dakshina Ranmal und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science & Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The combination of deep-learning and IoT plays a significant role in modern smart solutions, providing the capability of handling task-specific real-time offline operations with improved accuracy and minimised resource consumption. This study provides a novel hardware-aware neural architecture search approach called ESC-NAS, to design and develop deep convolutional neural network architectures specifically tailored for handling raw audio inputs in environmental sound classification applications under limited computational resources. The ESC-NAS process consists of a novel cell-based neural architecture search space built with 2D convolution, batch normalization, and max pooling layers, and capable of extracting features from raw audio. A black-box Bayesian optimization search strategy explores the search space and the resulting model architectures are evaluated through hardware simulation. The models obtained from the ESC-NAS process achieved the optimal trade-off between model performance and resource consumption compared to the existing literature. The ESC-NAS models achieved accuracies of 85.78%, 81.25%, 96.25%, and 81.0% for the FSC22, UrbanSound8K, ESC-10, and ESC-50 datasets, respectively, with optimal model sizes and parameter counts for edge deployment.

Schlagwörter

Stichwörter der Autor:innen

deep learningenvironment sound classificationhardware-aware neural architecture searchlightweight convolutional neural networkssearch space

Autor:innen und Institutionen

  • Department of Computer Science & Engineering, University of Moratuwa, Moratuwa 10400, Sri Lanka.
  • School of Computer Science and Informatics, Cardiff University, Cardiff CF24 3AA, UK.

ORCID-Profile: Dakshina Ranmal, Piumini Ranasinghe, Thivindu Paranayapa, Dulani Meedeniya, Charith Perera

Zitieren

APA

Ranmal, D., Ranasinghe, P., Paranayapa, T., Meedeniya, D., & Perera, C. (2024). ESC-NAS: Environment Sound Classification Using Hardware-Aware Neural Architecture Search for the Edge. Sensors, 24(12), 3749. https://doi.org/10.3390/s24123749

Vancouver

Ranmal D, Ranasinghe P, Paranayapa T, Meedeniya D, Perera C. ESC-NAS: Environment Sound Classification Using Hardware-Aware Neural Architecture Search for the Edge. Sensors. 2024;24(12):3749. doi:10.3390/s24123749

BibTeX
@article{Ranmal2024,
  author = {Ranmal, Dakshina and Ranasinghe, Piumini and Paranayapa, Thivindu and Meedeniya, Dulani and Perera, Charith},
  title = {ESC-NAS: Environment Sound Classification Using Hardware-Aware Neural Architecture Search for the Edge},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {12},
  pages = {3749},
  doi = {10.3390/s24123749}
}
Kostenlos starten →