Correspondence pubs.acs.org/IECR
Response to “Comment on ‘Enhanced Biosorptive Remediation of Hexavalent Chromium Using Chemotailored Biomass of a Novel Soil Isolate Bacillus aryabhattai ITBHU02: Process Variables Optimization through Artificial Neural Network Linked Genetic Algorithm’” Devendra Kumar Verma,† Syed Hadi Hasan,‡ Devendra Kumar Singh,‡ Shalini Singh,† and Yogendra Singh*,† †
School of Biochemical Engineering and ‡Water Pollution Research Laboratory, Department of Applied Chemistry, Indian Institute of Technology (Banaras Hindu University), Varanasi−221005 (U.P.), India
T
ANN-GA. In our view, it was sufficient to be justified with the performance of the used techniques in our study. As per another comment of Cheng and Li1 on RSM eq 16 in our original work,2 the equation was originally written using regression coefficients achieved in MINITAB software, following the method that has been similarly stated elsewhere in so much literature13,14 and already given by us in different articles.7−9 However, the coefficients used in the regression equation proposed by Cheng and Li1 were also achieved by the authors during the analysis; these, instead, were not utilized as in all other reports using RSM.14−16
his letter is intended as a response to the comments by Cheng and Li1 regarding our article2 that was published in a recent volume of I&EC Research. The objective of the published manuscript was to remove toxic hexavalent chromium from water through a biosorption process, using a chemically modified biomass of Bacillus aryabhattai ITBHU02, which was a novel bacterium originally isolated by our group from the soil disposal site contaminated with degrading waste;3 this bacterium was finally accredited with reference number NCIM 5503 from the National Collection of Industrial Microorganisms (NCIM), which is a Council of Scientific and Industrial Research (CSIR)-National Chemical Laboratory under the Government of India. Hence, this novel bacterium was harvested by growth in a nutrient broth medium; the biomass was harvested, chemically modified, and finally utilized for chromium(VI) removal from water. The process of metal removal necessitates a large amount of experimentation to achieve an optimized set of parameters, which might not be economically viable or environmentally friendly. Therefore, we have utilized the available statistical and mathematical approaches in the literature. The response surface method (RSM) and the artificial neural network linked genetic algorithm (ANN-GA) are useful techniques to achieve the target, and these have been extensively utilized simultaneously.4,5 The authors had already implemented RSM in most of their previous work.6−9 The ANN-GA technique had been reported to be potentially more accurate and powerful, in comparison to statistical approaches such as RSM.10,11 Therefore, the authors applied RSM and ANN-GA on the same dataset (31 experiments) to compare the results. As Cheng and Li pointed out,1 the obtained network was overtrained and overfitted. The authors of the manuscript accept this comment and further state that the MSE values might be resulted due to overtraining, which is feasible, since Cheng and Li1 had themselves admitted the possibility of infinite solutions. Furthermore, they had declared that at least 67 experiments would be required to train the network, but we only used 24 data to train the network by following the available literatures, in which researchers even have implemented using less than 30 experimental data.4,5,11,12 Furthermore, the predicted ANN-GA conditions were performed experimentally in the laboratory, and the authors had received satisfactory results closure to the predicted results through © 2014 American Chemical Society
■
AUTHOR INFORMATION
Corresponding Author
*Tel.: +91 9450283646. E-mail: yogendrasingh.rs.bce @iitbhu. ac.in. Notes
The authors declare no competing financial interest.
■
REFERENCES
(1) Cheng, X.; Li, S. Comment on “Enhanced biosorptive remediation of hexavalent chromium using chemotailored biomass of a novel soil isolate Bacillus aryabhattai ITBHU02: Process variables optimization through artificial neural network linked genetic algorithm”. Ind. Eng. Chem. Res. 2014, DOI: 10.1021/ie501189c. (2) Verma, D. K.; Hasan, S. H.; Singh, D. K.; Singh, S.; Singh, Y. Enhanced biosorptive remediation of hexavalent chromium using chemotailored biomass of a novel soil isolate Bacillus aryabhattai ITBHU02: Process variables optimization through artificial neural network linked genetic algorithm. Ind. Eng. Chem. Res. 2014, 53 (9), 3669−3681. (3) Singh, Y.; Srivastava, S. K. Statistical and evolutionary optimization for enhanced production of an anti-leukemic enzyme, L-asparaginase, in a protease-deficient Bacillus aryabhattai ITBHU02 isolate from the soil contaminated with hospital waste. Indian J. Exp. Biol. 2013, 51, 322−335. (4) Wang, J. L.; Wei, W. Optimization of fermentative hydrogen production process using genetic algorithm based on neural network and response surface methodology. Int. J. Hydrogen Energy 2008, 34, 255−261. (5) Zafar, M.; Kumar, S.; Kumar, S.; Dhiman, A. K. Optimization of polyhydroxybutyrate (PHB) production by Azohydromonas lata MTCC 2311 by using genetic algorithm based on artificial neural Published: April 15, 2014 7271
dx.doi.org/10.1021/ie501357u | Ind. Eng. Chem. Res. 2014, 53, 7271−7272
Industrial & Engineering Chemistry Research
Correspondence
network and response surface methodology. Biocatal. Agric. Biotechnol. 2012, 1, 70−79. (6) Talat, M.; Prakash, O.; Hasan, S. H. Enzymatic detection of As(III) in aqueous solution using alginate immobilized pumpkin urease: Optimization of process variables by response surface methodology. Bioresour. Technol. 2009, 100, 4462−4467. (7) Hasan, S. H.; Srivastava, P.; Talat, M. Biosorption of lead using immobilized Aeromonas hydrophila biomass in up flow column system: Factorial design for process optimization. J. Hazard. Mater. 2010, 177, 312−322. (8) Prakash, O.; Talat, M.; Hasan, S. H. Response surface design for the optimization of enzymatic detection of mercury ions in aqueous solution using immobilized Urease from vegetable waste. J. Mol. Catal. B: Enzym. 2008, 56, 265−271. (9) Ranjan, D.; Srivastava, P.; Talat, M.; Hasan, S. H. Removal of Cr(VI) from water using biomass of Aeromonas hydrophila: Central composite design for optimization of process variables. Appl. Biochem. Biotechnol. 2009, 158, 524−539. (10) Pal, M. P.; Vaidya, B. K.; Desai, K. M.; Joshi, R. M.; Nene, S. N.; Kulkarni, B. D. Medium optimization for biosurfactant production by Rhodococcus erythropolis MTCC 2794: Artificial intelligence verses a statistical approach. J. Ind. Microbiol. Biotechnol. 2009, 36, 747−756. (11) Desai, K. M.; Survase, S. A.; Saudagar, P. S.; Lele, S. S.; Singhal, R. S. Comparison of artificial neural network (ANN) and response surface methodology (RSM) in fermentation media optimization: Case study of fermentative production of scleroglucan. Biochem. Eng. J. 2008, 41, 266−273. (12) Sivapathasekaran, C.; Mukherjee, S.; Ray, A.; Sen, R. Artificial neural network modeling and genetic algorithm based medium optimization for the improved production of marine biosurfactant. Bioresour. Technol. 2010, 108, 2884−2887. (13) Mohana, S.; Shalini, S.; Jyoti, D.; Datta, M. Response surface methodology for optimization of medium for decolorization of textile dye Direct Black 22 by a novel bacterial consortium. Bioresour. Technol. 2008, 99, 562−569. (14) Liu, H. L.; Chiou, Y. R. Optimal decolorization efficiency of Reactive Red 239 by UV/TiO2 photocatalytic process coupled with response surface methodology. Chem. Eng. J. 2005, 112, 173−179. (15) Kumar, S.; Pakshirajan, K.; Venkata Dasu, V. Assessment of physical process conditions for enhanced production of novel glutaminase-free L-Asparaginase from Pectobacterium carotovorum MTCC 1428. Appl. Biochem. Biotechnol. 2010, 163, 327−337. (16) Lu, C. H.; Engelmann, N. J.; Lila, M. A.; Erdman, J. W., Jr. Optimization of lycopene extraction from tomato cell suspension culture by response surface methodology. J. Agric. Food Chem. 2008, 56, 7710−7714.
7272
dx.doi.org/10.1021/ie501357u | Ind. Eng. Chem. Res. 2014, 53, 7271−7272