<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Desai, Kiran M.</style></author><author><style face="normal" font="default" size="100%">Akolkar, S. K.</style></author><author><style face="normal" font="default" size="100%">Badhe, Yogesh P.</style></author><author><style face="normal" font="default" size="100%">Tambe, S. S.</style></author><author><style face="normal" font="default" size="100%">Lele, S. S.</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Optimization of fermentation media for exopolysaccharide production from lactobacillus plantarum using artificial intelligence-based techniques</style></title><secondary-title><style face="normal" font="default" size="100%">Process Biochemistry</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Artificial neural network</style></keyword><keyword><style  face="normal" font="default" size="100%">exopolysaccharide</style></keyword><keyword><style  face="normal" font="default" size="100%">Fermentation</style></keyword><keyword><style  face="normal" font="default" size="100%">Genetic algorithm</style></keyword><keyword><style  face="normal" font="default" size="100%">Lactobacillus plantarum</style></keyword><keyword><style  face="normal" font="default" size="100%">Media optimization</style></keyword><keyword><style  face="normal" font="default" size="100%">Plackett-Burman</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2006</style></year><pub-dates><date><style  face="normal" font="default" size="100%">AUG</style></date></pub-dates></dates><number><style face="normal" font="default" size="100%">8</style></number><publisher><style face="normal" font="default" size="100%">ELSEVIER SCI LTD</style></publisher><pub-location><style face="normal" font="default" size="100%">THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, OXON, ENGLAND</style></pub-location><volume><style face="normal" font="default" size="100%">41</style></volume><pages><style face="normal" font="default" size="100%">1842-1848</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;A Lactobacillus strain was isolated from the fermented Eleusine coracana. This strain was characterized as Lactobacillus plantarum and was found to produce an exopolysaccharide (EPS) in quantitative amounts. The objective of the present paper is to determine optimum media composition and inoculum volume for the stated fermentative production of the EPS. A hybrid methodology comprising the Plackett-Burman (PB) design method, artificial neural networks (ANN) and genetic algorithms (GA) was utilized. Specifically, the PB, ANN and GA forrnalisms were used for identifying influential media components, modeling non-linear process and optimizing the process, respectively. More specifically, the PB method was used to determine those media components, which significantly influence the EPS yield. By ignoring the less influential media components, the dimensionality of the input space of the process model could be reduced significantly. Out of the five media components only three were found influential namely, lactose, casein hydrolysate and triammonium citrate. Next, an ANN-based process model was developed for approximating the non-linear relationship between the fermentation operating variables and the EPS yield. The average % error and correlation coefficient for the developed ANN model were 4.8 and 0.999, respectively. The input parameters of ANN model were subsequently optimized using the GA formalism for obtaining maximum EPS yield in batch fermentation. The optimized media composition has predicted the yield of 7.01 g/l. The GA-optimized solution comprising media composition and inoculum volume was verified experimentally and it comes out be 7.14 g/l. (c) 2006 Elsevier Ltd. All rights reserved.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">8</style></issue><work-type><style face="normal" font="default" size="100%">Article</style></work-type><custom3><style face="normal" font="default" size="100%">&lt;p&gt;Foreign&lt;/p&gt;</style></custom3><custom4><style face="normal" font="default" size="100%">2.528</style></custom4></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Desai, Kiran M.</style></author><author><style face="normal" font="default" size="100%">Badhe, Yogesh P.</style></author><author><style face="normal" font="default" size="100%">Tambe, S. S.</style></author><author><style face="normal" font="default" size="100%">Kulkarni, B. D.</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Soft-sensor development for fed-batch bioreactors using support vector regression</style></title><secondary-title><style face="normal" font="default" size="100%">Biochemical Engineering Journal</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">deprotection</style></keyword><keyword><style  face="normal" font="default" size="100%">Microwave</style></keyword><keyword><style  face="normal" font="default" size="100%">stannous chloride</style></keyword><keyword><style  face="normal" font="default" size="100%">tert-butyldimethylsilyl ethers</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2006</style></year><pub-dates><date><style  face="normal" font="default" size="100%">JAN</style></date></pub-dates></dates><number><style face="normal" font="default" size="100%">3</style></number><publisher><style face="normal" font="default" size="100%">Indian Assoc Cultivat Sci</style></publisher><pub-location><style face="normal" font="default" size="100%">DR K S KRISHNAN MARG, NEW DELHI 110 012, INDIA</style></pub-location><volume><style face="normal" font="default" size="100%">27</style></volume><pages><style face="normal" font="default" size="100%">225-239</style></pages><isbn><style face="normal" font="default" size="100%">978-981-270-379-8</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;&lt;span style=&quot;color: rgb(51, 51, 51); font-family: arial, helvetica, sans-serif; font-size: 13px; line-height: 22px; background-color: rgb(248, 248, 248);&quot;&gt;In the present paper, a state-of-the-art machine learning based modeling formalism known as &quot;support vector regression (SVR)&quot;, has been introduced for the soft-sensor applications in the fed-batch processes. The SVR method possesses a number of attractive properties such as a strong statistical basis, convergence to the unique global minimum and an improved generalization performance by the approximated function. Also, the structure and parameters of an SVR model can be interpreted in terms of the training data. The efficacy of the SVR formalism for the soft-sensor development task has been demonstrated by considering two simulated bio-processes namely, invertase and streptokinase. Additionally, the performance of the SVR based soft-sensors is rigorously compared with those developed using the multilayer perceptron and radial basis function neural networks. The results presented here clearly indicate that the SVR is an attractive alternative to artificial neural networks for the development of soft-sensors in bioprocesses.&lt;/span&gt;&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">3</style></issue><work-type><style face="normal" font="default" size="100%">Article</style></work-type><notes><style face="normal" font="default" size="100%">Conference on Atomic Molecular and Optical Physics, Calcutta, INDIA, DEC 13-15, 2005</style></notes><custom3><style face="normal" font="default" size="100%">&lt;p&gt;Foreign&lt;/p&gt;</style></custom3><custom4><style face="normal" font="default" size="100%">2.463</style></custom4></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Mutalik, Snehal R.</style></author><author><style face="normal" font="default" size="100%">Vaidya, Bhalchandra K.</style></author><author><style face="normal" font="default" size="100%">Joshi, Renuka M.</style></author><author><style face="normal" font="default" size="100%">Desai, Kiran M.</style></author><author><style face="normal" font="default" size="100%">Nene, Sanjay N.</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Use of response surface optimization for the production of biosurfactant from rhodococcus spp. MTCC 2574</style></title><secondary-title><style face="normal" font="default" size="100%">Bioresource Technology</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Biosurfactant</style></keyword><keyword><style  face="normal" font="default" size="100%">Medium optimization</style></keyword><keyword><style  face="normal" font="default" size="100%">Response surface methodology</style></keyword><keyword><style  face="normal" font="default" size="100%">Rhodococcus spp.</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2008</style></year><pub-dates><date><style  face="normal" font="default" size="100%">NOV</style></date></pub-dates></dates><number><style face="normal" font="default" size="100%">16</style></number><publisher><style face="normal" font="default" size="100%">ELSEVIER SCI LTD</style></publisher><pub-location><style face="normal" font="default" size="100%">THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, OXON, ENGLAND</style></pub-location><volume><style face="normal" font="default" size="100%">99</style></volume><pages><style face="normal" font="default" size="100%">7875-7880</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;The production of biosurfactant from Rhodococcus spp. MTCC 2574 was effectively enhanced by response surface methodology (RSM). Rhodococcus spp. MTCC 2574 was selected through screening of seven different Rhodococcus strains. The preliminary screening experiments (one-factor at a time) suggested that carbon source: mannitol, nitrogen source: yeast extract and meat peptone and inducer: n-hexadecane are the critical medium components. The concentrations of these four media components were optimized by using central composite rotatable design (CCRD) of RSM. The adequately high R-2 value (0.947) and F score 19.11 indicated the statistical significance of the model. The optimum medium composition for biosurfactant production was found to contain mannitol (1.6 g/L), yeast extract (6.92 g/L), meat peptone (19.65 g/L), n-hexadecane (63.8 g/L). The crude biosurfactant was obtained from methyl tert-butyl ether extraction. The yield of biosurfactant before and after optimization was 3.2 g/L of and 10.9 g/L, respectively. Thus, RSM has increased the yield of biosurfactant to 3.4-fold. The crude biosurfactant decreased the surface tension of water from 72 mN/m to 30.8 mN/m (at 120 mg L-1) and achieved a critical, micelle concentration (CMC) value of 120 mg L-1. (C) 2008 Published by Elsevier Ltd.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">16</style></issue><work-type><style face="normal" font="default" size="100%">Article</style></work-type><custom3><style face="normal" font="default" size="100%">Foreign</style></custom3><custom4><style face="normal" font="default" size="100%">4.917</style></custom4></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Pal, Moumita P.</style></author><author><style face="normal" font="default" size="100%">Vaidya, Bhalchandra K.</style></author><author><style face="normal" font="default" size="100%">Desai, Kiran M.</style></author><author><style face="normal" font="default" size="100%">Joshi, Renuka M.</style></author><author><style face="normal" font="default" size="100%">Nene, Sanjay N.</style></author><author><style face="normal" font="default" size="100%">Kulkarni, Bhaskar D.</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Media optimization for biosurfactant production by rhodococcus erythropolis MTCC 2794: artificial intelligence versus a statistical approach</style></title><secondary-title><style face="normal" font="default" size="100%">Journal of Industrial Microbiology &amp; Biotechnology</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Artificial neural network</style></keyword><keyword><style  face="normal" font="default" size="100%">Biosurfactant</style></keyword><keyword><style  face="normal" font="default" size="100%">Genetic algorithm</style></keyword><keyword><style  face="normal" font="default" size="100%">Media optimization</style></keyword><keyword><style  face="normal" font="default" size="100%">Response surface methodology</style></keyword><keyword><style  face="normal" font="default" size="100%">Rhodococcus</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2009</style></year><pub-dates><date><style  face="normal" font="default" size="100%">MAY</style></date></pub-dates></dates><number><style face="normal" font="default" size="100%">5</style></number><publisher><style face="normal" font="default" size="100%">SPRINGER HEIDELBERG</style></publisher><pub-location><style face="normal" font="default" size="100%">TIERGARTENSTRASSE 17, D-69121 HEIDELBERG, GERMANY</style></pub-location><volume><style face="normal" font="default" size="100%">36</style></volume><pages><style face="normal" font="default" size="100%">747-756</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;This paper entails a comprehensive study on production of a biosurfactant from Rhodococcus erythropolis MTCC 2794. Two optimization techniques-(1) artificial neural network (ANN) coupled with genetic algorithm (GA) and (2) response surface methodology (RSM)-were used for media optimization in order to enhance the biosurfactant yield by Rhodococcus erythropolis MTCC 2794. ANN and RSM models were developed, incorporating the quantity of four medium components (sucrose, yeast extract, meat peptone, and toluene) as independent input variables and biosurfactant yield [calculated in terms of percent emulsification index (% EI24)] as output variable. ANN-GA and RSM were compared for their predictive and generalization ability using a separate data set of 16 experiments, for which the average quadratic errors were similar to 3 and similar to 6%, respectively. ANN-GA was found to be more accurate and consistent in predicting optimized conditions and maximum yield than RSM. For the ANN-GA model, the values of correlation coefficient and average quadratic error were similar to 0.99 and similar to 3%, respectively. It was also shown that ANN-based models could be used accurately for sensitivity analysis. ANN-GA-optimized media gave about a 3.5-fold enhancement in biosurfactant yield.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">5</style></issue><custom3><style face="normal" font="default" size="100%">&lt;p&gt;Foreign&lt;/p&gt;</style></custom3><custom4><style face="normal" font="default" size="100%">&lt;p&gt;2.416&lt;/p&gt;</style></custom4></record></records></xml>