A hybrid neural network/genetic algorithm to predict Zn(II) removal by ion flotation
There are few methods to predict ion removal using ion flotation without lengthy experiments. The objective of this study was to model the Zn(II) flotation using a hybrid neural network/genetic algorithm (GANN) and multivariate linear regression (MLR). Mean square error and correlation coefficient v...
Saved in:
Published in | Separation science and technology Vol. 55; no. 6; pp. 1197 - 1206 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
Abingdon
Taylor & Francis
12.04.2020
Taylor & Francis Ltd |
Subjects | |
Online Access | Get full text |
ISSN | 0149-6395 1520-5754 |
DOI | 10.1080/01496395.2019.1582543 |
Cover
Summary: | There are few methods to predict ion removal using ion flotation without lengthy experiments. The objective of this study was to model the Zn(II) flotation using a hybrid neural network/genetic algorithm (GANN) and multivariate linear regression (MLR). Mean square error and correlation coefficient values of 0.9228 and 190.1, respectively, for testing the datasets of the GANN model reveal the superiority of the GANN model in predicting the Zn(II) removal, while these values were obtained as 0.9125 and 220.36, respectively, for the MLR model. The results showed that this model could be useful in predicting the Zn(II) removal in response to changes in the input parameters. |
---|---|
Bibliography: | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
ISSN: | 0149-6395 1520-5754 |
DOI: | 10.1080/01496395.2019.1582543 |