Enhancing pH prediction accuracy in Al2O3 gated ISFET using XGBoost regressor and stacking ensemble learning
Abstract An ion-sensitive field-effect transistor (ISFET) is widely used in environmental and biomedical applications due to its rapid response, miniaturization, and cost-effectiveness. In this study, a numerical model of an Al₂O₃-gated ISFET was developed to detect pH levels. The effects of gate di...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-06-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-04530-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850242872236834816 |
|---|---|
| author | Ashirbad Panda Rishikesh Datar Shreyas Deshpande Gautam Bacher |
| author_facet | Ashirbad Panda Rishikesh Datar Shreyas Deshpande Gautam Bacher |
| author_sort | Ashirbad Panda |
| collection | DOAJ |
| description | Abstract An ion-sensitive field-effect transistor (ISFET) is widely used in environmental and biomedical applications due to its rapid response, miniaturization, and cost-effectiveness. In this study, a numerical model of an Al₂O₃-gated ISFET was developed to detect pH levels. The effects of gate dielectric thickness, doping concentration, and temperature on ISFET’s performance were evaluated using IDS–VDS characteristics. An eXtreme Gradient Boosting (XGBoost) regression model was employed to predict pH levels using data obtained from IDS–VDS characteristics. Further, Hyperparameter optimization was performed to tune critical XGBoost-hyperparameters such as maximum depth, minimum child weight, estimators, learning rate, α, and λ. The optimization strategies such as random search, grid search and Bayesian optimization were utilized to improve the efficacy of regressor by minimizing errors and maximizing accuracy in prediction. A stacking ensemble learning approach was also implemented to integrate multiple models, enhancing prediction accuracy and thereby capturing additional information. The XGBoost regressor achieved superior results with R2 = 0.9846, MSE = 0.2342, and MAE = 0.2317, compared to other regressor models. Therefore, the use of XGBoost regressors with hyperparameter optimization and stacking ensemble learning approach is found to be highly effective for pH prediction from ISFET under various operating conditions. |
| format | Article |
| id | doaj-art-2ffcfdcdcced49be937ed8e97cee7a3d |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-2ffcfdcdcced49be937ed8e97cee7a3d2025-08-20T02:00:09ZengNature PortfolioScientific Reports2045-23222025-06-0115111210.1038/s41598-025-04530-2Enhancing pH prediction accuracy in Al2O3 gated ISFET using XGBoost regressor and stacking ensemble learningAshirbad Panda0Rishikesh Datar1Shreyas Deshpande2Gautam Bacher3Department of Electrical and Electronics Engineering, BITS Pilani K K Birla Goa CampusDepartment of Electrical and Electronics Engineering, BITS Pilani K K Birla Goa CampusDepartment of Electrical and Electronics Engineering, BITS Pilani K K Birla Goa CampusDepartment of Electrical and Electronics Engineering, BITS Pilani K K Birla Goa CampusAbstract An ion-sensitive field-effect transistor (ISFET) is widely used in environmental and biomedical applications due to its rapid response, miniaturization, and cost-effectiveness. In this study, a numerical model of an Al₂O₃-gated ISFET was developed to detect pH levels. The effects of gate dielectric thickness, doping concentration, and temperature on ISFET’s performance were evaluated using IDS–VDS characteristics. An eXtreme Gradient Boosting (XGBoost) regression model was employed to predict pH levels using data obtained from IDS–VDS characteristics. Further, Hyperparameter optimization was performed to tune critical XGBoost-hyperparameters such as maximum depth, minimum child weight, estimators, learning rate, α, and λ. The optimization strategies such as random search, grid search and Bayesian optimization were utilized to improve the efficacy of regressor by minimizing errors and maximizing accuracy in prediction. A stacking ensemble learning approach was also implemented to integrate multiple models, enhancing prediction accuracy and thereby capturing additional information. The XGBoost regressor achieved superior results with R2 = 0.9846, MSE = 0.2342, and MAE = 0.2317, compared to other regressor models. Therefore, the use of XGBoost regressors with hyperparameter optimization and stacking ensemble learning approach is found to be highly effective for pH prediction from ISFET under various operating conditions.https://doi.org/10.1038/s41598-025-04530-2Al2O3Hyperparameter optimizationISFETRegressorStacking ensemble learningXGBoost |
| spellingShingle | Ashirbad Panda Rishikesh Datar Shreyas Deshpande Gautam Bacher Enhancing pH prediction accuracy in Al2O3 gated ISFET using XGBoost regressor and stacking ensemble learning Scientific Reports Al2O3 Hyperparameter optimization ISFET Regressor Stacking ensemble learning XGBoost |
| title | Enhancing pH prediction accuracy in Al2O3 gated ISFET using XGBoost regressor and stacking ensemble learning |
| title_full | Enhancing pH prediction accuracy in Al2O3 gated ISFET using XGBoost regressor and stacking ensemble learning |
| title_fullStr | Enhancing pH prediction accuracy in Al2O3 gated ISFET using XGBoost regressor and stacking ensemble learning |
| title_full_unstemmed | Enhancing pH prediction accuracy in Al2O3 gated ISFET using XGBoost regressor and stacking ensemble learning |
| title_short | Enhancing pH prediction accuracy in Al2O3 gated ISFET using XGBoost regressor and stacking ensemble learning |
| title_sort | enhancing ph prediction accuracy in al2o3 gated isfet using xgboost regressor and stacking ensemble learning |
| topic | Al2O3 Hyperparameter optimization ISFET Regressor Stacking ensemble learning XGBoost |
| url | https://doi.org/10.1038/s41598-025-04530-2 |
| work_keys_str_mv | AT ashirbadpanda enhancingphpredictionaccuracyinal2o3gatedisfetusingxgboostregressorandstackingensemblelearning AT rishikeshdatar enhancingphpredictionaccuracyinal2o3gatedisfetusingxgboostregressorandstackingensemblelearning AT shreyasdeshpande enhancingphpredictionaccuracyinal2o3gatedisfetusingxgboostregressorandstackingensemblelearning AT gautambacher enhancingphpredictionaccuracyinal2o3gatedisfetusingxgboostregressorandstackingensemblelearning |