A Stacked Ensemble Deep Learning Approach for Imbalanced Multi-Class Water Quality Index Prediction

作     者：Wen Yee Wong Khairunnisa Hasikin Anis Salwa Mohd Khairuddin Sarah Abdul Razak Hanee Farzana Hizaddin Mohd Istajib Mokhtar Muhammad Mokhzaini Azizan 

作者机构：Department of Biomedical EngineeringFaculty of EngineeringUniversity of MalayaKuala Lumpur50603Malaysia Department of Electrical EngineeringFaculty of EngineeringUniversity of MalayaKuala Lumpur50603Malaysia Institute of Biological SciencesFaculty of ScienceUniversity of MalayaKuala Lumpur50603Malaysia Department of Chemical EngineeringFaculty of EngineeringUniversity of MalayaKuala Lumpur50603Malaysia Department of Science and Technology StudiesFaculty of ScienceUniversity of MalayaKuala Lumpur50603Malaysia Department of Electrical and Electronic EngineeringFaculty of Engineering and Built EnvironmentUniversiti Sains Islam MalaysiaNilaiNegeri Sembilan71800Malaysia 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2023年第76卷第8期

页      面：1361-1384页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：primarily supported by the Ministry of Higher Education through MRUN Young Researchers Grant Scheme(MY-RGS),MR001-2019,entitled“Climate Change Mitigation:Artificial Intelligence-Based Integrated Environmental System for Mangrove Forest Conservation,”received by K.H.,S.A.R.,H.F.H.,M.I.M.,and M.M.A secondarily funded by the UM-RU Grant,ST065-2021,entitled Climate Smart Mitigation and Adaptation:Integrated Climate Resilience Strategy for Tropical Marine Ecosystem 

主　　题：Water quality classification imbalanced data SMOTE stacked ensemble deep learning sensitivity analysis 

摘      要：A common difficulty in building prediction models with real-world environmental datasets is the skewed distribution of *** are significantly more samples for day-to-day classes,while rare events such as polluted classes are ***,the limited availability of minority outcomes lowers the classifier’s overall *** study assesses the capability of machine learning(ML)algorithms in tackling imbalanced water quality data based on the metrics of precision,recall,and F1 *** intends to balance the misled accuracy towards the majority of ***,10 ML algorithms of its performance are *** classifiers included are AdaBoost,SupportVector Machine,Linear Discriminant Analysis,k-Nearest Neighbors,Naive Bayes,Decision Trees,Random Forest,Extra Trees,Bagging,and the Multilayer *** study also uses the Easy Ensemble Classifier,Balanced Bagging,andRUSBoost algorithm to evaluatemulti-class imbalanced learning *** comparison results revealed that a highaccuracy machine learning model is not always good in recall and *** paper’s stacked ensemble deep learning(SE-DL)generalization model effectively classifies the water quality index(WQI)based on 23 input *** proposed algorithm achieved a remarkable average of 95.69%,94.96%,92.92%,and 93.88%for accuracy,precision,recall,and F1 score,*** addition,the proposed model is compared against two state-of-the-art classifiers,the XGBoost(eXtreme Gradient Boosting)and Light Gradient Boosting Machine,where performance metrics of balanced accuracy and g-mean are *** experimental setup concluded XGBoost with a higher balanced accuracy and ***,the SE-DL model has a better and more balanced performance in the F1 *** SE-DL model aligns with the goal of this study to ensure the balance between accuracy and completeness for each water quality *** proposed algorithm is also capable of higher efficiency at a lower computa