Artificial Neural Network Genetic Algorithm Research Articles

Evaluating the apparent shear stress in prismatic compound channels using the Genetic Algorithm based on Multi-Layer Perceptron: A comparative study

Apparent shear stress acting on a vertical interface between the main channel and floodplain in a compound channel is used to quantify the momentum transfer between these sub-areas of a cross section. In order to simulate the apparent shear stress, two soft computing techniques, including the Genetic Algorithm-Artificial Neural Network (GA-ANN) and Genetic Programming (GP) along with Multiple Linear Regression (MLR) were used. The proposed GA-ANN is a novel self-hidden layer neuron adjustable hybrid method made by combining the Genetic Algorithm (GA) with the Multi-Layer Perceptron Artificial Neural Network (MLP-ANN) method. In order to find the optimum condition of the methods considered in modeling apparent shear stress, various input combinations, fitness functions, transfer functions (for the GAA method), and mathematical functions (for the GP method) were investigated. Finally, the results of the optimum GAA and GP methods were compared with the MLR as a basic method. The results show that the hybrid GAA method with RMSE of 0.5326 outperformed the GP method with RMSE of 0.6651. In addition, the results indicate that both GAA and GP methods performed significantly better than MLR with RMSE of 1.5409 in simulating apparent shear stress in symmetric compound channels.

Modeling and Optimizing a New Culture Medium for In Vitro Rooting of G\xd7N15 Prunus Rootstock using Artificial Neural Network-Genetic Algorithm

The main aim of the present investigation is modeling and optimization of a new culture medium for in vitro rooting of G×N15 rootstock using an artificial neural network-genetic algorithm (ANN-GA). Six experiments for assessing different media culture, various concentrations of Indole – 3- butyric acid, different concentrations of Thiamine and Fe-EDDHA were designed. The effects of five ionic macronutrients (NH4+, NO3−, Ca2+, K+ and Cl−) on five growth parameters [root number (RN), root length (RL), root percentage (R%), fresh (FW) and dry weight (DW)] were evaluated using the ANN-GA method. The R2 correlation values of 0.88, 0.88, 0.98, 0.94 and 0.87 between observed and predicted values were acquired for all five growth parameters, respectively. The ANN-GA results indicated that among the input variables, K+ (7.6) and NH4+ (4.4), K+ (7.7) and Ca2+ (2.8), K+ (36.7) and NH4+ (4.3), K+ (14.7) and NH4+ (4.4) and K+ (7.6) and NH4+ (4.3) had the highest values of variable sensitivity ratio (VSR) in the data set, for RN, RL, R%, FW and DW, respectively. ANN-GA optimized LS medium for G×N15 rooting contained optimized amounts of 1 mg L−1 IBA, 100, 150, or 200 mg L−1 Fe-EDDHA and 1.6 mg L−1 Thiamine. The efficiency of the optimized culture media was compared to other standard media for Prunus rooting and the results indicated that the optimized medium is more efficient than the others.

A Modified Back Propagation Artificial Neural Network Model Based on Genetic Algorithm to Predict the Flow Behavior of 5754 Aluminum Alloy.

In order to predict flow behavior and find the optimum hot working processing parameters for 5754 aluminum alloy, the experimental flow stress data obtained from the isothermal hot compression tests on a Gleeble-3500 thermo-simulation apparatus, with different strain rates (0.1–10 s–1) and temperatures (300–500 °C), were used to construct the constitutive models of the strain-compensation Arrhenius (SA) and back propagation (BP) artificial neural network (ANN). In addition, an optimized BP–ANN model based on the genetic algorithm (GA) was established. Furthermore, the predictability of the three models was evaluated by the statistical indicators, including the correlation coefficient (R) and average absolute relative error (AARE). The results showed that the R of the SA model, BP–ANN model, and ANN–GA model were 0.9918, 0.9929, and 0.9999, respectively, while the AARE of these models was found to be 3.2499–5.6774%, 0.0567–5.4436% and 0.0232–1.0485%, respectively. The prediction error of the SA model was high at 400 °C. It was more accurate to use the BP–ANN model to determine the flow behavior compared to the SA model. However, the BP–ANN model had more instability at 300 °C and a true strain in the range of 0.4–0.6. When compared with the SA model and BP–ANN model, the ANN–GA model had a more efficient and more accurate prediction ability during the whole deformation process. Furthermore, the dynamic softening characteristic was analyzed by the flow curves. All curves showed that 5754 aluminum alloy showed the typical rheological characteristics. The flow stress rose rapidly with increasing strain until it reached a peak. After this, the flow stress remained constant, which demonstrates a steady flow softening phenomenon. Besides, the flow stress and the required variables to reach the steady state deformation increased with increasing strain rate and decreasing temperature.

Removal of Congo Red from Aqueous Solution by Hydroxyapatite Nanoparticles Loaded on Zein as an Efficient and Green Adsorbent: Response Surface Methodology and Artificial Neural Network-Genetic Algorithm

This study is based on the application of hydroxyapatite nanoparticles loaded on Zein (Zein/nHAp) as an efficient adsorbent for the removal of Congo red from aqueous solutions. The properties of the adsorbent were characterized using various techniques including FT-IR, XRD, FE-SEM, and BET. The influence of five parameters such as pH, temperature, contact time, initial dye concentration, and adsorbent dosage on the removal percentage of the dye was investigated. The optimum conditions of 5.83, 34.32 °C, 5.20 min, 392.10 ppm, and 0.007 g were achieved for pH, temperature, contact time, initial dye concentration, and adsorbent dosage, respectively. The maximum removal percentage of 99.48% was obtained under the optimum condition that exhibited high adsorption potential of the used adsorbent. Central composite design (CCD) under response surface methodology and artificial neural network-genetic algorithm (ANN-GA) were utilized for optimization of parameters. Comparison of the results of the two models in terms of coefficient of determination (R2) and mean absolute percentage error confirmed the prediction potential of CCD and ANN-GA. Higher ability and accuracy of ANN-GA in prediction was found based on given results. The experimental equilibrium data were studied by Langmuir, Freundlich, Temkin and Dubinin-Radushkevic isotherm models and explored that the data well presented by Langmuir model with maximum adsorption capacity of 416.66 mg/g. The adsorption kinetic was well-fitted by the pseudo-second-order model. The thermodynamics of the adsorption displayed spontaneous and endothermic nature of the process. Regeneration investigation showed that Zein/nHAp can impressively be reused, indicating that the adsorbent was a promising one for the removal of Congo red from aqueous solution.

Ultrasound–assisted extraction optimization of phenolic compounds from Psidium guajava L. using artificial neural network-genetic algorithm

Artificial Neural Network-Genetic Algorithm (ANN-GA) was used in this work to model the extraction parameters using Ultrasound Assisted Extraction (UAE) in producing phenolic compounds of guava (Psidium guajava L.) leaves. The ANN-GA model was used to evaluate and predict the effect of frequency, temperature, time, and their interaction under optimum conditions. The controlled parameters were frequency (20-40 kHz), temperature (2535 °C), and sonication time (20-40 minutes). Furthermore, the input and output parameters were modeled by LM-back propagation ANN. The optimization variable was then determined by GA. ANN trial and error method was used to determine the bias, weight, and number of hidden layer nodes. The fitness function for optimization with GA used the bias and weight which were obtained from ANN. The prediction of total phenolic on guava leaves using the ANN model shows the mean absolute precentage error value is 13.07. Based on the experiment the optimum conditions were obtained at 40 kHz, 35°C,30 minutes and resulted 589.02 ppm. While ANN-GA model obtained optimum results at 39.79 kHz, 34.83°C, 20 min, then the mean absolute error optimization was 3.46. It can be concluded that ANN-GA model can be used for optimizing the phenolic yields of guava leaves.

Identifying Soil and Plant Nutrition Factors Affecting Yield in Irrigated Mature Pistachio Orchards

ABSTRACTThe main objective of this study was to evaluate the potential use of a hybrid Genetic Algorithm-Artificial Neural Network (GA–ANN) method for predicting pistachio yield and for identifying the determinant factors affecting pistachio yield in Rafsanjan region, Iran. A total of 142 pistachio orchards were selected randomly and soil samples were taken at three depths. Besides, water samples and leaves from branches without fruit were taken in each sampling point. Management information and pistachio yields were achieved by completing a questionnaire. Primarily, 58 variables affecting pistachio yield were measured, and then 26 out of them were selected by minimizing mean square error (MSE) using a feature selection (FS) method. The results showed that the accuracy of the method was acceptable. Furthermore, the sensitivity analysis showed that the main determinant features affecting the pistachio yield were the irrigation water amount, leaf phosphorus, soil soluble magnesium, electrical conductivity (EC), and leaf nitrogen.

An efficient simulation–neural network–genetic algorithm for flexible flow shops with sequence-dependent setup times, job deterioration and learning effects

This study presents an integrated approach based on artificial neural network (ANN), genetic algorithm (GA) and computer simulation to explore all the solution space in stochastic flexible flow shop with sequence-dependent setup times, job deterioration and learning effects. The objective of this study is minimizing total tardiness of jobs in the sequences. In this study, the outputs of ANN are inputted to GA and outputs of simulation model are inputted to ANN. We consider learning effects in this problem which means that workers become more experienced with the passage of time, and thus, the processing duration decreases. Deterioration of job means that processing time is a decreasing function of its execution start time. It is not possible to propose a mathematical optimization model for the stated problem; therefore, a simulation optimization approach based on ANN–GA is introduced for a relatively large problem. Finally, actual experiments are conducted to show the applicability of the proposed novel algorithm in finding near-optimal solutions with normal, uniform and exponential processing and setup times. This is the first study that presents an integrated intelligent approach for optimal solution of stochastic flexible flow shop problem with sequence-dependent setup times, job deterioration and learning effects in a real case study.

Optimization of HS-SPME Using Artificial Neural Network and Response Surface Methodology in Combination with Experimental Design for Determination of Volatile Components by Gas Chromatography-Mass Spectrometry in Korla Pear Juice

In this study, the effects of five fibers on volatile compounds of Korla pear (Pyrus bretschneideri rehd) juice were studied. Four main extraction parameters of headspace solid-phase micro-extraction, namely, sample amount, extraction temperature, extraction time, and salt addition, were optimized for the first time using response surface methodology (RSM) and artificial neural network-genetic algorithm (ANN-GA). The prediction and the generalization ability of RSM and ANN models using the same experimental design were compared. The absolute average deviations of the ANN and RSM models were 0.458 and 0.313, and the correlation coefficients were 0.927 and 0.978, respectively. These results indicated that 65-μm PDMS/DVB fiber is the best extraction fiber of SPME for the volatile compounds of Korla pear juice. The ANN model exhibited more accurate prediction and better generalization capabilities than the RSM model, and the optimum conditions obtained by GA were more accurate than those of RSM. The optimum sample amount, extraction temperature, extraction time, and salt addition were 5.33 g, 45 °C, 25 min, and 11.8% of the amount of SPME of the Korla pear juice sample, respectively. Under the optimum conditions, the content of nine volatile compounds, including propanoic acid ethyl ester, 1-hexanal, butanoic acid ethyl ester, 1-hexanol, (E)-2-hexenal, hexanoic acid ethyl ester, 2-hexenal, 1-nonanal, and acetic acid ethyl ester, was 3.37 ± 0.23 μg/g.

Robustness lake water level prediction using the search heuristic-based artificial intelligence methods

Lakes have a crucial role in the industrial, agricultural, environment, and drinking water fields. Accurate prediction of lake levels is one of the most important parameters in the reservoir management and lakeshore structure designing. The goal of the present study is to examine the robustness of two different Genetic Algorithm-based regression methods namely the Genetic Algorithm Artificial neural network (GAA) and the Genetic Programming (GP) by considering their performance in predicting the non-observed lakes. To do that, data collected from the four-year daily measurements of the Chahnimeh#1 lake in Eastern Iran were used for developing the GAA and GP models and after that, the performance of the considered models are examined to predict the lake water levels of an adjacent lake namely Chahnimeh#4 as the non-observed information. The results showed that both model has the ability to simulate adjacent lakes using the considered lake water levels for the training procedure. In addition, another goal is to develop simple, practical formulation for predicting the lake water level, So that, using the GP method, as the superior model, three different formulations are proposed in order to predict the one, three, and five days ahead lake water level, respectively.

A Quantitative Structure–Activity Relationship Study of Calpeptin (Calpain Inhibitor) as an Anticancer Agent

Calpeptin analogs show anticancer properties with inhibition of calpain. In this work, we applied a quantitative structure–activity relationship (QSAR) model on 34 calpeptin derivatives to select the most appropriate compound. QSAR was employed to generate the models and predict the more significant compounds through a series of calpeptin derivatives. The HyperChem, Gaussian 09, and Dragon software programs were used for geometry optimization of the molecules. The 2D and 3D molecular structures were drawn by ChemDraw (Ultra 16.0) and Chem3D (Pro16.0) software. The Unscrambler program was used for the analysis of data. Multiple linear regression (MLR‐MLR), partial least‐squares (MLR‐PLS1), principal component regression (MLR‐PCR), a genetic algorithm‐artificial neural networks (GA‐ANN), and a novel similarity analysis‐artificial neural network (SA‐ANN) method were used to create QSAR models. Among the three MLR models, MLR‐MLR provided better statistical parameters. The R2 and RMSE of the prediction were estimated as 0.8248 and 0.26, respectively. Nevertheless, the constructed model using GA‐ANN revealed the best statistical parameters among the studied methods (R2 test = 0.9643, RMSE test = 0.0155, R2 train = 0.9644, RMSE train = 0.0139). The GA‐ANN model is found to be the most favorable method among the statistical methods and can be employed for designing new calpeptin analogs as potent calpain inhibitors in cancer treatment.

Optimization of Bioactive Ingredient Extraction from Chinese Herbal Medicine Glycyrrhiza glabra: A Comparative Study of Three Optimization Models.

The ultraviolet spectrophotometric method is often used for determining the content of glycyrrhizic acid from Chinese herbal medicine Glycyrrhiza glabra. Based on the traditional single variable approach, four extraction parameters of ammonia concentration, ethanol concentration, circumfluence time, and liquid-solid ratio are adopted as the independent extraction variables. In the present work, central composite design of four factors and five levels is applied to design the extraction experiments. Subsequently, the prediction models of response surface methodology, artificial neural networks, and genetic algorithm-artificial neural networks are developed to analyze the obtained experimental data, while the genetic algorithm is utilized to find the optimal extraction parameters for the above well-established models. It is found that the optimization of extraction technology is presented as ammonia concentration 0.595%, ethanol concentration 58.45%, return time 2.5 h, and liquid-solid ratio 11.065 : 1. Under these conditions, the model predictive value is 381.24 mg, the experimental average value is 376.46 mg, and the expectation discrepancy is 4.78 mg. For the first time, a comparative study of these three approaches is conducted for the evaluation and optimization of the effects of the extraction independent variables. Furthermore, it is demonstrated that the combinational method of genetic algorithm and artificial neural networks provides a more reliable and more accurate strategy for design and optimization of glycyrrhizic acid extraction from Glycyrrhiza glabra.

Artificial Neural Network–Genetic Algorithm to Optimize Yin Rice Inoculation Fermentation Conditions for Improving Physico-chemical Characteristics

Artificial Neural Network–Genetic Algorithm to Optimize Yin Rice Inoculation Fermentation Conditions for Improving Physico-chemical Characteristics

Investigation of 2-nitrophenol solar degradation in the simultaneous presence of K2S2O8 and H2O2: Using experimental design and artificial neural network

In this study, the interaction effect of K2S2O8 (PDS) and H2O2 (as two powerful oxidants) was investigated on the solar degradation of 2-nitrophenol (2-NF) in the two systems, i.e. absence and presence of Ag/S/TiO2 photocatalyst. Experiments were designed based on the central composite design, and two methods of response surface methodology (RSM) and artificial neural network (ANN) were developed for modeling of the systems. Concentrations of PDS and H2O2 were considered as independent variables and 2-NF degradation efficiency was selected as the response. It was revealed that the predictive capacity of ANN model is more than RSM model according to their corresponding R2, R2adj, RMS, MAE, and AAD values. Therefore, ANN model was utilized to analyze the effects of the independent variables. Moreover, it was found that, by increasing the amount of either PDS or H2O2, less amount of the other oxidant was required to reach the highest degradation efficiency which shows the contributive effect of the oxidants on each other. By adding Ag/S/TiO2 visible-light-sensitive photocatalyst to the solution containing PDS and H2O2, a significant enhancement in the 2-NF degradation efficiency was observed. Using an ANN-genetic algorithm (ANN-GA) approach, the values of 172.1 mg/l and 80.9 mg/l were respectively obtained as optimum concentrations for PDS and H2O2 (in the presence of the photocatalyst). Under this condition, 2-NF degradation efficiency was predicted to be 96% after only 45 min of solar light irradiation that is in a good agreement with the actual degradation efficiency of 97.1% obtained at the optimum concentrations. In addition, the relative importance of the independent variables was studied using Garson method and it was found that PDS had more impact on the response in comparison with H2O2.

Mathematical Modeling and Optimizing of in Vitro Hormonal Combination for G × N15 Vegetative Rootstock Proliferation Using Artificial Neural Network-Genetic Algorithm (ANN-GA).

The efficiency of a hybrid systems method which combined artificial neural networks (ANNs) as a modeling tool and genetic algorithms (GAs) as an optimizing method for input variables used in ANN modeling was assessed. Hence, as a new technique, it was applied for the prediction and optimization of the plant hormones concentrations and combinations for in vitro proliferation of Garnem (G × N15) rootstock as a case study. Optimizing hormones combination was surveyed by modeling the effects of various concentrations of cytokinin–auxin, i.e., BAP, KIN, TDZ, IBA, and NAA combinations (inputs) on four growth parameters (outputs), i.e., micro-shoots number per explant, length of micro-shoots, developed callus weight (CW) and the quality index (QI) of plantlets. Calculation of statistical values such as R2 (coefficient of determination) related to the accuracy of ANN-GA models showed a considerably higher prediction accuracy for ANN models, i.e., micro-shoots number: R2 = 0.81, length of micro-shoots: R2 = 0.87, CW: R2 = 0.88, QI: R2 = 0.87. According to the results, among the input variables, BAP (19.3), KIN (9.64), and IBA (2.63) showed the highest values of variable sensitivity ratio for proliferation rate. The GA showed that media containing 1.02 mg/l BAP in combination with 0.098 mg/l IBA could lead to the optimal proliferation rate (10.53) for G × N15 rootstock. Another objective of the present study was to compare the performance of predicted and optimized cytokinin–auxin combination with the best optimized obtained concentrations of our other experiments. Considering three growth parameters (length of micro-shoots, micro-shoots number, and proliferation rate), the last treatment was found to be superior to the rest of treatments for G × N15 rootstock in vitro multiplication. Very little difference between the ANN predicted and experimental data confirmed high capability of ANN-GA method in predicting new optimized protocols for plant in vitro propagation.

Determining optimal combination of roller compacted concrete pavement mixture containing recycled asphalt pavement and crumb rubber using hybrid artificial neural network–genetic algorithm method considering energy absorbency approach

The present study investigates the effectiveness of evolutionary algorithms such as genetic algorithm (GA) evolved neural network in estimating roller compacted concrete pavement (RCCP) characteristics including flexural and compressive strength of RCC and also energy absorbency of mixes with different compositions. A real coded GA was implemented as training algorithm of feed forward neural network to simulate the models. The genetic operators were carefully selected to optimize the neural network, avoiding premature convergence and permutation problems. To evaluate the performance of the genetic algorithm neural network model, Nash-Sutcliffe efficiency criterion was employed and also utilized as fitness function for genetic algorithm which is a different approach for fitting in this area. The results showed that the GA-based neural network model gives a superior modeling. The well-trained neural network can be used as a useful tool for modeling RCC specifications.

Photocatalytic activity of g-C3N4: An empirical kinetic model, optimization by neuro-genetic approach and identification of intermediates

The polymeric graphitic carbon nitride (g-C3N4) was synthesized via direct heating of melamine precursor. The obtained solid was characterized by X-ray diffraction (XRD), scanning electron microscopy (SEM), UV–vis diffuse reflection spectra (DRS) and Fourier transform infrared (FT-IR). The photocatalytic performance of the synthesized g-C3N4 was investigated by photodegradation of Reactive Black 5 as a model organic pollutant. The removal efficiency of dye over g-C3N4 was yielded 95% after 120min. The effect of operational parameters including pH, catalyst dosage and dye initial concentration was investigated. An artificial neural network-genetic algorithm approach was utilized to find the optimal conditions for achieving maximum degradation efficiency. A nonlinear empirical kinetic model was also developed to predict the first order rate constant (kapp). The photocatalytic degradation intermediates were identified using GC-MS and a probable degradation pathway was proposed.

Optimization of slot geometry in shock wave boundary layer interaction phenomenon by using CFD–ANN–GA cycle

Slot is one of the measures to control the Shock Wave–Boundary Layer Interaction (SBLI) used to avoid strong interference of shock waves with the boundary layer in supersonic flows. In this control measure, the Height of Triple Point (HTP) of λ shock significantly increases, compared to the one without controller, and cause a decline in shock power and pressure drops rate. In this paper, the main focus is on optimization of slot geometry as an influential parameter on the structure of the shock and flow characteristics by using Genetic Algorithm (GA). The averaged implicit Navier–Stokes equations and two equation standard k–ω turbulence models for the numerical simulation of the flow field have been used. The optimization problem is formulated in term of one objective function, namely, height of triple point maximization. Artificial neural network with two hidden layers has been used to achieve objective function based on the numerical simulation of the flow field data base. Root Mean Square Error (RMSE) was calculated for comparison and selecting the best algorithm in sequential steps. In order to simulate and compare the results with data obtained from experimental tests, the Cambridge University's wind tunnel tests and geometry have been used as the base design. The study demonstrates that, the HTP for optimized slot geometry is about 7.6 percentages more than base design.

Enhanced production of glutaminase free L-asparaginase II by Bacillus subtilis WB800N through media optimization

We studied the crucial components which elevate the expression of recombinant novel glutaminase free L-asparaginase II (rL-asp II) from Bacillus subtilis WB800N. The Plackett-Burman tool identified sucrose, NH4Cl, NaH2-PO4 and MgSO4 as the significant influencing factors (p<0.05). Further investigations showed that artificial neural network-genetic algorithm (ANN-GA) was more effective than central composite design (CCD) in optimizing the influencing factors. The maximum rL-asp II expression was found to be 389.56 IU/ml and 525.98 IU/ml using CCD (R2=90.4%) and ANN-GA (R2=96.2%), respectively. The validation experiments were carried out in a 3 L batch bioreactor where kinetic modelling of the obtained data was done. The rL-asp II expressed effectively inhibiting the polyacrylamide formation in vitro where no solidification was observed, when 2ml of purified rL-asp II used even after 60 min of incubation. This is the first study to report highest production of rL-asp II in B. subtilis WB800N (525.98 IU/ml) till date by combining statistical designs with consecutive intermittent addition of IPTG in batch reactor.

Xylanase production from Thermomyces lanuginosus VAPS-24 using low cost agro-industrial residues via hybrid optimization tools and its potential use for saccharification

The xylanase production from Thermomyces lanuginosus VAPS-24 has been optimized using OFAT (One factor at a time) approach using agro-industrial substrates. Further, central composite design (CCD) has been employed to optimize various process parameters such as temperature (45–55°C), carbon source concentration (1.5–2.5%), fermentation time (72–120h) and production medium pH (6−8). Maximum xylanase yield after RSM optimization was approximately double (119.91±2.53UmL−1) than un-optimized conditions (61.09±0.91UmL−1). Several hybrid statistical tools such as Genetic Algorithm-Response Surface Methodology (GA-RSM), Artificial Neural Network (ANN), Genetic Algorithm-Artificial Neural Network (GA-ANN) were employed to obtain more optimized process parameters to maximize the xylanase production and observed an increase of 10.50% xylanase production (132.51±3.27UmL−1) as compared to RSM response (119.91±2.53UmL−1). The various pretreated and untreated agricultural residues were subjected to saccharification by using crude xylanase in which the pretreated rice straw yielded maximum fermentable sugars 126.89mgg−1.

Prediction of thermodynamic properties of polyvinylpyrrolidone solutions by artificial neural networks coupled with genetic algorithm

ABSTRACTIn the present study, the artificial neural networks coupled with the genetic algorithm (ANN–GA) models were used to predict the thermodynamic properties of polyvinylpyrrolidone (PVP) solutions in water and ethanol at various temperatures, mass fractions, and molecular weights of polymer. The genetic algorithm (GA) was used to find the best weights and biases of the network and improve the performance of ANNs. The proposed model was composed of three input variables including the temperature of the solution, the mass fraction, and molecular weight of the polymer. Density, viscosity, and surface tension of PVP solutions with various molecular weights (10,000, 25,000, and 40,000) in water and ethanol have been measured in the temperature range 20–55°C and various mass fractions of polymer. The ANN–GA models were trained by the experimental datasets and the prediction of density, surface tension, and viscosity of PVP solutions was performed using these models. The predicted values were compared with the experimental ones and the mean absolute relative error was less than 0.5% for the density and surface tension and about 3% for the viscosity of solutions.