Estimation of water quality index using artificial intelligence approaches and multi-linear regression

Abstract

<span lang="EN-US">Water quality index is a measure of water quality at a certain location and over a period of time. High value indicates that the water is unsafe for drinking and inadequate in quality to meet the designated uses. Most of the classical models are unreliable producing unpromising forecasting results. This study presents Artificial Intelligence (AI) techniques and a Multi Linear Regression (MLR) as the classical linear model for estimating the Water Quality Index (WQI) of Palla station of Yamuna river, India. Full-scale data of the river were used in validating the models. Performance measures such as Mean Square Error (MSE), Root Mean Squared Error (RMSE) and Determination Coefficient (DC) were utilized in evaluating the accuracy and performance of the models. The obtained result depicted the superiority of AI models over the MLR model. The results also indicated that, the best model of both ANN and ANFIS proved high improvement in performance accuracy over MLR up to 10% in the verification phase. The difference between ANN and ANFIS accuracy is negligible due to a slight increment in performance accuracy indicating that both ANN and ANFIS could serve as reliable models for the estimation of WQI</span>.

Intelligent machine for sorting semi-precious minerals

“…The final version of the regression model of the mineral sorting process, = 7.614 + 0.146 1 + 0.116 2 + 0.014 3 (8) a multiple correlation coefficient was used to estimate the contribution of regression coefficients to the model equation. In this case, the correlation coefficient was K=0.9987, so the regression ( 8) almost completely describes the results of the experiment [28]- [33].…”

Data-Driven AI-Based Parameters Tuning Using Grid Partition Algorithm for Predicting Climatic Effect on Epidemic Diseases

“…One benefit of this architecture is a reliable representation of sophisticated non-linear relationships among unions. However special interests in using ANFIS to predict complex relationships have risen due to its good representation, fast convergence and soft computing [37]- [40]. ANFIS can be described with the following equations: It is assumed that exists linear and nonlinear parameters, h 1 , h 2 , c 1 , c 2 , j 1 and j 2 , when Q of m, tunes in K 1 ; Q of n , tunes in L 1 and Q of m, tunes in K 2 , and Q of n , tunes in L 2 respectively.…”

Best neural simultaneous approximation

“…Scientists approximate functions by polynomials, wavelets, splines and neural networks. For the wide usage of neural networks and their ability to solve problems from different fields (see [21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38]) a set of functions from Lp space is approximated by neural networks in this work. Many papers contains this topic widely, we mention some of them in the references below (see [39][40][41][42][43][44][45][46][47]).…”