A Comparison of “Neural Networks and Multiple Linear Regressions” Models to Describe the Rejection of Micropollutants by Membranes

Abstract

A rejection process of organic compounds by nanofiltration and reverse osmosis membranes was modelled using the artificial neural networks. Three feed-forward neural networks based on quantitative structure-activity relationship (QSAR-NN models) characterised by a similar structure (twelve neurons for QSAR-NN<sub>1</sub>, QSAR-NN<sub>2</sub>, and QSAR-NN<sub>3</sub> in the input layer, one hidden layer and one neuron in the output layer), were constructed with the aim of predicting the rejection of organic compounds. A set of 1394 data points for QSAR-NN<sub>1</sub>, 980 data points for QSAR-NN<sub>2</sub>, and 436 data points for QSAR-NN<sub>3</sub> were used to construct the neural networks. Good agreements between the predicted and experimental rejections were obtained by QSAR-NN models (the correlation coefficient for the total dataset were 0.9191 for QSAR-NN<sub>1</sub>, 0.9338 for QSAR-NN<sub>2</sub>, and 0.9709 for QSAR-NN<sub>3</sub>). Comparison between the feed-forward neural networks and multiple linear regressions based on quantitative structure-activity relationship “QSAR-MLR” revealed the superiority of the QSAR-NN models (the root mean squared errors for the total dataset for the QSAR-NN models were 10.6517 % for QSAR-NN<sub>1</sub>, 9.1991 % for QSAR-NN<sub>2</sub>, and 5.8869 % for QSAR-NN<sub>3</sub>, and for QSAR-MLR models they were 20.1865 % for QSAR-MLR<sub>1</sub>, 19.3815 % for QSAR-MLR<sub>2</sub>, and 16.2062 % for QSAR-MLR<sub>3</sub>).

Computing Techniques for Modeling the Retention of Polar Pharmaceutical Active Compounds by Membranes

“…The two extreme layers correspond to the input layer which receives its inputs from the outside environment on the one hand and to the output layer which provides the result of the treatments carried out on the other hand. The intermediate layers are called hidden layers, their number is variable (Ammi et al 2020;Khaouane et al 2013;Meshram et al 2020). The feedforward neural networks can be given as follow for the prediction of the polar pharmaceutical With: i (i = 1: n=13) is the number of neurons in the input layer, j (j = 1:m) is the number of neurons in the output layer, k (k = 1) is the number of neurons in the output layer, 𝑥 𝑖 is the inputs of the FNN,…”

“…Ratio "RER" provided by Viscarra Rossel: excellent predictions (RER and RPD > 2.5); good (RER and RPD of 2.0 to 2.5); approximate quantitative predictions (RER and RPD of 1.8 to 2.0); possibility to distinguish high and low values (RER and RPD of 1.4 to 1.8); and unsuccessful (RER and RPD < 1.40) (Ammi et al 2020;Rossel et al 2006).…”

An artificial intelligence approach for modeling the rejection of anti-inflammatory drugs by nanofiltration and reverse osmosis membranes using kernel support vector machine and neural networks

“…On the other hand, we adopted the five-level interpretations of Residual Predictive Deviation "RPD" and Range Error Ratio "RER" provided by Viscarra Rossel: excellent predictions (RPD and RER > 2.5); good (RPD and RER of 2.0 to 2.5); approximate quantitative predictions (RPD and RER of 1.8 to 2.0); possibility to distinguish high and low values (RPD and RER of 1.4 to 1.8); and unsuccessful (RPD and RER < 1.40) [22,41]. The RPD and RER of the ANNs and SVM models are higher than 2.5 (RPD = 8.4808% and RER = 54.5525% for ANN; RPD = 6.8644% and RER = 15.3455% for SVM) for the total phase.…”

“…However, there have been few models of ANNs due to the complexity of mechanisms to predict the rejection of organic compounds by NF/RO [15][16][17][18][19][20][21][22]. There is no modeling study for the rejection of organic compounds by NF/RO membranes using SVMs.…”

Application of artificial neural network (ANN-MLP) for the prediction of fouling resistance in heat exchanger to MgO-water and CuO-water nanofluids

“…(Sarafraz & Hormozi 2014) shown that fouling resistance represents the linear/asymptotic behavior with time in force convective and nucleate boiling heat transfer regions, by studying experimentally the influence of different operating parameters such as dilute concentrations of nanofluid (by weight), heat flux and mass flux on the single phase, two-phase flow-boiling and particulate fouling resistance of CuO/EG nanofluid. Artificial Neural Network (ANN) technique has been used in many scientific domains such as (solar, nucleate boiling, solubility of solid drugs, methodology, Biofuels, Micropollutants) (Laidi and Hanini 2013;Mohamedi et al 2015;Rezrazi et al 2016;Abdallahelhadj et al 2017;Ammi et al 2020;Belmadani et al 2020), and it has proven its reliability and robustness by establishing the relationship between the variables without considering the detailed physical process. This feature of ANN encourages its use for predicting of thermophysical properties of nanofluids.…”