EUVIMEDEUVIMED entdecken
Crossref

Quantum Federated Deep Learning and Dragonfly Optimization for Smart Wastewater Treatment Prediction

Immanuel Mary, Jebamalar A, Angelin Stella

Journal of Quantum Nano- Green Environmental Systems · 2026

DOI: 10.70023/21605 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Quantum Nano- Green Environmental Systems, 2026. Verfasst von Immanuel Mary und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To optimally use resources, control contamination, and remain sustainable in environmental management, precise, predictive models are required for smart wastewater treatment systems. While traditional machine learning and deep learning methods may not be as effective as expected when wastewater data is distributed, they can suffer from limitations in prediction accuracy, computational complexity, convergence, and privacy protection. These limitations can significantly affect the functioning of an intelligent wastewater system, decision-making and treatment effectiveness. To address these challenges, the research proposes a novel framework, Quantum Federated Deep Learning (QFDL), and an optimization algorithm, Dragonfly Optimization (DFO), to build an intelligent wastewater treatment prediction system. The quantum federated learning model proposes a hybrid approach that integrates the federated learning paradigm with quantum computation to enhance feature representation and learning while preserving data privacy. Also, the Dragonfly Optimization algorithm optimally tunes the network parameters, increases convergence speed and enhances the prediction performance. The model is validated using a standard wastewater treatment dataset, including a range of physicochemical and biological water quality parameters. The accuracy is 99.34%, precision 98.91%, recall 99.12%, F1- score 99.01%, Matthews correlation coefficient (MCC) 98.76% and area under the ROC Curve (AUC) 99.58%, which are better than the existing state-of-the-art approaches. Overall, the proposed framework is a strong solution for next-generation smart wastewater treatment systems and sustainable environmental monitoring applications by providing accurate predictions, better privacy, reduced computational complexity, fast convergence and good scalability.

Zitieren

APA

Mary, I., A, J., & Stella, A. (2026). Quantum Federated Deep Learning and Dragonfly Optimization for Smart Wastewater Treatment Prediction. Journal of Quantum Nano- Green Environmental Systems. https://doi.org/10.70023/21605

Vancouver

Mary I, A J, Stella A. Quantum Federated Deep Learning and Dragonfly Optimization for Smart Wastewater Treatment Prediction. Journal of Quantum Nano- Green Environmental Systems. 2026. doi:10.70023/21605

BibTeX
@article{Mary2026,
  author = {Mary, Immanuel and A, Jebamalar and Stella, Angelin},
  title = {Quantum Federated Deep Learning and Dragonfly Optimization for Smart Wastewater Treatment Prediction},
  journal = {Journal of Quantum Nano- Green Environmental Systems},
  year = {2026},
  doi = {10.70023/21605}
}
Kostenlos starten →