Performance evaluation of hydroponic wastewater treatment plant integrated with ensemble learning techniques : A feature selection approach
Wastewater treatment and reuse are being regarded as the most effective strategy for combating water scarcity threats. This study examined and reported the applications of the Internet of Things (IoT) and artificial intelligence in the phytoremediation of wastewater using Salvinia molesta plants. Wa...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI
2023
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/37639/1/Performance%20evaluation%20of%20hydroponic%20wastewater%20treatment%20plant%20integrated.pdf http://umpir.ump.edu.my/id/eprint/37639/ https://doi.org/10.3390/pr11020478 https://doi.org/10.3390/pr11020478 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Wastewater treatment and reuse are being regarded as the most effective strategy for combating water scarcity threats. This study examined and reported the applications of the Internet of Things (IoT) and artificial intelligence in the phytoremediation of wastewater using Salvinia molesta plants. Water quality (WQ) indicators (total dissolved solids (TDS), temperature, oxidation-reduction potential (ORP), and turbidity) of the S. molesta treatment system at a retention time of 24 h were measured using an Arduino IoT device. Finally, four machine learning tools (ML) were employed in modeling and evaluating the predicted concentration of the total dissolved solids after treatment (TDSt) of the water samples. Additionally, three nonlinear error ensemble methods were used to enhance the prediction accuracy of the TDSt models. The outcome obtained from the modeling and prediction of the TDSt depicted that the best results were observed at SVM-M1 with 0.9999, 0.0139, 1.0000, and 0.1177 for R2, MSE, R, and RMSE, respectively, at the training stage. While at the validation stage, the R2, MSE, R, and RMSE were recorded as 0.9986, 0.0356, 0.993, and 0.1887, respectively. Furthermore, the error ensemble techniques employed significantly outperformed the single models in terms of mean square error (MSE) and root mean square error (RMSE) for both training and validation, with 0.0014 and 0.0379, respectively. |
|---|