The Study on the Accuracy of Classifiers for Water Quality Application

Rosly, Rosaida; Makhtar, Mokhairi; Awang, Mohd Khalid; Nordin, Mohamad Sahari; Abidin, Zainal

doi:10.14257/ijunesst.2015.8.3.13

Cited by 10 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Classification models can be used to analyze various influential factors in natural environmental processes and in this case, we analyze the impact of human activities using the water quality classification standards (WQCS) for a river basin [18]. Among various classification models, such as the Bayesian network (BN), artificial neural networks (ANNs), decision trees and support vector machines, we propose to use the BN model to find the optimum population ranges that can be carried by the natural environment in a watershed [19]. The BN is a network with nodes representing probabilistic variables and links representing probabilistic dependencies.…”

Section: Introductionmentioning

confidence: 99%

Impact of Population Growth on the Water Quality of Natural Water Bodies

2017

View full text Add to dashboard Cite

Human activities pose a significant threat to the water quality of rivers when pollution exceeds the threshold limit. Urban activities in particular are highlighted as one of the major causes of contamination in surface water bodies in Asian countries. Evaluation of sustainable human population capacities in river watersheds is necessary to maintain better freshwater ecosystems in a country while achieving its development goals as a nation. We evaluated the correlation between the growth rate of the population in a watershed area and water quality parameters of a river ecosystem. The Kelani River in Sri Lanka was selected for the study. The highest correlation coefficients of 0.7, 0.69, 0.69 (p < 0.01) corresponding to biochemical oxygen demand (BOD), dissolved oxygen (DO) and total coliform (TC) were obtained with the population in watersheds of the Kelani river in Sri Lanka. Thus, we propose a quantitative approach to estimating the population capacity of watersheds based on water quality classification standards (WQCS), employing the Bayesian network (BN) classification model. The optimum population ranges were obtained from the probability distribution table of the population node in the BN. The results showed that the population density should be approximately less than 2375 to keep the water quality in the watershed for bathing and drinking purposes and approximately less than 2672 for fish and other aquatic organisms. This research will offer a means that can used to understand the impact of population on water quality in river basins and confer direct influence on natural water bodies.

show abstract

Section: Introductionmentioning

confidence: 99%

Impact of Population Growth on the Water Quality of Natural Water Bodies

2017

View full text Add to dashboard Cite

show abstract

“…Before making any major choices, it is common for people to seek second or third views. In general, before a decision is made, individual opinions that may be slightly different from each other will be considered, and then their opinions will be combined to reach the final decision [23]- [25].…”

Section: E Ensemble Methodsmentioning

confidence: 99%

Improving Customer Churn Classification with Ensemble Stacking Method

Awang¹,

Makhtar²,

Udin³

et al. 2021

IJACSA

Self Cite

View full text Add to dashboard Cite

Due to the high cost of acquiring new customers, accurate customer churn classification is critical in any company. The telecommunications industry has employed single classifiers to classify customer churn; however, the classification accuracy remains low. Nevertheless, combining several classifiers' decisions improves classification accuracy. This article attempts to enhance ensemble integration via stack generalisation. This paper proposed a stacking ensemble based on six different learning algorithms as the base-classifiers and tested on five different meta-model classifiers. We compared the performance of the proposed stacking ensemble model with single classifiers, bagging and boosting ensemble. The performances of the models were evaluated with accuracy, precision, recall and ROC criteria. The findings of the experiments demonstrated that the proposed stacking ensemble model resulted in the improvement of the customer churn classification. Based on the results of the experiments, it indicates that the prediction accuracy, precision, recall and ROC of the proposed stacking ensemble with MLP meta-model outperformed other single classifiers and ensemble methods for the customer churn dataset.

show abstract

Analysing Ground Water Quality in the Regions of Kadapa District Using Supervised Learning Methods

Devi¹

2020

Learning and Analytics in Intelligent Systems

View full text Add to dashboard Cite

The Study on the Accuracy of Classifiers for Water Quality Application

Cited by 10 publications

References 19 publications

Impact of Population Growth on the Water Quality of Natural Water Bodies

Impact of Population Growth on the Water Quality of Natural Water Bodies

Improving Customer Churn Classification with Ensemble Stacking Method

Analysing Ground Water Quality in the Regions of Kadapa District Using Supervised Learning Methods

Contact Info

Product

Resources

About