A Deep Learning Approach to Organic Pollutants Classification Using Voltammetry
This paper proposes a deep leaning technique for accurate detection and reliable classification of organic pollutants in water. The pollutants are detected by means of cyclic voltammetry characterizations made by using low-cost disposable screen-printed electrodes. The paper demonstrates the possibi...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/20/8032 |
| _version_ | 1797469920718487552 |
|---|---|
| author | Mario Molinara Rocco Cancelliere Alessio Di Tinno Luigi Ferrigno Mikhail Shuba Polina Kuzhir Antonio Maffucci Laura Micheli |
| author_facet | Mario Molinara Rocco Cancelliere Alessio Di Tinno Luigi Ferrigno Mikhail Shuba Polina Kuzhir Antonio Maffucci Laura Micheli |
| author_sort | Mario Molinara |
| collection | DOAJ |
| description | This paper proposes a deep leaning technique for accurate detection and reliable classification of organic pollutants in water. The pollutants are detected by means of cyclic voltammetry characterizations made by using low-cost disposable screen-printed electrodes. The paper demonstrates the possibility of strongly improving the detection of such platforms by modifying them with nanomaterials. The classification is addressed by using a deep learning approach with convolutional neural networks. To this end, the results of the voltammetry analysis are transformed into equivalent RGB images by means of Gramian angular field transformations. The proposed technique is applied to the detection and classification of hydroquinone and benzoquinone, which are particularly challenging since these two pollutants have a similar electroactivity and thus the voltammetry curves exhibit overlapping peaks. The modification of electrodes by carbon nanotubes improves the sensitivity of a factor of about ×25, whereas the convolution neural network after Gramian transformation correctly classifies 100% of the experiments. |
| first_indexed | 2024-03-09T19:29:48Z |
| format | Article |
| id | doaj.art-8040cd81324d4738b371fb551e4f7903 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T19:29:48Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8040cd81324d4738b371fb551e4f79032023-11-24T02:30:44ZengMDPI AGSensors1424-82202022-10-012220803210.3390/s22208032A Deep Learning Approach to Organic Pollutants Classification Using VoltammetryMario Molinara0Rocco Cancelliere1Alessio Di Tinno2Luigi Ferrigno3Mikhail Shuba4Polina Kuzhir5Antonio Maffucci6Laura Micheli7Department of Electrical and Information Engineering, University of Cassino and Southern Lazio, 03043 Cassino, ItalyDepartment of Chemical Science and Technologies, University of Rome “Tor Vergata”, 00133 Rome, ItalyDepartment of Chemical Science and Technologies, University of Rome “Tor Vergata”, 00133 Rome, ItalyDepartment of Electrical and Information Engineering, University of Cassino and Southern Lazio, 03043 Cassino, ItalyCenter of Physical Science and Technologies, 10257 Vilnius, LithuaniaInstitute of Photonics, Department of Physics and Mathematics, University of Eastern Finland, 80101 Joensuu, FinlandDepartment of Electrical and Information Engineering, University of Cassino and Southern Lazio, 03043 Cassino, ItalyDepartment of Chemical Science and Technologies, University of Rome “Tor Vergata”, 00133 Rome, ItalyThis paper proposes a deep leaning technique for accurate detection and reliable classification of organic pollutants in water. The pollutants are detected by means of cyclic voltammetry characterizations made by using low-cost disposable screen-printed electrodes. The paper demonstrates the possibility of strongly improving the detection of such platforms by modifying them with nanomaterials. The classification is addressed by using a deep learning approach with convolutional neural networks. To this end, the results of the voltammetry analysis are transformed into equivalent RGB images by means of Gramian angular field transformations. The proposed technique is applied to the detection and classification of hydroquinone and benzoquinone, which are particularly challenging since these two pollutants have a similar electroactivity and thus the voltammetry curves exhibit overlapping peaks. The modification of electrodes by carbon nanotubes improves the sensitivity of a factor of about ×25, whereas the convolution neural network after Gramian transformation correctly classifies 100% of the experiments.https://www.mdpi.com/1424-8220/22/20/8032carbon nanotubesconvolutional neural networkspollutant detectionscreen-printed electrodescyclic voltammetry |
| spellingShingle | Mario Molinara Rocco Cancelliere Alessio Di Tinno Luigi Ferrigno Mikhail Shuba Polina Kuzhir Antonio Maffucci Laura Micheli A Deep Learning Approach to Organic Pollutants Classification Using Voltammetry Sensors carbon nanotubes convolutional neural networks pollutant detection screen-printed electrodes cyclic voltammetry |
| title | A Deep Learning Approach to Organic Pollutants Classification Using Voltammetry |
| title_full | A Deep Learning Approach to Organic Pollutants Classification Using Voltammetry |
| title_fullStr | A Deep Learning Approach to Organic Pollutants Classification Using Voltammetry |
| title_full_unstemmed | A Deep Learning Approach to Organic Pollutants Classification Using Voltammetry |
| title_short | A Deep Learning Approach to Organic Pollutants Classification Using Voltammetry |
| title_sort | deep learning approach to organic pollutants classification using voltammetry |
| topic | carbon nanotubes convolutional neural networks pollutant detection screen-printed electrodes cyclic voltammetry |
| url | https://www.mdpi.com/1424-8220/22/20/8032 |
| work_keys_str_mv | AT mariomolinara adeeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT roccocancelliere adeeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT alessioditinno adeeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT luigiferrigno adeeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT mikhailshuba adeeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT polinakuzhir adeeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT antoniomaffucci adeeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT lauramicheli adeeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT mariomolinara deeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT roccocancelliere deeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT alessioditinno deeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT luigiferrigno deeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT mikhailshuba deeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT polinakuzhir deeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT antoniomaffucci deeplearningapproachtoorganicpollutantsclassificationusingvoltammetry AT lauramicheli deeplearningapproachtoorganicpollutantsclassificationusingvoltammetry |