جستجوی مقالات مرتبط با کلیدواژه « الگوریتم ژنتیک » در نشریات گروه « علوم پایه »

For the last 50 years, activities like urbanization, industrialization and population growth, make air as a significant inseparable part of our life. Air pollution can be defined as the presence of chemicals or toxic compounds in the air to extent that they pose a health risk. Emissions from cars, plant chemicals, dust, pollen and mold spores are introduced as particulate matter (PM). The World Health Organization reported that ambient air pollution causes 4.2 million deaths from strokes, heart disease, lung cancer and chronic respiratory diseases. Of the various pollutants affecting air quality, particulate matter smaller than 2.5 microns is the major air pollution problem (Ścibor et al., 2020). As well, there is growing evidence of the effects of PM10 and PM2.5 on cardiovascular disease (CVD) and respiratory disease (DR).Forecasting air pollutants provides an opportunity to determine the intensity of air pollution in different areas and prevent irreversible impacts. In addition, these models also allow decision-makers to make the right decisions and prepare for the prevention or control of the PMs in the future. Some of the models used in air pollution forecasting studies are auto-regressive Integrated Moving Average (ARIMA), artificial neural network (ANN), Community Multiscale Air Quality Model (CMAQ), the Weather Research and Forecasting (WRF) model coupled with Chemistry (WRF-CHEM), Fuzzy models, grey model and/or hybrid models. ANN has been used extensively by scientists to provide rapid and parsimonious solutions to mitigate the negative impacts of air pollution worldwide. Neural networks, as an alternative, have been successfully used in air pollution forecasting and have produced accurate results in time series data. Different types of noise and nonlinear structure were present in the data. Hybrid modeling approaches have a wide variety of applications in which numerous methods or attributes are merged to create a more sophisticated model with superior performance in certain scenarios.Urmia is one of Iran's most polluted cities, owing to continuous traffic and traffic congestion, growing CO2 and PM levels, and a lack of knowledge on regulating and locating industrial manufacturing units. Dust from Iraq affects the region, as well as inversion, which occurs 90 days a year, are instances of region-specific air pollution. In addition, the drying of Urmia Lake, which can result in salt storms, is one of the critical concerns that will lead to significant pollution in the near future.In this study, ANN-GA with missing data imputation was used to predict PM2.5 in Urmia, Iran, in the short-term to demonstrate how data-gap filling and preprocessing methods could improve hybrid models' performance.

The concentrations of air pollutants (carbon monoxide, nitrogen dioxide, and sulfur dioxide) as well as meteorological data (temperature, relative humidity, and wind velocity) were used as inputs in this research to predict PM2.5. Air pollution concentrationsand meteorological data over a two-year period were obtained from Monitoring Station No. 3, Urmia municipality, and Iran's meteorology website (Data.irimo.ir).The data was then preprocessed with the Savitsky-Golay filter before being fed into the ANN and ANN-GA networks. Data gaps and imputed data (KNN/SPLINE method) were used as input in each network, and the results were compared.In this study, a single system contains two hidden layers and one output layer. The time series method was used to introduce the data to the network. The data was divided into three parts. 70% of the data is used for training, 15% for validation, and 15% for testing. Data import scenarios were defined in two ways. The first scenario used no imputation, while the second used SPLINE and KNN to fill in data gaps. As a transfer function, a sigmoid (logsig) layer was used for hidden layers, and a linear layer (Purelin) was used for the output layer. The Levenberg-Marquardt algorithm was chosen as the learning algorithm based on the type of problem and the speed of convergence. To improve the results, the number of neurons, repetition parameters, number of permitted evaluations, Levenberg algorithm parameters, and reliability were all adjusted through a trial-and-error process.New ANN-GA network was used in this study and GA was used as a training function. After introducing the data as a time series and selecting the amount of data for each episode of learning, evaluation, and testing, the structure and number of networklayers were created with the "newff" function. The main difference is that the genetic learning process was used instead of the "train" function. It's worth noting that the network layer characteristics in both methods were the same. To learn how to complete the process, the new learning function requires several side processes, including cost function creation, selection, intersection, and mutation. Three methods of roulette selection, tournament selection and random were used in the selection process. To introduce the cost function, weights were taken from those created by the "newff" function. Different values were assigned to the initial population variables, maximum mutation number, and selection pressure coefficient by trial-and-error method. Moreover, two data import scenarios were defined.

Forecasting methods have been considered an important tool in research on air pollution. Among the various pollutants that influence air quality, particles with an aerodynamic diameter of less than 2.5 micrometers (PM2.5) are one of the key issues in air pollution control management. In this study, a model for predicting future concentrations of PM2.5 was developed by the Hybrid Network (ANN-GA). Two methods of data imputation (KNN and SPLINE) were used to minimize training issues and improve network accuracy. PM10, PM2.5, nitrogen dioxide, oxide, carbon monoxide, and weather data were used for predictions. The results show that multi-line neural networks are relatively efficient for predictive purposes but lack sufficient accuracy to predict. The ANN network produced MSE error of 0.023 and coherence coefficient of R 0.543 only with data gap filling methods. In order to improve R and reduce network errors, a genetic algorithm was used in combination with a multi-layer neural network (ANN-GA). As the results showed, MSE and R for hybrid networks (ANN-GA) were improved (R=0.91 and MSE=0.001). In addition, compared to ANN, the R increased by 40 percent and the MSE improved by 95 percent. Thus, it can be concluded that ANN-GA can be used as a powerful and reliable tool for predicting air pollution.

The most important sources of risk that farmers face include economic risks such as fluctuations in the price of raw materials needed by farmers, including seeds and chemical fertilizers, as well as social risks such as theft from farms and agricultural machinery and natural hazards such as pests and diseases of crops. (Hosseini et al., 2021). The agricultural sector has special capabilities due to its continuous and sustainable economic growth, food security, return on investment, currency appreciation, lower valuation, creating social justice in comparison with other economic sectors of the country, so that it has been able to play a very significant role in the economic field. Have a country (Mousavi and Khosravi Pour, 2020). In recent years, due to the growing population and the growing need for food and clothing, the initial human attitude to nature, which was a friendly attitude, gave way to one-sided interaction with nature (Vahedi et al., 2021). Therefore, chemical fertilizers, pesticides, hormonal products and antibiotics entered the agricultural sector and by using the improved cultivars, great successes were achieved in increasing the production of agricultural products to meet the growing demand for food (Azami et al., 2019). Therefore, considering the importance of organic products in Saveh, in this study, the effective factors on risk management determinants of organic products in Saveh using the method of genetic function approximation and logit algorithm to determine what factors affect the risk of products Organic in Saveh city in changing the pattern of cultivation of environmental products. Nowadays, considering that any agricultural activity faces risk due to the existence of harmful natural events, planning to reduce the amount of risk and increase the security of investment in this sector is essential. Therefore, identifying important factors and determinants affecting farmers' risk management is of particular importance. The aim of this study was to identify the factors affecting the risk of pomegranate growers in Saveh city with the focus on changing the pattern of environmental cultivation using the approximation method of algorithm function and logit regression model. Statistical sample was collected using random sampling method from 130 pomegranate growers in the city in 2020 . Education factors, consumption of animal manure, interest in organic farming, type of tree breed, reduce soil and water pollution, working capital and insurance of pomegranate crop have been positively related to the risk of Kashmir pomegranate growers.

- Statistical community and required data The area under irrigated and rainfed crops of Saveh plain is estimated at 62,540 hectares, which varies in terms of rainfall under different climatic conditions. The statistical population of the present study includes all organic farmers in Saveh region who cultivate selected crops such as irrigated wheat, barley, cantaloupe, pomegranate and grapes in their Faryab or irrigated lands. Pomegranate is considered as a strategic product and index of Saveh city as the center of world production and in terms of the area under pomegranate cultivation, Saveh city is the second province in the country, but in terms of production per unit area and quality, it has the first place. The statistical population includes 130 Saveh pomegranate producers and the statistical sample was extracted from 130 organic products of Saveh (in 1399) using simple random sampling method. Data and information related to the level of cultivation of organic products in Saveh city were collected from the region. In this study, the factors affecting the risk of Saveh organic products have been predicted using the functional approximation of genetic algorithm and Logit, which is briefly described in the method of genetic function approximation algorithm. The genetic algorithm is inspired by Darwin's genetics and evolutionary theory and is based on the survival of the fittest or natural selection. A common application of genetic algorithms is to use it as an optimization function. The algorithm operates on a range of disciplines called populations, and this population evolves and is searched for this purpose. According to the GFA model, a search criterion is performed for each field. Three corresponding operators, namely selection, mixing, and mutation, are executed. New members are scored according to the fit criteria. In GFA, scoring criteria for models are based on the quality of regression fitted to the data. Election opportunities must be added to each new member and re-evaluated for the population. This method continues for a certain number of generations until convergence is achieved (Samuel et al., 2015). Below each of the three operators is examined.

In the agricultural sector, there are natural hazards (drought, hail, etc.), social (theft) and economic (price fluctuations). Therefore, the producers of this sector are forced to allocate resources optimally in more uncertain conditions and environments than other economic sectors. Considering the importance of organic products in Saveh and the region, in this study, the effective factors on risk management determinants of organic products in order to change the pattern of environmental cultivation in Saveh city using the method of genetic function approximation and logit algorithm. Based on the results, education variables, animal manure consumption, market knowledge of organic produce, natural disaster (drought and frost), interest in organic farming, price fluctuations and stability, tree species, soil and water pollution reduction, working capital Organic crop insurance and reduction of farmer income from organic crop cultivation Factors affecting the risk of Saveh organic products can be mentioned. Among the effective factors of education, use of animal manure, interest in organic farming, tree species, reduction of soil and water pollution, working capital and crop insurance have a positive relationship with the risk of Saveh organic products, among which working capital (savings) is effective. Has been more positive on farmers' risk. Also, the components of not knowing the market of organic products, the cause of heat and frost, price fluctuations and its instability and reducing the income of organic farmers have had a negative impact on risk. The results obtained from the logit model estimation also showed that education factor, market knowledge of organic product, interest in organic farming and working capital have become significant. Among the components of education, interest and working capital have a positive effect on pomegranate risk management. In this regard, it is suggested that in order to reduce the risk management of pomegranate growers, the government should intervene in the management of the agricultural products market and increase the insurance of agricultural products, and reduce the price differences to the final consumer between pomegranate growers to a minimum. Organic farming and working capital reduced risk management for organic pomegranates.

Accurate and correct identification of vessels moving in the waters from a distance is important in many ways. Having information type of vessels more correct decisions on how to deal with them. The sounds emitted by the vessels can be distinguished from each other and it is possible to identify the vessels by their sound. Therefore, in this study, the vessels have been classified based on their weight and the sound emitted by them. In the present study, the characteristics of each of the sounds recorded the vessels were extracted using the Mel-Frequency Cepstrum Coefficients (MFCC) method, and the ability of the artificial neural network and its hybrids with the Genetic Algorithm (ANN-GA) and the Imperialist Competitive Algorithm (ANN-ICA) The results showed that artificial neural network feed forward back propagation (BP-FF) with learning functions Levenberg-Marquardt (LM), Bayesian (BR) and Resilient Backpropagation (RP) has an accuracy of 86, 96 and 82 percent respectively in assigning the features of each vessels to them. Also, ANN-GA and ANN-ICA networks showed classification accuracy equal to 94% and 77%, respectively. Finally, it can be concluded that the Artificial Neural Network with the Bayesian learning function has the ability to acceptably classify the sounds emitted the vessels and can be used in marine and military applications.

Multivariate time series data, often, modeled using vector autoregressive moving average (VARMA) model. But presence of outliers can violates the stationary assumption and may lead to wrong modeling, biased estimation of parameters and inaccurate prediction. Thus, detection of these points and how to deal properly with them, especially in relation to modeling and parameter estimation of VARMA model is necessary. By detecting outliers, their effect can be eliminated over time and we obtain the modified data. Using this modified data, the proper estimates of the VARMA model are obtained which have the least effect on the outliers. On the other hand, detect of outliers is important in finding an external event over time. For example, by finding outliers in river water monitoring data, flood times can be obtained. The parameter estimation of VAR model is less time consuming than VARMA. On the other hand, under condition of invertibility, VARMA models could be approximated by VAR(p) for large p. Therefore, we use this model to fit and investigate the data generated from VARMA models that contaminated by outliers. Multivariate observations of time series may be contaminated with different types of outliers. However, the effect of different types of outliers in multivariate and univariate case is different, and this observation must be assessed by multivariate approach. In this research, we use a Genetic Algorithm (GA) to develop a procedure for detecting different types of outliers (additive, innovation, level shift and temporary change outliers) in a multivariate time series. GA detects outlier location which minimizes Akaike-like Information Criterion (AIC) and we try to "minimize the number of outliers" and "maximize the likelihood function".  GA is a numerical optimization algorithm whose idea is based on natural selection and natural genetics. This algorithm does not require strong assumptions to obtain the optimal value of a function and has the ability to search for the optimal solution from a space with several local optimal. That is, for example, if a function has several relative maxima, GA finds the absolute maximum of this function as well. For minimization of a function, GA operates by first generating, at random or optionally, several minimal solutions to the function that this set of solutions called the initial population and each solution as a chromosome. Then, using reproductive operators, we combine chromosomes and make a jump into them. If the function of newly produced chromosomes is lower than the previous chromosomes, these chromosomes can be added to the initial population or replaced with chromosomes with less function in this population. This process is repeated until convergence occurs or the end number of itteration obtained. Furthermore, we introduce another method of detecting outliers, the Tsay Pena and Pankratz (TPP) method. TPP uses some test statistics based on outliers size and VAR parameters. This method detects outliers in three stages. In stage I, it detects one by one outliers and remove their effects. Iteration done until no outlier found. In stage II, for detected outlier in stage I, the estimation of outliers effects are obtained simultaneously. Then, outliers with insignificant effects are removed. The VAR parameters re-estimated based on modified series of this stage. In stage III, we repeated stage I and II with new VAR parameter estimation. In each iteration of TPP, an outlier is detected and the effect of this outlier is removed from series (modified series). Then the parameter estimation is obtained from the modified series and the next outlier detection is continued using these estimates. This may lead to biased estimates and wrong detection of the next outlier point. In other words, in the TPP method, one detected outlier hides another outlier (masking), or one detected outlier reveals the usual observation as an outlier (swamping). This method often mis-detects the type of outliers. But in each iteration of GA, a random pattern of outliers (for testing) is first generated and a temporary modified series is obtained by removing effect of this pattern from series. Then the estimation of the parameters obtained and the detection of this pattern is tested. This work reduces the effect of the previously identified outliers on the full pattern of the outliers. In fact, if the random pattern of all outliers is correctly generated, almost effect of all of them will be eliminated in the modified series. Therefore using this temporary modified series, the GA obtained more accurate estimates and detected outliers more accurately. The simulation results confirm the validity of the GA method and the percentage of correct outlier detection in this method is higher than the TPP method. GA, of course, needs more time to calculate. Also, although the VAR model is used in both detection methods, the percentage of correct outlier detection in the VARMA model data is similar to the VAR model. Gas-furnace data were analyzed and modeled and it was determined that GA and TPP methods detected similar outliers. Fitting the VAR(6) model on these data shows that the variance of input gas error in modified data of GA to TPP is reduced by 17% and the variance of carbon dioxide error in the modified data of GA to TPP reduced by 43%.

Evaluation of Longshore Sediment Transport Rate in Imam Khomeini port using three examples of meta-heuristics algorithmImam Khomeini port is one of the ports of Khuzestan province in the Persian Gulf, which has 38 active wharves with a length of 7 km, is the largest active port in Iran and the annual dredging volume in this port is about 600 thousand cubic meters, of which about 400 thousand cubic meters is related to the Duragh canal and about 200 thousand are related to other ports of the port, since the sedimentation rate and dredging cost in this port is significant, so, in this study the rate and volume of sedimentation based on field information and modeling obtained from the Ports and Maritime Organization And comparing these values with the results obtained from meta-heuristic algorithms under MATLAB software in two-dimensional flow conditions and also the presence of all parameters affecting the transfer of sediment along the coast in Imam Khomeini port. After combining the three equations of CERK, Kamphuis and Bayram (CKB) and calculating the optimal coefficients and capabilities by Differential Evolution, Ant Colony Optimization and Genetic Algorithm, evaluation and validation with the values obtained from the available field data, coefficient error and computational capabilities Calculated using the root mean squares and bias method, therefore, it was observed that the coefficients and powers obtained from the genetic algorithm that were placed in the CKB equation have the most overlap with the rate longshore sediment transport from field data.

The aim of this study is to explain to the theoretical model in order to find a new solution for the production and development of spatial arrangement of architectural plans based on interactive and integrated methods with the help of machine learning and genetic algorithms. Evolutionary algorithms alone are not effective, but machine learning algorithms can learn plans and form the basis of practical models that can develop and generate new samples through the use of genetic algorithms.

In this regard, the combined research method includes library studies, collecting raw data, reviewing case samples, and using computational formulas as objective and penalty functions.

Studies show that the genetic algorithm does not have the ability to store memory and on the other hand, the basis of its calculations is jumping and random action that this process is not effective in the production of architectural plans alone and research.

 findings show that the algorithm Machine learning, due to its exemplary structure, can store and recognize examples, and the genetic algorithm, which is a searchable and scalable algorithm, can produce more examples of architectural plans each time based on the proposed mathematical model.

In this study the adsorption of the anionic dye, aniline blue, onto a novel biosorbent with the local name of Tonbak Toureh and the scientific name of Grantia aucheri was considered. FT-IR and SEM were used for characterization of the biosorbent. The effect of dominant parameters including pH, amount of biosorbent, time, temperature, and initial dye concentration were investigated and the optimum conditions of pH of 4-5, time of 10 min, temperature of 25 ͦ C, dye concentration of 40 mg L-1, and biosorbent amount of 12 mg were achieved. The adsorption isotherms corroborate the experimental data were appropriately fitted to the Langmuir model with high adsorption capacity of 65.79 mg g -1. Artificial neutral network-genetic algorithm (ANN-GA) was applied for prediction and optimization of the process in which the closeness of the predicted values with experimental data confirms the efficiency and potential of ANN-GA for prediction and optimization of the adsorption process. The thermodynamic parameters were assessed. The positive ΔH° and ΔS° values described endothermic nature of adsorption. The adsorption of aniline blue followed the pseudo-second order kinetic model.

Finding the optimal global solution in optimization problems is such an important issue that various related approaches have been proposed so far. An effective attempt before solving such problems is to reduce the search space in such a way that the search is concentrated in a smaller subspace and therefore the probability of finding the optimal global solution increases. In this article, three methods of clustering, classification and association in data mining are used to reduce the search space in a nonlinear optimization problem. After that, using the Genetic Algorithm, the problem is solved on the entire initial feasible space and the reduced spaces resulting from three data mining methods. The results show that by combining data mining methods and Genetic Algorithm, more accurate approximations for the global optimal solution of the problem can be obtained.

Wheat is one of the most important grains in the human food basket, which is known as a major source of energy, protein and fiber due to its valuable nutrients. The post-harvest stage of the wheat crop is explained in two ways: either it is sent to food processing factories or it is stored in silos for sale at regular intervals. Various parameters represent the quality of wheat grain that the percentage of purity of the mass is one of the main factors affecting the purchase price of the product. Several types of non-wheat grains, including germinated grains, broken grains, legumes, weed seeds, insect-damaged grains, foreign matter (pebbles, straw), etc. are the main sources of impurities in wheat. Researchers have always tried to develop computer-based solutions for impurities in wheat grain to be able to develop automated wheat grain separators. Image processing based on morphology, color and texture characteristics of grains has been used for various applications in the grain industry, including grain quality assessment and wheat classification. Various grading systems based on image processing have been studied. The presence of various impurities at the time of wheat harvest is one of the important factors in reducing the quality of wheat, so it seems necessary to detect impurities in wheat grain. The quality of wheat has a significant effect on its marketability. In addition, if wheat is used as a crop seed, the impurities in the mass will be a determining factor in the yield of the future crop.

In statistical analysis of data, situations are sometimes encountered in which the relationship between problem variables is very complex. This makes it difficult to analyze and process the data, so that sometimes no definite relationship can be found between the variables. In these cases, instead of purely theoretical research, applied research is done. Artificial neural networks are one of the solutions that, by processing experimental data, discover the knowledge or law behind the data, and transfer it to the network structure. In this study, the possibility of identifying wheat in wheat grain mass and estimating the amount of impurities in the mass, based on video processing using two types of artificial neural network (ANN) algorithms and hybrid genetic algorithm (GA) has been investigated. For this study, the code related to the artificial neural network with two hidden layers and the number of different neurons in each layer was written in MATLAB software. This code was used to identify and classify each component in the wheat grain mass. The main task of ANN is to learn the structure of the model data set. To achieve this, the network is trained with examples of related outcomes to generalize the capability. Multilayer artificial neural networks (MLPs) are the most common ANN models. In the present study, to reduce the computational load and increase the accuracy of the results, as well as to save time, some parameters that can be changed in the genetic algorithm were extracted as a fixed number using trial and error method. Among these parameters is the number of layers in the main structure of the neural network.

A hidden layer with a number of neurons 2 to 12 was used as an even number. It should be noted that the number of neurons above this amount of computational time increased dramatically and did not have much effect on classification accuracy. Another parameter in this field is the Max Reproduction factor (Max Generation) which according to the results of trial and error for this factor, the results showed that increasing this value more than 30 has little effect on classification accuracy and decreases the mean squared error. And only increases the computation time, so a constant value of 30 was considered for this parameter. 4 values of 50, 100, 150 and 200 were used for the Pop Size parameter. Values above 200 dramatically increased computational volume and processing time, so values over 200 were omitted. Values less than 50 also reduced classification accuracy, and values less than 50 were excluded from the analysis process. After preparing the video of mass movement on the conveyor belt, using MATLAB software and image processing toolbox, 17 shape features, 12 color features and 6 texture features were extracted from each grain sample in the image. The data obtained from the image processing section were classified into five categories: wheat, barley, oats, straw and weed seeds. Two types of artificial neural network (ANN) algorithms, feeder (newff) and feeder (newcf), and hybrid genetic algorithm (GA) were used to achieve the highest classification accuracy and minimum error.

Techniques related to image segmentation were used to separate objects within the image. In this stage of image processing, an attempt is made to separate interconnected objects using a variety of morphological and color methods in the image. In fact, the purpose of separating interconnected objects in the image is to make it possible to examine the individual objects in the image separately and extract the different characteristics of each of them. The results showed that from 36 different artificial neural network (ANN) structures, the 5-4-10-35 structure for the newff algorithm with 100 and 89.74% accuracy for training and testing conditions, respectively, with a processing time of 10.39 seconds and the structure 5-8-10-35 for newcf algorithm was obtained with 100% accuracy for training conditions and 87.17% for test conditions with a processing time of 44.94 seconds. On the other hand, the results of the hybrid GA algorithm showed the highest classification accuracy with 95.55% and 86.66% for training and testing, respectively, in a structure in which 8 neurons in the hidden layer with a population size of 200 were used. Was obtained. According to the obtained results, the use of video processing using ANN artificial neural network and newff algorithm due to high accuracy and lower computation time is a powerful tool for detecting impurities in wheat grain mass. Therefore, the use of artificial neural network with the help of video processing has the ability to classify wheat grains and can be used in a practical way. Given the importance of grain mass velocity in the discussion of industrial application, it is suggested that higher grain mass velocities be investigated in a similar way.

Saving on inputs, preservation of fossil fuels and decreasing air pollution are the advantages to using energy efficiently.  The purpose of this study was to optimize energy inputs and greenhouse gas emissions of orange product in Dezful County, with two methods of data envelopment analysis and multi-objective genetic algorithm optimization techniques.

 Data from 60 farmers were randomly collected through face-to-face interviews and a questionnaire during the year 2016 and using two methods of data envelopment analysis and multi-objective genetic algorithm were analyzed.

Regarding the results of data envelopment analysis technique based on fixed and variable return scale models and input-axis measurement, technical efficiency, net technical efficiency and scale efficiency were calculated to be 0.95, 0.98 and 97%. The results of optimization of energy consumption and greenhouse gas emissions by using data envelopment analysis showed that about 4.36% of orange energy has storage potential, that chemical fertilizers and diesel fuel have the highest amount of stored energy of all stored energy. Data envelopment analysis can reduce 34.38 kg of carbon dioxide per hectare from greenhouse gas emissions in orange crops. The results of the genetic algorithm showed that if all inputs were completely optimized, it could reduce the energy consumption of orange production in the study area by 26.1%. Also, the energy input for ideal orange production system could be 32810.6 MJ per ha.

According to the results of this study, it is recommended to use of new machines and encourage farmers to conduct soil tests before using of fertilizer.

Motor oils have different physicochemical properties, namely viscosity, viscosity index, flash point, pour point, etc. Viscosity is one of the important properties of motor oils since all the properties of industrial lubricants are referred to as their viscosities. The changes in viscosity with variation in temperature are regarded as the viscosity index. The greater the viscosity index, the lower the chances of the viscosity of motor oil with temperature and vice versa. According to the importance of viscosity index in lubricants and because the viscosity index of lubricants is dependent on the chemical composition of motor oils, thus in this study, a simple spectroscopic technique like Fourier Transform InfraRed (FT-IR) spectroscopy was used to analyze the Behran motor oils. The important wavenumbers that affect the viscosity indices were identified by using the Genetic Algorithm (GA) as a variable selection method. By using this method, some functional groups like Alkyl halides, Alkene, Nitro, Acid, Alkane, Alkyne, and Alcohol were recognized that affect the viscosity index of motor oils. Modeling the viscosity index of motor oils was done by Multivariate Linear Regression (MLR) method. Various data preprocessing techniques like Mean Centering and Auto-scaling were operated before the MLR and GA-MLR techniques. The results of modeling were evaluated by using different parameters like regression coefficients (R2) and Root Mean Square Error (RMSE). The values of R2 and RMSE, obtained by the GA-MLR were 0.998 and 0.954 respectively.

In this study, the melting temperature of ionic liquids based on bis(trifluoromethylsulfonyl)imide anion using experimental data were modeled using the QSPR approach. The structures of ionic liquids were drawn by Avogadro software and their 3D structure were optimized by Merck molecular force field. Descriptors were calculated using Dragon and Padel software. After reducing the number of descriptors, the ionic liquids were divided into training and test set employing Kenard- Stone algorithm. For choosing the best set of descriptors, a genetic algorithm with Friedman's lack of fitness was used. Then, the numbers of optimized variables were determined by the multiple linear regression MLR method and the linear equation between variables was obtained. Linear and nonlinear models were built by means of Multiple Linear Regressions (MLR), MultiLayer Perceptron (MLP) neural networks, and using genetic algorithm. R2, AARD values were 0.787, 0.043 for linear model and 0.785, 0.0428, for nonlinear model. Both models showed the same accuracy. The applicability domain of the proposed models was also determined. Also using the obtained descriptors, the effect of molecular structure on the physical properties such as melting temperature was addressed.