EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Smart Buildings: Water Leakage Detection Using TinyML

Othmane Atanane, Asmaa Mourhir iD, Nabil Benamar iD, Marco Zennaro iD

Sensors · 16.11.2023 · 23 (22) · 9210

DOI: 10.3390/s23229210 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 16.11.2023. Verfasst von Othmane Atanane und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Science and Engineering, Al Akhawayn University in Ifrane, P.O. Box 104, Hassan II Avenue, Ifrane 53000, Morocco. Die Arbeit wurde bisher 49-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The escalating global water usage and the increasing strain on major cities due to water shortages highlights the critical need for efficient water management practices. In water-stressed regions worldwide, significant water wastage is primarily attributed to leakages, inefficient use, and aging infrastructure. Undetected water leakages in buildings’ pipelines contribute to the water waste problem. To address this issue, an effective water leak detection method is required. In this paper, we explore the application of edge computing in smart buildings to enhance water management. By integrating sensors and embedded Machine Learning models, known as TinyML, smart water management systems can collect real-time data, analyze it, and make accurate decisions for efficient water utilization. The transition to TinyML enables faster and more cost-effective local decision-making, reducing the dependence on centralized entities. In this work, we propose a solution that can be adapted for effective leakage detection in real-world scenarios with minimum human intervention using TinyML. We follow an approach that is similar to a typical machine learning lifecycle in production, spanning stages including data collection, training, hyperparameter tuning, offline evaluation and model optimization for on-device resource efficiency before deployment. In this work, we considered an existing water leakage acoustic dataset for polyvinyl chloride pipelines. To prepare the acoustic data for analysis, we performed preprocessing to transform it into scalograms. We devised a water leak detection method by applying transfer learning to five distinct Convolutional Neural Network (CNN) variants, which are namely EfficientNet, ResNet, AlexNet, MobileNet V1, and MobileNet V2. The CNN models were found to be able to detect leakages where a maximum testing accuracy, recall, precision, and F1 score of 97.45%, 98.57%, 96.70%, and 97.63%, respectively, were observed using the EfficientNet model. To enable seamless deployment on the Arduino Nano 33 BLE edge device, the EfficientNet model is compressed using quantization resulting in a low inference time of 1932 ms, a peak RAM usage of 255.3 kilobytes, and a flash usage requirement of merely 48.7 kilobytes.

Schlagwörter

Stichwörter der Autor:innen

CNNEfficientNetTinyMLaccelerometeracoustic datadeep learningscalogram

Autor:innen und Institutionen

  • School of Science and Engineering, Al Akhawayn University in Ifrane, P.O. Box 104, Hassan II Avenue, Ifrane 53000, Morocco.
  • School of Technology, Moulay Ismail University of Meknes, Meknes 50050, Morocco.
  • The Abdus Salam International Centre for Theoretical Physics, 34151 Trieste, Italy.

ORCID-Profile: Asmaa Mourhir, Nabil Benamar, Marco Zennaro

Zitieren

APA

Atanane, O., Mourhir, A., Benamar, N., & Zennaro, M. (2023). Smart Buildings: Water Leakage Detection Using TinyML. Sensors, 23(22), 9210. https://doi.org/10.3390/s23229210

Vancouver

Atanane O, Mourhir A, Benamar N, Zennaro M. Smart Buildings: Water Leakage Detection Using TinyML. Sensors. 2023;23(22):9210. doi:10.3390/s23229210

BibTeX
@article{Atanane2023,
  author = {Atanane, Othmane and Mourhir, Asmaa and Benamar, Nabil and Zennaro, Marco},
  title = {Smart Buildings: Water Leakage Detection Using TinyML},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {22},
  pages = {9210},
  doi = {10.3390/s23229210}
}
Kostenlos starten →