Searching for just a few words should be enough to get started. If you need to make more complex queries, use the tips below to guide you.
Article type: Research Article
Authors: Khan, Izaz Ullaha; * | Shah, Jehanzeb Alib | Bilal, Muhammadb | Faiza, c | Khan, Muhammad Saqibb | Shah, Sajidd | Akgül, Alie
Affiliations: [a] Department of Mathematics, COMSATS University Islamabad, Abbottabad Campus, Pakistan | [b] Department of Environmental Sciences, COMSATS University Islamabad, Abbottabad Campus, Pakistan | [c] Virtual University of Pakistan | [d] EIAS Data science and Block Chain Lab, CCIS, Prince Sultan University, Riyadh, Saudi Arabia | [e] Department of Computer Science and Mathematics, Lebanese American University, Beirut, Lebanon Department of Mathematics, Arts and Science Faculty, SIIRT University, 56100, SIIRT, Turkey Near East University, Mathematics Research Centre, Department of Mathematics, Nicosia/Mersin-10 Turkey
Correspondence: [*] Corresponding author. Izaz Ullah Khan, Department of Mathematics, COMSATS University Islamabad, Abbottabad Campus Pakistan. E-mail: [email protected].
Abstract: This study develops machine learning model of removal of reactive orange dye (Azo) RO16 from textile wastewater by chemical activated carbon CAC. The study addresses the contamination removal efficiency with respect to changing dynamics of concentration, temperature, time, pH and dose, respectively. Machine learning based learning multiple polynomial regression is implemented to fit a model on the experimental observed data. The machine learns from the data and fit the multiple polynomial regression model for the data. The observed and predicted data are in close agreement with the R-squared value of 92%. The results show that the baseline efficiency of using chemical activated carbon adsorbent for removing RO16 is 76.5%. The most significant input parameter increasing the efficiency by a constant value of 35 units out of 100 is the second order response of the dose. Moreover, four input parameters can considerably increase the efficiency. Furthermore, six input parameters can considerably decrease the efficiency. It is investigated, that the second order response with respect to time has the minute decreasing effect on the removal efficiency. The superior abilities of the modeling are two fold. Firstly, the contamination removal of reactive orange dye (Azo) RO16 with chemical activated carbon adsorbent is studied with respect to five multiple parameters. Secondly, the model exploits the machine learning capability of the renowned Python machine learning module sklearn to fit a multiple polynomial regression model. Thus a robust model is fitted giving twenty-one inputs/output interactions and responses. From the input-target correlation analysis it is clear that the removal efficiency has a strong correlation with the time. It has considerably significant relationship with dose of the CAC and the temperature with values of 18% and 17%, respectively. Moreover, the removal efficiency has inverse relations with pH and Ci, with values of 15% and 12%, respectively.
Keywords: Textile wastewater, reactive orange dye, contamination removal, chemical activated carbon, machine learning, multiple polynomial regression
DOI: 10.3233/JIFS-220781
Journal: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 5, pp. 7977-7993, 2023
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
USA
Tel: +1 703 830 6300
Fax: +1 703 830 2300
[email protected]
For editorial issues, like the status of your submitted paper or proposals, write to [email protected]
IOS Press
Nieuwe Hemweg 6B
1013 BG Amsterdam
The Netherlands
Tel: +31 20 688 3355
Fax: +31 20 687 0091
[email protected]
For editorial issues, permissions, book requests, submissions and proceedings, contact the Amsterdam office [email protected]
Inspirees International (China Office)
Ciyunsi Beili 207(CapitaLand), Bld 1, 7-901
100025, Beijing
China
Free service line: 400 661 8717
Fax: +86 10 8446 7947
[email protected]
For editorial issues, like the status of your submitted paper or proposals, write to [email protected]
如果您在出版方面需要帮助或有任何建, 件至: [email protected]