EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

A Lightweight Embedded Neural Network for Real‐Time Water Quality Classification in IoT ‐Based Monitoring Systems

Eduardo C. Vicente, Anita M. da Rocha Fernandes, Luis Augusto Silva Zendron, Wemerson D. Parreira

Concurrency and Computation: Practice and Experience · 2026-11 · 38 (21)

DOI: 10.1002/cpe.71015 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Concurrency and Computation: Practice and Experience, online erschienen am 01.11.2026. Verfasst von Eduardo C. Vicente und 3 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Fundação de Amparo à Pesquisa e Inovação do Estado de Santa Catarina.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A lightweight neural‐network classifier was developed to assign surface‐water samples to the five quality classes established by Brazil's environmental standard CONAMA 357/2005. The study used a 2018 dataset from SEMASA‐Itajaí comprising 8928 hourly observations of pH, turbidity, apparent color, and local rainfall. After removing outliers, applying weighted k‐nearest‐neighbor imputation and performing min–max normalization, the data were evaluated using a 5‐fold Stratified Cross‐Validation approach to ensure robust generalization. The network, implemented in TensorFlow, consists of two fully connected layers with 32 and 16 rectified linear units, followed by a softmax output layer. Training for 100 epochs with the Adam optimizer (learning rate 0.001) achieved an average validation accuracy of 97.63% (±0.86%), with misclassifications restricted to adjacent regulatory classes. Adding rainfall as an auxiliary feature and fine‐tuning the learning rate further increased accuracy by 0.7 percentage points and reduced training variance.

Förderung

  • Fundação de Amparo à Pesquisa e Inovação do Estado de Santa Catarina

Zitieren

APA

Vicente, E. C., Fernandes, A. M. D. R., Zendron, L. A. S., & Parreira, W. D. (2026). A Lightweight Embedded Neural Network for Real‐Time Water Quality Classification in IoT ‐Based Monitoring Systems. Concurrency and Computation: Practice and Experience, 38(21). https://doi.org/10.1002/cpe.71015

Vancouver

Vicente EC, Fernandes AMDR, Zendron LAS, Parreira WD. A Lightweight Embedded Neural Network for Real‐Time Water Quality Classification in IoT ‐Based Monitoring Systems. Concurrency and Computation: Practice and Experience. 2026;38(21). doi:10.1002/cpe.71015

BibTeX
@article{Vicente2026,
  author = {Vicente, Eduardo C. and Fernandes, Anita M. da Rocha and Zendron, Luis Augusto Silva and Parreira, Wemerson D.},
  title = {A Lightweight Embedded Neural Network for Real‐Time Water Quality Classification in IoT ‐Based Monitoring Systems},
  journal = {Concurrency and Computation: Practice and Experience},
  year = {2026},
  volume = {38},
  number = {21},
  doi = {10.1002/cpe.71015}
}
Kostenlos starten →