A Deep Transfer Learning Approach to an Effective Classification of Water Pollutants From Voltammetric Characterizations
Authors: Guido Ala, Sergio Rapuano, Tiziana Tambosso, Molinara M., Ferrigno L., Maffucci A., Kuzhir P., Cancelliere R., Tinno A. D., Micheli L., Shuba M., Tinno A.D.
Abstract
This paper proposes a deep transfer learning approach based on convolutional neural networks to the detection of organic pollutants in water, starting from the results of electrochemical characterizations based on voltammetry. The approach is based on a deep transfer learning based on convolutional neural network. The results shown here refer to the detection of Hydroquinone and Benzoquinone by using voltammetry characterization results obtained from different screen printed platforms. The proposed approach provides a significant robustness against the input data heterogeneity and a highly reliable detection performance.
BibTeX
@article{guidoala2022a,
title={A Deep Transfer Learning Approach to an Effective Classification of Water Pollutants From Voltammetric Characterizations},
author={Guido Ala and Sergio Rapuano and Tiziana Tambosso and Molinara M. and Ferrigno L. and Maffucci A. and Kuzhir P. and Cancelliere R. and Tinno A. D. and Micheli L. and Shuba M. and Tinno A.D.},
year={2022},
doi={10.1109/MELECON53508.2022.9842896}
}