Evaluating the Performance of Pre-Trained Convolutional Neural Network for Audio Classification on Embedded Systems for Anomaly Detection in Smart Cities
Sensors · 07.07.2023 · 23 (13) · 6227
DOI: 10.3390/s23136227 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 07.07.2023. Verfasst von Mimoun Lamrini und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Engineering Sciences and Technology (INDI), Vrije Universiteit Brussel (VUB), 1050 Brussels, Belgium. Hauptthemen laut MEDLINE: Neural Networks, Computer, Machine Learning. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Environmental Sound Recognition (ESR) plays a crucial role in smart cities by accurately categorizing audio using well-trained Machine Learning (ML) classifiers. This application is particularly valuable for cities that analyzed environmental sounds to gain insight and data. However, deploying deep learning (DL) models on resource-constrained embedded devices, such as Raspberry Pi (RPi) or Tensor Processing Units (TPUs), poses challenges. In this work, an evaluation of an existing pre-trained model for deployment on Raspberry Pi (RPi) and TPU platforms other than a laptop is proposed. We explored the impact of the retraining parameters and compared the sound classification performance across three datasets: ESC-10, BDLib, and Urban Sound. Our results demonstrate the effectiveness of the pre-trained model for transfer learning in embedded systems. On laptops, the accuracy rates reached 96.6% for ESC-10, 100% for BDLib, and 99% for Urban Sound. On RPi, the accuracy rates were 96.4% for ESC-10, 100% for BDLib, and 95.3% for Urban Sound, while on RPi with Coral TPU, the rates were 95.7% for ESC-10, 100% for BDLib and 95.4% for the Urban Sound. Utilizing pre-trained models reduces the computational requirements, enabling faster inference. Leveraging pre-trained models in embedded systems accelerates the development, deployment, and performance of various real-time applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Engineering Sciences and Technology (INDI), Vrije Universiteit Brussel (VUB), 1050 Brussels, Belgium.
- SIGL Laboratory, National School of Applied Sciences of Tetuan, Abdelmalek Essaadi University, Tetuan 93000, Morocco.
- Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), 1050 Brussels, Belgium.
ORCID-Profile: Mimoun Lamrini, Mohamed Yassin Chkouri, Abdellah Touhafi
Zitieren
APA
Lamrini, M., Chkouri, M. Y., & Touhafi, A. (2023). Evaluating the Performance of Pre-Trained Convolutional Neural Network for Audio Classification on Embedded Systems for Anomaly Detection in Smart Cities. Sensors, 23(13), 6227. https://doi.org/10.3390/s23136227
Vancouver
Lamrini M, Chkouri MY, Touhafi A. Evaluating the Performance of Pre-Trained Convolutional Neural Network for Audio Classification on Embedded Systems for Anomaly Detection in Smart Cities. Sensors. 2023;23(13):6227. doi:10.3390/s23136227
BibTeX
@article{Lamrini2023,
author = {Lamrini, Mimoun and Chkouri, Mohamed Yassin and Touhafi, Abdellah},
title = {Evaluating the Performance of Pre-Trained Convolutional Neural Network for Audio Classification on Embedded Systems for Anomaly Detection in Smart Cities},
journal = {Sensors},
year = {2023},
volume = {23},
number = {13},
pages = {6227},
doi = {10.3390/s23136227}
}
EUVIMED