Please use this identifier to cite or link to this item:
https://oarep.usim.edu.my/jspui/handle/123456789/23269
Title: | A Stacked Ensemble Deep Learning Approach For Imbalanced Multi-class Water Quality Index Prediction | Authors: | Wen Yee Wong Khairunnisa Hasikin Anis Salwa Mohd Khairuddin Sarah Abdul Razak Hanee Farzana Hizaddin Mohd Istajib Mokhtar Muhammad Mokhzaini Azizan |
Keywords: | Water quality classification; imbalanced data; SMOTE; stacked ensemble deep learning; sensitivity analysis | Issue Date: | 2023 | Publisher: | Tech Science Press | Source: | W. Y. Wong, K. Hasikin, A. S. M. Khairuddin, S. A. Razak, H. F. Hizaddin et al., "A stacked ensemble deep learning approach for imbalanced multi-class water quality index prediction," Computers, Materials & Continua, vol. 76, no.2, pp. 1361–1384, 2023. | Journal: | Computers, Materials and Continua | Abstract: | A common difficulty in building prediction models with realworld environmental datasets is the skewed distribution of classes. There are significantly more samples for day-to-day classes, while rare events such as polluted classes are uncommon. Consequently, the limited availability of minority outcomes lowers the classifier’s overall reliability. This study assesses the capability of machine learning (ML) algorithms in tackling imbalanced water quality data based on the metrics of precision, recall, and F1 score. It intends to balance the misled accuracy towards the majority of data. Hence, 10 ML algorithms of its performance are compared. The classifiers included are AdaBoost, Support Vector Machine, Linear Discriminant Analysis, k-Nearest Neighbors, Naïve Bayes, Decision Trees, Random Forest, Extra Trees, Bagging, and the Multilayer Perceptron. This study also uses the Easy Ensemble Classifier, Balanced Bagging, and RUSBoost algorithm to evaluate multi-class imbalanced learning methods. The comparison results revealed that a highaccuracy machine learning model is not always good in recall and sensitivity. This paper’s stacked ensemble deep learning (SE-DL) generalization model effectively classifies the water quality index (WQI) based on 23 input variables. The proposed algorithm achieved a remarkable average of 95.69%, 94.96%, 92.92%, and 93.88% for accuracy, precision, recall, and F1 score, respectively. In 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 included. The experimental setup concluded XGBoost with a higher balanced accuracy and G-mean. However, the SE-DL model has a better and more balanced performance in the F1 score. The SE-DL model aligns with the goal of this study to ensure the balance between accuracy and completeness for each water quality class. The proposed algorithm is also capable of higher efficiency at a lower computational time against using the standard Synthetic Minority Oversampling Technique (SMOTE) approach to imbalanced datasets. |
Description: | Vol.76, No.2 |
URI: | https://oarep.usim.edu.my/jspui/handle/123456789/23269 https://www.techscience.com/cmc/v76n2/54031 https://www.scopus.com/record/display.uri?eid=2-s2.0-85173545973&origin=resultslist&sort=plf-f&src=s&sid=3dd9073fabd4e7c8b4c704f3645e3e2b&sot=b&sdt=b&s=TITLE-ABS-KEY%28A+Stacked+Ensemble+Deep+Learning+Approach+for+Imbalanced+Multi-Class+Water+Quality+Index+Prediction%29&sl=101&sessionSearchId=3dd9073fabd4e7c8b4c704f3645e3e2b&relpos=0 |
ISSN: | 1546-2226 | DOI: | 10.32604/cmc.2023.038045 |
Appears in Collections: | Scopus |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
A Stacked Ensemble Deep Learning Approach for Imbalanced Multi-Class Water Quality Index Prediction.pdf | 1.37 MB | Adobe PDF | View/Open |
SCOPUSTM
Citations
4
checked on May 1, 2024
Download(s)
10
checked on Apr 25, 2024
Google ScholarTM
Check
Altmetric
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.