Journal Article
Artificial neural network (ANN) approach for modelling of arsenic (III) biosorption from aqueous solution by living cells of Bacillus cereus biomass
[2011]
Giri, A.K.;
Patel, R.K.;
Mahapatra, S.S.;
Artificial neural network (ANN) approach for modelling of arsenic (III) biosorption from aqueous solution by living cells of Bacillus cereus biomass
2011
Giri, A.K.; Patel, R.K.; Mahapatra, S.S.
http://dx.doi.org/10.1016/j.cej.2011.09.111
In this work, an intensive study has been made on the removal efficiency of As (III) from aqueous solution by biosorption of living Bacillus cereus biomass. Bacillus cereus biomass is characterized using SEM-EDX and FTIR. The effect of various parameters such as initial concentration of arsenic (III), biosorbent dosage, temperature and contact time is studied systematically. The maximum biosorption of arsenic (III) is found to be 85.24% at pH 7.5, equilibrium time of 90min by using biosorbent of 6g/L and initial concentration of 1mg/L of arsenic (III) solution. The data collected from laboratory scale experimental set up is used to train a back propagation (BP) learning algorithm having 4-7-1 architecture. The model uses tangent sigmoid transfer function at input to hidden layer whereas a linear transfer function is used at output layer. The data is divided into training (75%) and testing (25%) sets. The network is found to be working satisfactorily as absolute relative percentage error of 0.567 during training phase. Comparison between the model results and experimental data gives a high degree of correlation (R²=0.986) indicating that the model is able to predict the sorption efficiency with reasonable accuracy.
[Chemical engineering journal]
2015/US/US2015_2.rdf
In this work, an intensive study has been made on the removal efficiency of As (III) from aqueous solution by biosorption of living Bacillus cereus biomass. Bacillus cereus biomass is characterized using SEM-EDX and FTIR. The effect of various parameters such as initial concentration of arsenic (III), biosorbent dosage, temperature and contact time is studied systematically. The maximum biosorption of arsenic (III) is found to be 85.24% at pH 7.5, equilibrium time of 90min by using biosorbent of 6g/L and initial concentration of 1mg/L of arsenic (III) solution. The data collected from laboratory scale experimental set up is used to train a back propagation (BP) learning algorithm having 4-7-1 architecture. The model uses tangent sigmoid transfer function at input to hidden layer whereas a linear transfer function is used at output layer. The data is divided into training (75%) and testing (25%) sets. The network is found to be working satisfactorily as absolute relative percentage error of 0.567 during training phase. Comparison between the model results and experimental data gives a high degree of correlation (R²=0.986) indicating that the model is able to predict the sorption efficiency with reasonable accuracy.
