Enhancing Predictive Accuracy of Wastewater Treatment Process: An Approach via Optimizing Data Collection and Increasing Operating State Diversity DOI

Chuntao Pan,

Yikun Huang, Yao Lu

и другие.

Journal of Cleaner Production, Год журнала: 2024, Номер unknown, С. 144621 - 144621

Опубликована: Дек. 1, 2024

Язык: Английский

Bibliometric analysis of artificial intelligence in wastewater treatment: Current status, research progress, and future prospects DOI
Xingyang Li, Jiming Su, Hui Wang

и другие.

Journal of environmental chemical engineering, Год журнала: 2024, Номер 12(4), С. 113152 - 113152

Опубликована: Май 23, 2024

Язык: Английский

Процитировано

13
A comprehensive overview of the applications of kernel functions and data-driven models in regression and classification tasks in the context of software sensors DOI Creative Commons
Joyce Chen Yen Ngu, Wan Sieng Yeo,

Teck Fu Thien

и другие.

Applied Soft Computing, Год журнала: 2024, Номер 164, С. 111975 - 111975

Опубликована: Июль 10, 2024

Data-driven models can reduce the number of hardware sensors in a process plant by acting as low-cost substitutes for sensors. Since some data-driven have difficulty dealing with nonlinear data, kernel functions been integrated into due to their capability handle this behavior data. However, existing review studies on and regression classification are still limited. Moreover, functions, most research only focused radial basis function group, such gaussian hyperbolic tangent functions. Considering these gaps, study aims summarize up-to-date cumulative application categories, integration models. Different from other studies, discussed characteristics, advantages, disadvantages different Additionally, also summarizes critically reviews tasks, including advantages disadvantages. discovers state art that were used classification. Besides, found mostly task rather than task. In addition, is be applied various applications. Lastly, it recommended emphasize integrating adaptive industrial

Язык: Английский

Процитировано

5
Prediction and optimization of wastewater treatment process effluent chemical oxygen demand and energy consumption based on typical ensemble learning models DOI
Jian Chen, Jinquan Wan, Gang Ye

и другие.

Bioresource Technology, Год журнала: 2024, Номер 411, С. 131362 - 131362

Опубликована: Авг. 27, 2024

Язык: Английский

Процитировано

4
Comprehensive Assessment of E. coli Dynamics in River Water Using Advanced Machine Learning and Explainable AI DOI

Santanu Mallik,

Bikram Saha,

Krishanu Podder

и другие.

Process Safety and Environmental Protection, Год журнала: 2025, Номер unknown, С. 106816 - 106816

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Joint SOH and RUL estimation for lithium-ion batteries via optimal deep belief network with Bayesian algorithm DOI

Ruyi Zheng,

Bo Yang,

Yucun Qian

и другие.

Journal of Energy Storage, Год журнала: 2025, Номер 114, С. 115891 - 115891

Опубликована: Фев. 20, 2025

Язык: Английский

Процитировано

0
Data-driven prediction of effluent quality in wastewater treatment processes: Model performance optimization and missing-data handling DOI

Zhicheng Deng,

Jinquan Wan, Gang Ye

и другие.

Journal of Water Process Engineering, Год журнала: 2025, Номер 71, С. 107352 - 107352

Опубликована: Фев. 26, 2025

Язык: Английский

Процитировано

0
Optimizing airflow rate and carbon source dosage strategies for wastewater treatment plant: Toward carbon emission reduction and enhanced nitrogen removal DOI
Xuefei Li,

Huaying Sun,

Zunfang Hu

и другие.

Journal of Water Process Engineering, Год журнала: 2025, Номер 72, С. 107513 - 107513

Опубликована: Март 19, 2025

Язык: Английский

Процитировано

0
An improved graph neural network integrating indicator attention and spatio-temporal correlation for dissolved oxygen prediction DOI Creative Commons
Fei Ding, Shilong Hao,

Mingcen Jiang

и другие.

Ecological Informatics, Год журнала: 2025, Номер unknown, С. 103126 - 103126

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
An interpretable machine learning model for predicting mortality risk in adult ICU patients with acute respiratory distress syndrome DOI Creative Commons

Wanyi Li,

Hangyu Zhou,

Yingxue Zou

и другие.

Frontiers in Medicine, Год журнала: 2025, Номер 12

Опубликована: Апрель 25, 2025

Background Acute respiratory distress syndrome (ARDS) is a clinical triggered by pulmonary or extra-pulmonary factors with high mortality and poor prognosis in the ICU. The aim of this study was to develop an interpretable machine learning predictive model predict risk death patients ARDS Methods datasets used were obtained from two independent databases: Medical Information Mart for Intensive Care (MIMIC) IV eICU Collaborative Research Database (eICU-CRD). This eight algorithms construct models. Recursive feature elimination cross-validation screen features, cross-validation-based Bayesian optimization filter features find optimal combination hyperparameters model. Shapley additive explanations (SHAP) method explain decision-making process Results A total 5,732 severe ADRS included analysis, which 1,171 (20.4%) did not survive. Among models, XGBoost performed best; AUC-ROC 0.887 (95% CI: 0.863–0.909) AUPRC 0.731 0.673–0.783). Conclusion We developed learning-based predicting critically ill ICU, our can effectively identify high-risk at early stage, thereby supporting decision-making, facilitating intervention, improving patient prognosis.

Язык: Английский

Процитировано

0
Machine learning modeling of thermally assisted biodrying process for municipal sludge DOI
Kaiqiang Zhang,

Ningfung Wang

Waste Management, Год журнала: 2024, Номер 188, С. 95 - 106

Опубликована: Авг. 10, 2024

Язык: Английский

Процитировано

3