Abstract— In this study, the Multivariate Linear Regression (MLR), Artificial Neural Network (ANN), k-Nearest Neighbour (kNN), and Support Vector Machine (SVM) models had been developed to simulate and to predict the water quality of Laguna Lake. The input variables for the MLR model had been determined through linear regression. The ANN, kNN, and SVM had been modelled per water quality parameter with cross validation and evaluated through its accuracy. The performance of the MLR models had been evaluated with the statistical metrics R-squared, Mean Absolute Error, and Root Mean Square Error. A web-based water quality monitoring had been developed to incorporate in their monitoring. The results had indicated that the performance of SVM is superior in the prediction of classes in most water quality parameters. The study results had shown that the poor correlation between the water quality parameters indicated that the data cannot be modelled. The results had shown that the correlation had not reached the threshold to be significant of 60% for R-squared. As per the classification models, the results of the comparison had shown that SVM had been the best model in the majority of parameters.
Index Terms— Artificial neural network, classification, multivariate linear regression, machine learning, predictive model.
The authors are with the College of Computer and Information Science at Malayan College Laguna, A Mapua School, Pulo-Diezmo Road, Cabuyao, Laguna, Philippines (e-mail: firstname.lastname@example.org, email@example.com, firstname.lastname@example.org, email@example.com).
Cite: Jonalyn G. Ebron, Rommel Ivan D. De Leon, Arviejhay D. Alejandro, and Basaron A. Amoranto , " Computational and Numerical Modeling for Classification of Water Quality of Lake ," International Journal of Environmental Science and Development vol. 11, no. 9, pp. 425-431, 2020.Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).