Search

Stress concentration and nonlinear buckling caused by grain boundaries in two-dimensional structures and geometric defects are introduced as factors affecting the fracture behavior of two-dimensional materials. Since the mechanical behavior of polycrystalline nanostructures is not well known, in this article, the mechanical behavior of carbon nitride nanosheets was studied as a function of temperature and grain boundaries. The mechanical performance of polycrystalline carbon nitride was tested in the presence and absence of edge cracks and at temperatures from 100 K to 900 K. Molecular dynamics simulation was used as a cost-effective method for modeling and testing two-dimensional nanosheets by choosing the appropriate potential function and boundary conditions. The results showed that the mechanical properties of carbon nitride monocrystalline decrease with increasing temperature and the results were reported in zigzag direction higher than armchair. The same trend was observed for the polycrystalline structures. The increase in temperature caused the Young's modulus, failure stress and strain to decrease. Also, increasing the crack length from 5 to 25 angstroms caused a decrease in mechanical properties. On the other hand, increasing the number of regions for carbon nitride polycrystalline decreased the failure stress. In addition, the optimization was carried out by genetic algorithm and the results showed that the optimal value of Young's modulus for carbon nitride polycrystalline with 53 regions at a temperature of 586.95 K and a crack length of 6.52 angstroms is equivalent to 338.18 GPa. The results obtained from this study can be generalized to more complex cases to predict a deeper understanding of the next generations of two-dimensional structures. [ABSTRACT FROM AUTHOR]

Background and Objectives Water resources management, especially irrigation practices, is heavily reliant on reference evapotranspiration (ET0). ET0 is the rate of evaporation and transpiration from a standard reference surface with a presumed surface resistance of 70 s m-1, the height of 0.12 m and an albedo of 0.23. Penman-Monteith FAO-56 (P-M FAO-56) approach is the most commonly used method for calculating ET0. In spite of the fact that FAO-PM is achievable, its implementation remains inconvenient because it requires a large amount of meteorological data, which is derived from standard meteorological observation stations. In the absence of complete climate data, it is highly desirable to have a model with fewer input climatic dates. Therefore, remote sensing methods have been used and improved over time to estimate ET0 at various spatial scales. Alternatively, it has been observed that the research community has become increasingly interested in obtaining data from metaheuristic algorithms that are based on artificial intelligence (AI). Methodology In this research, it has been attempted to estimate the amount of daily reference evapotranspiration (ET0) using two data-driven models, using a combination of inputs from meteorological station data and satellite imagery data from MODIS sensor, by considering different inputs from these sources. The models include the random forest (RF) and hybridized RF with genetic algorithm optimization (GA-RF). Moreover, the correlation of input variables with ET0 is evaluated and the possibility of training a simple and accurate machine learning model in the conditions of lack or absence of meteorological data using satellite image data is investigated. So, this study aimed to determine ET0 in the time period of 2003-2021 using land surface temperature (LST) data and leaf area index (LAI) acquired from MODIS sensor and Tabriz meteorological station data including maximum and minimum air temperatures (Tmax, Tmin), average temperatures (T), wind speeds (U2), average relative humidity (RH), maximum and minimum relative humidity (RHmax, RHmin), and sunny hours (n). For the study area, daily LST were extracted from the Terra (MOD11A1) and Aqua (MYD11A1) satellites. Moreover, the LST of Terra and Aqua satellites were combined, since the LST values had missing data due to the presence of clouds. Furthermore, MODIS MCD15A3H version 6.1 using fourday data from Terra and Aqua satellites was used to determine the leaf area index (LAI). The standard P-M FAO-56 method for calculating daily reference evapotranspiration was considered as the base method. The set of input parameters was considered based on the cross-correlation of the parameters with reference evapotranspiration obtained from the FAO-Penman-Monteith equation. Findings The results of two data-driven models including standalone random forest (RF) and hybridized RF model with genetic algorithm (GA) to estimate ET0 values were compared with calculated ET0 by P-M FAO-56 equation. The results indicated that all of the studied input variables are highly correlated with the target variable. Based on the P-M FAO-56 method, the average air temperature with the highest value (R²=0.903) and the wind speed with the lowest value (R²=0.282) has a high and low correlation with reference evapotranspiration. Also, by comparing LAI and LST MODIS parameters, LST has the highest correlation coefficient with ET0 with R²=0.865. A total of twelve scenarios for estimating ET0 are evaluated, each with a different set of input parameters. Based on the correlation between the parameters and ET0, the first ten scenarios are categorized. Additionally, the eleventh scenario is based only on satellite images, and the twelfth scenario is based solely on weather station data. Based on the results, the GA-RF-10 (R²=0.976, RMSE=0.200, MAPE=11.373, and MBE=0.028), which includes all input parameters, outperforms the other models. There was a greater degree of accuracy with the RF-10 (R²=0.949, RMSE=0.293, MAPE=16.442, and MBE=0.017) when compared with the other random forest models. Based on the comparison of scenario 11 (satellite image data) and scenario 12 (meteorological station data), it appears that scenario 12 is more accurate for both RF (R²=0.922, RMSE=0.357, MAPE=20.712, and MBE=0.009) and GA-RF (R²=0.944, RMSE=0.306, MAPE=17.037, and MBE=0.013) models. Despite the fact that only satellite image parameters did not provide accurate estimation of ET0 compared to independent meteorological parameters, the inclusion of these parameters in the ET0 estimation resulted in more acceptable results, demonstrating the importance of satellite image parameters. Thus, satellite data may be useful and recommended for estimating ET0, particularly in areas without meteorological stations. Conclusion According to the results obtained from the present research, GA-RF-10 model (R²=0.976, RMSE=0.200, MAPE=11.373 and MBE=0.027), which includes all input parameters; It has the best performance among other models. According to the results, although the satellite parameters alone had weaker estimates than the independent meteorological parameters, but by including these parameters in the estimation of ET0, more accurate results are obtained, which shows the importance of satellite image parameters in estimation. [ABSTRACT FROM AUTHOR]

Background and Objectives Reference evapotranspiration (ET0) is an important parameter in the interactions among soil, vegetation, atmosphere, surface energy and water. Direct measurement of evapotranspiration values is costly and time consuming. On the other hand, modeling this complex process in which many variables interact with each other is not feasible without considering multiple assumptions. In this regard, the FAO Penman-Monteith method is used in a wide range of climatic and environmental conditions. One of the weaknesses of FAO Penman-Monteith method is its dependence on various meteorological parameters. Therefore, it is necessary to implement methods with lower meteorological variables that can estimate ET0 with suitable accuracy. Thus, in the present study, an attempt was made to estimate ET0 with acceptable accuracy using machine learning models. Methodology In the present study, daily meteorological parameters in the time period of 2000-2020 including maximum and minimum air temperature (Tmax, Tmin), mean temperature (T), wind speed (U2), average relative humidity (RH), maximum and minimum relative humidity (RHmax, RHmin) and sunshine hours (n) were obtained on a daily basis in three stations of East Azerbaijan province (Tabriz, Sarab, and Maragheh). Moreover, six scenarios were defined as input combinations. Then, using random forest (RF) method in two cases: Single random forest and using the genetic algorithm (GA) to optimize its effective parameters with considering the FAO Penman-Monteith model as a basis, the machine learning models were calibrated and validated for estimating ET0 values at studied stations. Furthermore, the performance of empirical equations in three groups based on temperature (Hargreaves, Blaney-Criddle and Romanenko), radiation (Irmak) and mass transfer (Meyer) were also investigated. It should be noted that 75% of the data were considered for calibration and 25% for the validation of machine learning methods. Finally, using the statistical criteria of correlation coefficient (CC), scattered index (SI) and Willmott’s Index of agreement (WI), a suitable machine learning method was introduced to estimate the reference evapotranspiration. Also, the most suitable combination of meteorological parameters for ET0 estimation was suggested. Findings The obtained results showed that in all studied stations, the scenario 6 has the best performance, either in the case of single random forest (RF) or in the case of random forest optimized by genetic algorithm (GA-RF). Meteorological parameters of this scenario include minimum and maximum air temperature, minimum and maximum relative humidity, sunshine hours and wind speed. By optimizing the RF-6 parameters with the genetic algorithm at Tabriz Station, the statistical criteria were improved (CC from 0.990 to 0.991, SI from 0.103 to 0.098). At Sarab Station, the CC was increased from 0.980 to 0.982, the SI was decreased from 0.140 to 0.132 and the WI was increased from 0.989 to 0.990. At Maragheh Station, CC was increased from 0.990 to 0.991, SI was decreased from 0.103 to 0.098 and WI remained unchanged at 0.995. In general, the decreasing trend of the scattered index for RF method from scenarios 1 to 6 can be understood by increasing the input parameters of the random forest method. Among the three groups of empirical methods based on air temperature, radiation and mass transfer for estimating ET0, the best performance was seen for the Blaney-Criddle method based on air temperature. In all studied stations, the GA-RF model showed better performance than the empirical methods. Also, GA-RF-5 with similar meteorological parameters with Blaney-Criddle method provided accurate ET0 estimations. Conclusion Determining the amount of daily evapotranspiration and consequently accurate estimation of water requirement of plants provide the basis for proper designing of irrigation systems by reducing installation costs and providing a suitable program for the use of water resources in the agriculture sector. Therefore, in the present study, meteorological data from Tabriz, Sarab and Maragheh Stations were used to evaluate the ability of machine learning methods including RF and GA-RF to estimate the values of reference evapotranspiration. The results showed the high accuracies of RF-6 and GA-RF-6 for all studied stations and Belany-criddel among the empirical models. In a more detailed look, the genetic algorithm had positive effects on increasing the model accuracies by reducing scattered index of GA-RF scenarios 1, 4, 5 and 6 in Tabriz and Maragheh Stations as well as scenarios 1, 5 and 6 at Sarab Station. Finally, it can be concluded that both RF and GA-RF models provided the most accurate estimates of daily reference evapotranspiration in the East Azerbaijan province. [ABSTRACT FROM AUTHOR]

In the present paper, crop pattern criteria have been evaluated relying on sustainable development to increase agricultural water productivity. Seven criteria were selected as the main environmental and economic criteria and were prioritized and reviewed for important and strategic products in the Tajan catchment of Mazandaran province. Criteria prioritization was done using optimization through a genetic algorithm with an objective function based on sustainable development. Then, physical and economic productivity indices were calculated to determine the productivity value. Based on the results, in the selection of the crop pattern, firstly, the category of economic criteria and finally the category of environmental criteria have been given attention to the farmers in the current situation. But in the genetic optimization algorithm, all priorities have a similar order from the environmental point of view and then from the economic point of view although each product has its order of criteria. By this prioritization, the parameters of the cultivated area, the volume of water consumed, and the amount of chemical fertilizers have decreased on average by 26%, 34%, and 21%, respectively, and the parameters of product performance and profitability have increased by 43% and 61%, respectively. In addition to providing environmental standards and increasing sustainable development, this prioritization causes an average increase in physical productivity by 84% and an increase in economic productivity by 72%. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to propose a flow shop scheduling problem for equipment overhaul. This problem consists of three stages, the separation of the components of an equipment is done in the first stage. Repairs and overhaul operations are carried out on the separated parts of the first stage in the second stage. Finally, the overhauled parts of the previous stage are mounted on each other in the third stage. In the third stage, operations are performed in parallel workshops. The objective function of the problem is the maximum time to complete jobs, and the sequence of processing jobs should be done in such a way that the value of the objective function is minimized. Design/methodology/approach: To solve the problem, a mixed integer programming model has been proposed for small size, which determines the processing sequence of jobs based on the position of each job. A genetic algorithm has been used to solve the problem in large dimensions. By increasing the size of the problem and in different sizes, the results have been examined and analyzed, which shows the efficiency of the model and the proposed algorithm. Findings: To check the accuracy of the model's performance and also the effect of the presence of parallel machines in the third stage, an example was presented in this paper. Accordingly, while the accuracy of the model's performance was checked, the effect of the presence of more machines was determined in the third stage. As the number of machines increased in the third stage, the value of the objective function did not deteriorate. The performance of GAMS in solving the problem in a small size was investigated. Considering that solving the problem for large dimensions is not possible in a reasonable time and the problem is NP-hard, then solving the problem in large dimensions was done using a genetic algorithm. Therefore, solving the problem on a large dimension has been done using the genetic algorithm. According to the obtained results, the efficiency of the genetic algorithm was shown. Due to its low average value, it indicated the convergence of the genetic algorithm. Research limitations/implications: Considering that there are not many published papers in the field of equipment overhaul, it is difficult to access related models and papers. Therefore, in this paper, the model and solution method have been written with many reviews. Also, to check and reduce costs, the number of third-stage machines has been determined using sensitivity analysis. Practical implications: The problem of equipment overhaul is used in many fields in reality. For example, the operations related to the maintenance, repair and overhaul of the aircraft engine have been investigated. Since the planning of maintenance and maintenance operations is difficult, the focus of research has been on improving maintenance operations by finding suitable scheduling for job shop operations in maintenance operations. They emphasized that scheduling can improve maintenance operations and presented a simulation model. Social implications: The purpose of creating a space to start an activity is to reduce costs, earn money and achieve profit. To examine the cost-effectiveness of the equipment overhaul issue, we can refer to the number of third-stage machines. According to the amount of equipment to perform an overhaul on them, the number of third-stage machines can be determined. Therefore, extra machines can be removed to reduce the cost. On the other hand, if the related equipment to the customers is different, to reduce the storage costs or increase customer satisfaction, different goals should be considered. Here, the objective function of maximum completion time is considered for this purpose. If the equipment must be available at a certain time, goals such as the total time to complete the job can be considered. In line with the application of the social implications in the investigated problem in this paper and considering that the investment costs, as well as the ability to respond to the applicants' requests, are related to the number of third-stage machines, the value of the objective function is analyzed based on the number of third-stage machines and analysis has been done. Originality/value: In this paper, a three-stage flow shop scheduling problem in the overhaul industry was studied. Accordingly, a new mathematical model based on the job processing position was proposed, which dealt with the exact solution of the problem in small dimensions. According to the type of problem in the overhaul environment, the combined flow shop problem for equipment overhaul was investigated. Also, the use of parallel machines in the third stage of the equipment overhaul problem is one of the new issues under investigation. [ABSTRACT FROM AUTHOR]

Studying the bedrock geometry in mining and oil exploration operations to obtain its 2D pattern requires nonlinear reverse computations. Local optimization methods for solving nonlinear inverse problems are based on linearizing the changes of the model similar to a primary model and finding an objective function of minimum error from the model's parameters; however, these optimization methods are not able to select a suitable primary function that is close enough to the general optimal value. That is to say, every objective function can have several minimum and maximum solutions. The lowest minimum is called the global minimum while the rest of them are named local minimums. Therefore, in local inverse methods, the objective is to find the minimum of an objective function, and also an objective function might have a few local minimums with different values. In this case, it is not suitable to use gradient-based methods for exploration purposes, unless the primary model is very close to the actual answer; which is outside the control of geological structures or the geometry of the subsurface. Despite the easy execution and high convergence rate of the local methods, there is the possibility of being trapped in local minimums because these methods are dependent on the primary model and also finding more than one optimized point in 2D or 3D simulations; this is why local optimization methods are considered deterministic algorithms. Multiobjective and single-objective metaheuristic optimization algorithms are capable of searching the feasible region and they also provide a solution independent of the primary model. Searching the feasible region means finding all the feasible solutions for a problem and each point in this region is representing a solution that can be ranked based on its value. One of the important differences between local optimization and metaheuristic methods is constraining. Constraining metaheuristic global optimization methods are only used for constraining the feasible region based on previous knowledge or estimation relations; which is very different from constraining local optimization that is used for stabilizing inverse simulation. The algorithms used in the present work included a non-dominated sorting genetic algorithm (NSGA-II) and single-objective genetic algorithm, which were used to estimate the depth. The NSGA-II is commonly used to solve problems with multiple, typically conflicting, objective functions. This algorithm is capable of being developed and also has a high potential for solving unbounded multi-objective problems. In addition, the single-objective genetic algorithm (GA) is capable of modeling and solving complex problems. In the present study, both algorithms were verified and validated using the data produced by an imaginary and complex synthetic model. In order for a more precise examination of the performance of both algorithms, the imaginary synthetic data were used both with no noise and with up to 10% Gaussian white noise (GWN). Accordingly, the modeling results indicated a good consistence between the algorithms and the primary model; so that, the root mean square error parameter for the data obtained from the initial data of the synthetic model ranged from 0.05 to 0.35mGal for the NSGA-II and from 0.07 to 0.52mGal for the GA. Also, this parameter didn't exceed 72.4 in the NSGA-II and didn't exceed 93.8 in the GA. Based on the gravimetric modeling of the Western Anatolia, Turkey, the results obtained from both algorithms under similar conditions in terms of parameter settings and number of algorithm executions indicated good performance of the NSGA-II algorithm compared to the single-objective algorithm. [ABSTRACT FROM AUTHOR]

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%.

Multi-objective location-routing problem is one of the most important research areas in the field of transportation and distribution management. The aim of this study is to optimize a multi-objective problem. Combining two routing and location problems, considering a set of warehouses, meeting the customer’s requirements from each warehouse, and designing an optimal route for the vehicle that brings the lowest cost to the transportation system are the main objectives of this research. Although factors such as customer satisfaction with receiving services, fuel constraints in vehicles and the existence of important time intervals, which are referred to as hard time window, are of great importance in location and routing problems, less has been paid to them. In this research, efforts have been made to address these issues. To achieve the best priority by finding the shortest route and to reach the least deviation from the time window is some of the objectives of this research. Combining variables related to vehicle fuel capacity and fuel consumption speed has also been applied in this study. In this research, first, a mixed integer linear programming model is presented and then metaheuristic method based on Non-dominated Sorting Genetic Algorithm is proposed to find the optimal solution. To evaluate the proposed performance, an example is mentioned in this framework. The result of computational experiments, shows the efficiency of the existing research methodology and its strengths and weaknesses. [ABSTRACT FROM AUTHOR]

The present article deals with the optimal design of the contour or profile of the divergent part of an overexpanded supersonic nozzle in order to achieve the maximum possible thrust while maintaining the length and the exit to throat area ratio of the nozzle. To do so, a reliable and robust tool has been developed by combining computational fluid dynamics (CFD) and artificial intelligence. At first, the original profile is modeled by an innovative method using a thirdorder B-spline, and then by changing the breakpoints of the profile, a set of possible profiles is produced. This set of profiles has been analyzed by CFD. The geometry of the nozzle along with the thrust force obtained from the profiles have been used to train the artificial neural network. In the next step, the optimal profile was obtained by applying the genetic algorithm. Finally, the prediction of the artificial intelligence for the optimal nozzle thrust is compared with the value obtained from the CFD, which shows the validity of the present approach. The comparison between the original profile and the optimal profile for the nozzle pressure ratio of 14 shows a 36% increase in thrust and a 138% increase in the total pressure recovery factor. The comparison of nozzles for off-design conditions shows that the performance of the optimal nozzle is better than the original nozzle up to a pressure ratio of 30. If the nozzle pressure ratio exceeds 30, using the optimal nozzle instead of the original nozzle will not have priority. [ABSTRACT FROM AUTHOR]

This paper presents an approach that uses both genetic algorithm (GA) and fuzzy inference system (FIS), for feature selection for descriptor in a quantitative structure activity relationships (QSAR) classification and prediction problem. Unlike the traditional techniques that employed GA, the FIS is used to evaluate an individual population in the GA process. So, the fitness function is introduced and defined by the error rate of the GA and FIS combination. The proposed approach has been implemented and tested using a data set with experimental value anti-human immunodeficiency virus (HIV) molecules. The statistical parameters q2 (leave many out) is equal 0.59 and r (coefficient of correlation) is equal 0.98. These results reveal the capacity for achieving subset of descriptors, with high predictive capacity as well as the effectiveness and robustness of the proposed approach.

Time series data may be contaminated with different types of outliers. i.e. additive outliers, innovation outliers, level shift and temporary changes. Of course, the effects of these outliers in univariate and multivariate time series are different and detection of outliers in multivariate data are more complicated. Multivariate time series often, modeled using vector autoregressive moving average (VARMA) model and presence of outliers can violate the stationarity assumptions and may lead to wrong modeling, biased estimation and inaccurate prediction. Thus, detection and properly dealing with these data, especially in relation to modeling and parameter estimation of VARMA model is necessary. By detection of outliers, their effects can be removed or robustified and the adjusted data could be prepared for further analysis. The multivariate detection methods, suggested by Baragona and Battaglia (2007) and Cucina, et al. (2014), could not detect the innovational outliers and temporary changes. In this paper, after introducing the VARMA models, the principles of genetic algorithm and its application in detecting outliers are discussed. Then, the Tsay, Pena and Pankratz (TPP) method (Tsay, et al.(2000)) and the genetic algorithm (GA) for detecting different types of outliers in multivariate time series are described. Also, the efficiency of GA and TPP detection methods is discussed using simulation studies and real data. At the end, a conclusion is presented. Material and methods A genetic algorithm makes uses of techniques inspired from evolutionary biology such as selection, mutation, inheritance and recombination to solve a problem. The most commonly employed method in genetic algorithms is to create a group of individuals randomly from a given population. The individuals thus formed are evaluated with the help of the evaluation function provided by the programmer. Individuals are then provided with a score which indirectly highlights the fitness to the given situation. The best two individuals are then used to create one or more offspring, after which random mutations are done on the offspring. Depending on the needs of the application, the procedure continues until an acceptable solution is derived or until a certain number of generations have passed. For minimization of a function, GA operates by first generating, at random or optionally, several minimal solutions to the function, where 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 iteration obtained. Furthermore, we introduce another method for detecting outliers, i.e. the Tsay Pena and Pankratz (TPP) method. TPP uses some test statistics based on outlier's size and vector autoregressive (VAR) parameters. This method detects outliers in three stages. In stage I, it detects one by one outliers and remove their effects. Iteration continues until no outlier found. In stage II, for detected outlier in stage I, the estimation of outliers effects is 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 parameters estimation. In each iteration of TPP, an outlier is detected and removed from the 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 undetects 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 method reduces the effect of the previously identified outliers on the full pattern of them. In fact, if the random pattern of all outliers is correctly generated, almost effect of them will be eliminated in the modified series. Therefore, using this temporary modified series, the GA obtains more accurate estimates and detects outliers more accurately. Results and discussion 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. The Gas-furnace data set, called Series J by Box and Jenkins (1994), contains sequentially recorded measurements of two variables (gas rate and CO2) were analyzed and modeled. It was determined that GA and TPP methods detect similar outliers. Fitting the VAR (6) model to these data shows that the variance of input gas error in modified data of GA is reduced by 17% as compared with TPP and the variance of carbon dioxide error in the modified data of GA is reduced by 43% respectively. Conclusion The following conclusions were obtained from this research: In each iteration of the TPP outlier detection method, an outlier is detected and the effect of this point is adjusted. Then the estimation of the parameters is obtained from the modified series and the next point detection continues using these estimates. This may lead to bias of estimates and misdiagnosis of the next point. In other words, using the TPP method, one detected outlier hides another outlier. In the proposed method based on the genetic algorithm in each iteration, first a random design is generated from all outliers and the modified series is obtained from the same design. This reduces the effect of previously detected outliers on revealing the complete design of the outliers. In fact, if the random design of all outliers are generated correctly, the effect of them will be eliminated in the modified series. Thus, with this modified series, GA obtains more accurate estimates and detects outliers more correctly. The simulation results confirm the accuracy of the GA method and the percentage of correct detection of outlier in this method is higher than the TPP approach. Of course, GA requires more time for calculations. [ABSTRACT FROM AUTHOR]

The main purpose of the reliability theory of structural systems is the optimal design based on the reliability concept. Trusses and space structures are widely used, and cost and safety both are important in these structures. Therefore the weight optimization of these structures based on the theory of reliability (probabilistic optimization) using Genetic Algorithms was studied in this paper. The objective function was weight of structure and the constraints were based on the failure probability of elements or nodes or the system. To increase the accuracy of structural safety calculations, the probabilistic form of buckling is presented in this research.The results of this study show that increasing the system allowable failure probability decreases the optimum weight of structure. The process of this weight loss occurred at first with a very fast slope and then with a gentle slope and finally tended to a constant value. Optimum weight was very sensitive to coefficient of variation comparison of allowable failure probability. In the probabilistic optimization, if the system allowable failure probability and coefficient of variation of load and yield stress are considered near zero, and if results are compared to the deterministic optimization, the difference in optimum weight is less than 9%. In this case, convergence for deterministic optimization was very fast and occurred in less than 20 generations but convergence in probabilistic optimization occurred slowly after 85 generations.

Surface runoff is one of the most significant components of the water cycle, which increases soil erosion and sediment transportation in rivers and decreases the water quality of rivers. Therefore, accurate prediction of hydrological response of watersheds is one of the important steps in regional planning and management plans. In this regard, the rainfall-runoff modeling helps hydrological researchers, especially in water engineering sciences. The present study was conducted to analyze the rainfall-runoff simulation in the Gorganrood watershed located in northeastern Iran using AWBM, Sacramento, SimHyd, SMAR, and Tank models. Daily rainfall, daily evapotranspiration, and daily runoff of seven hydrometric stations in the period of 1970-2010 and 2011-2015 were used for calibration and validation, respectively. The automated calibration process was performed using genetic evolutionary search algorithms and SCEUA methods, using Nash Sutcliffe Efficiency (NSE) and root mean of square error (RMSE) evaluation criteria. The results indicated that the SimHyd model with NSE of 0.66, TANK model using Genetic Algorithm and SCE-UA methods with NSE of 0.67 and 0.66, and Sacramento model using genetic algorithm and SCE-UA methods with NSE of 0.52 and 0.55 have the best performance in the validation period. [ABSTRACT FROM AUTHOR]

Errors are inevitable in accounting and factors such as diversity and complexity of economical subjects, workloads, exhaustion, and similar issues increase their likelihood. As well, the constant change of the economic, social, and other factors makes it vital to consider the change of the accounting principles and methods, in order to enable the adaptation of the enterprises to new conditions, since all these issues can result in the detection of manipulation of earnings in the financial statements.This subject received serious attention after the Enron Corporation scandal incurred. This research aims to prove the need for the application of the enhanced Beneish Model for credited companies listed in the Tehran Stock Exchange between the years 2009 and 2020. Target sample consists of 265 companies, which have been used to estimate and improve the Benish model using logit regression and genetic algorithm. The result shows that, according to the Confusion Matrix, among all models of detection of manipulation of earnings in financial statements, the genetic algorithm Beneish model has maintained 73.21 accuracies, which is considered the highest rate for predictability compared to the primary Beneish model and models offered with logistic regression, thus the theory of this writing is approved. [ABSTRACT FROM AUTHOR]

Incremental sheet forming is a flexible forming technology in which the sheet metal is gradually formed by the movement of tools in specified path. Due to the progressively localized deformation of the sheet and concentration of the forces on contact area of tool and sheet metal, the formability of the sheet increases compared with other common forming methods. In this study, numerical simulation of the incremental forming of AA3105-St12 two- layer sheet has been performed to calculate forming force and final thicknesses of the layers. The validity of the simulation results is evaluated by comparing them with those obtained from experiments. Numerical models for estimating the vertical force applied on the tool and the final thicknesses of the layers in terms of the process variables have been obtained using artificial neural network. Multi-objective optimization has been conducted to achieve the minimum force and the minimum thickness reduction of layers using obtained numerical models based on genetic algorithm method. Optimum thickness of the two-layer sheet and the thickness ratio the layers in different states of contact of the aluminum or the steel layers with the forming tool have been determined. [ABSTRACT FROM AUTHOR]

Sports simulation mechanisms practically have a lot of appeal and application to implement virtual reality environments. Cycling simulator has a more special place in sports and urban transportation due to the popularity of cycling activities. In this paper, the design and construction of a new motion generating mechanism for an interactive cycling simulator is presented. First, by using the references, the range of velocity and acceleration that the user should experience while cycling has been extracted, and by analyzing other cycling simulators, the required degrees of freedom and its range have been determined. Then, a new motion generating mechanism with two degrees of freedom is designed. Genetic algorithm has been used for dimensional optimization of the mechanism parameters. Kinematics and dynamic equations of the mechanism have been extracted. According to the dynamic model of the mechanism, a controller has been designed using the feedback linearization method and the performance have been investigated. Finally, the designed motion generating mechanism has been constructed and the position control has been implemented on the platform. [ABSTRACT FROM AUTHOR]

Evaporation is one of the important factors in the hydrological cycle and is one of the determinants of energy equilibrium at ground level and water balance, which is required in various areas such as hydrology, hydrology, agriculture, forest management, and management of water resources (Sanei Nejad et al., 2011). In this regard, one of the basic data in designing irrigation and drainage networks is the amount of evaporation power in each region. Because the design of transmission networks, such as drainage or drainage channels, as well as other parts of water design, depends on the amount of water required by the evaporation phenomenon (Jahanbakhsh et al., 1380). In general, evaporation hydrology is generally referred to as the phenomenon of water It simply turns steam into a physical process.

Optimization of artificial intelligence (AI) models is a significant issue because it enhances the performance and flexibility of the numerical models. In this study, scour depth around bridge abutments with different shapes was estimated by means of ANFIS and ANFIS-Genetic Algorithm. In other words, the membership functions of the ANFIS model were optimized using the genetic algorithm, finding that the performance of ANFIS model was increased. Firstly, effective input parameters on the scour depth around bridge abutments were defined. Then, by using the input parameters, eleven ANFIS and ANFIS-GA models were produced. Next, the superior ANFIS and ANFIS-GA models were introduced by analyzing the numerical results. For example, the correlation coefficient and scatter index for ANFIS model were calculated to be 0.979 and 0.070; for ANFIS-GA, these were 0.986 and 0.056, respectively. In addition, the average discrepancy ratio (DRave) for ANFIS and ANFIS-GA models was 0.984 and 0.988, respectively. Also, it was shown that the ANFIS-GA models had more accuracy, as compared to the ANFIS models. Moreover, a sensitivity analysis showed that Froude number (Fr) and ratio of flow depth to radius of scour hole (h/L) were the most influential input parameters for simulating the scour depth around bridge abutments. [ABSTRACT FROM AUTHOR]

In recent years, the use of renewable energy systems has grown significantly, among which photovoltaic systems have received much attention. Solar cells are known as the building blocks of a photovoltaic system. Because of the nonlinear nature of solar cells and the continuous changes in atmospheric conditions, maximum power point tracking (MPPT) is essential to extract the maximum power of a photovoltaic system. In this study, in order to achieve the maximum power, it was proposed to apply flower pollination algorithm (FPA) combined with a comprehensive selection algorithm, named as improved FPA. In addition, to evaluate the proposed algorithm, its performance was compared with genetic algorithm (GA) and standard FPA under rapid changes in atmospheric conditions. The calculated results showed that the improved FPA has a better accuracy than GA; moreover it has a higher convergence rate as compared with other applied algorithms. [ABSTRACT FROM AUTHOR]

Permanent magnet machines are widely used in wind turbines due to theirs prominent characteristics. The direct-drive wind generators have large size and high manufacturing cost because of low operational speed so that these disadvantages deteriorate when the rated output power increases. Therefore, the main objective of the optimal design proposed in this paper is to minimize the wind turbine system cost maintaining the high efficiency characteristic. Thus, a multiphysics model of the wind generation system is firstly presented to be the basis of the optimal design. One of the paramount feature of the current study is to precisely calculate all of the energy production costs, including the manufacturing cost of generator, power converter, electrical subsystem, and also wind turbine tower cost. In order to obtain the optimum solution, the Genetic Algorithm (GA) optimization method is implemented with consideration of a predetermined proper range for optimal variables. By comparing the optimal design results with those attained by the innerrotor permanent magnet generator, the superiority of the proposed method is justified in terms of the total volume, weight, and annual output energy. Eventually, the finite element analysis has also been carried out to validate the outcomes obtained from the proposed optimal design. [ABSTRACT FROM AUTHOR]

Long-term prediction of time series is an important but challenging issue. Today, deep networks, especially Long short Term Memory (LSTM) networks, have been successfully used to predict time series. The LSTM network is capable of maintaining long-term dependencies, but its ability to assign varying degrees of attention to sub window features over multiple time steps is not sufficient. Also, the performance of these networks depends heavily on their hyper-parameters and it is important to adopt an efficient method to ensure optimum values. In this study, to overcome the above challenges, an evolutionary attention-based deep LSTM for predicting multivariate time series is recommended that automatically finds one of the best combinations of LSTM parameter values and sub window features. The proposed algorithm uses a genetic algorithm to properly adjust the deep LSTM network architecture. In order to evaluate the performance of the proposed algorithm, three data sets in the fields of energy and environment have been used. The experimental results show that the proposed algorithm performs better than other basic models. [ABSTRACT FROM AUTHOR]

Introduction: Hospitals as the most important consumer of resources in healthcare section are highly sensitive to maximum consumption of minimum existing resources. In the recent two decades, computer data processing to extract knowledge and improve utilization of resources has attracted the attention of organizations. In this study, allocation of CCU beds in Shahid Faghihi Hospital of Shiraz is investigated through optimizing and combining Genetic Algorithm (GA) and Imperialist Competitive Algorithm (ICA). Methods: In this analytic cross-sectional study, patients were monitored through optimization and combination of genetic algorithm and imperialist competitive and allocated to CCU beds in the spring of 2016. To this end, number of patients, number of beds, number of doctors and vital signs of patients were used as input and configuration of patients and allocation optimization were considered as output. MATLAB 2012 was used to analyze data. Results: Results of this study show that ICA is more efficient compared to GA in optimization of allocating CCU beds to patients. Moreover, the hybrid algorithm obtained from combination of ICA and GA is more efficient than ICA. Conclusion: In the process of this study, priorities of patients' hospitalization and also manner of hospitalization were determined and suggestions for allocation of beds to patients were presented.

Surge tanks and air chambers are the most useful solution to deal with water hammer in water transmission systems (WTS). The optimal design of these protective devices can be effective in reducing the costs of constructing and operating a water transmission system. In this article, some software with the capability of simulating and optimizing these protective equipment is presented. To simulate the behavior of the system in the transient condition, the characteristic method was used. To optimize the number, dimensions and location of the surge tanks and air chambers, the genetic algorithm was employed. Constraints of the problem included the control of negative and positive pressures within the permissible range to prevent the cavitation and water hammer. To test the performance of simulation and optimization models, a well-known water transmission system in the previous research was selected as a case study. The results indicated that the critical heads were damped to a safer and allowable range; also, the total cost of the surge tanks and air chambers was reduced by 17% by the proposed method. [ABSTRACT FROM AUTHOR]

Drying is one of the ways of storing of persimmon. In this study, to increasing shelf life of persimmon and producing high-quality products, infrared dryer was used and mass transfer kinetics, density, rehydration and color of samples were measured. The results showed that radiation lamp power and distance of lamp from sample had significant effect on the moisture loss kinetics and drying time (P<0.05). With increasing in radiation power, as well as reducing the distance of samples from the source of radiation, drying time decreased. The average density and rehydration for the dried samples in infrared were 639 kg /m3 and 270 %, respectively. The average calculated color changes (ΔE) for the power of 200, 300 and 400 w were 14.43, 10.09 and 20.04, respectively. The results of modeling by genetic algorithm-artificial neural network showed that artificial neural network combined with genetic algorithm provides better results and with combine them the speed of analysis and accuracy of modeling process increases. Using a network with 15 neurons in the hidden layer and using the hyperbolic tangent activation function and percentage data used to training/validation/testing equal 20/20/60 may be predicted drying kinetics of persimmon. [ABSTRACT FROM AUTHOR]

The growing use of internet and the existence of vulnerable points in networks have made the use of intrusion detection systems as one of the most important security elements. Intrusion detection is essentially a classification problem and it is the identification of effective features such as important issues in the classification This paper presents a novel method for selecting effective features in network intrusion detection based on an estimation of distribution algorithm that uses a probabilistic dependency tree to identify important interactions between features. To evaluate the performance of the proposed method, the NSL- KDD dataset is used, in which the packets are divided into five normal types and intrusive types of DOS, U2R, R2L and Prob. The performance of the proposed algorithm has been compared alone and in combination with other feature selection algorithms such as forward selection, backward selection and genetic algorithm. Moreover, the effect of algorithm parameters like population size on intrusion detection accuracy is tested. Based on this analysis and also considering the intra-class accuracy of different feature selection methods studied in this paper, an effective subset of features for intrusion detection is identified. [ABSTRACT FROM AUTHOR]

Grain design is the most important part of a solid rocket motor. The aim of this study is finocyl grain design based on predetermined objective function with respect to ballistic curves in order to satisfy various thrust performance requirements through an innovative design approach using a genetic algorithm optimization method. The classical sampling method has been used for design space-filling. The level set method has been used for simulating the evolution of the burning surface in the propellant grain. An algorithm has been developed beside the level set code that prepares the initial grain configuration using Pro/Engineer software to export generated models to level set code. The lumped method has been used to perform internal ballistic analysis. Two meta-models are used to surrogate the level set method in the optimization design loop. The first method is based on adaptive basis function construction and the second method is based on the artificial neural network. In order to validate the proposed algorithm, a grain finosyl sample has been investigated. The results show that both grain design method reduced the design time significantly and this algorithm can be used in designing of any grain configuration. In addition, data have more accuracy in grain design based on the artificial neural network, so this method is the more effective and practical method to grain burn-back training. [ABSTRACT FROM AUTHOR]

In the selection of a collection of investment assets, the expected utility of investor is determined via risk and return criteria. Regarding the uncertainty of the investor about the future, portfolio diversification is a common path towards risk reduction in investment problem. In this study, not only the Euclidean Distance Criterion (EDI) was introduced to be a measure of portfolio diversification, but also a multi-objective model was designed for portfolio selection. This model intended to maximize the return and diversification of portfolio, and also to minimize non-systematic risk of it. Since this is a non-linear model and in terms of complexity is among "NP-hard", regarding the computational efficiency of the Genetic Algorithms (GA) in optimization, it was used for solving the model. Results from the implementation of the dual-objective model (return and diversification) and triple-objective model (return, diversification, and non-systematic risk) with multiple-repetition showed that the average return of the portfolio selected by perposed model was higher than the favorable level. Investigation into portfolio performance indices indicates the efficiency of the dual-objective model (return and diversification).

In this study, the discharge coefficient of the circular side orifices was predicted using a new hybrid method. Combinations made in this study were divided into two sections: 1) the combination of two algorithms including Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) and providing the PSOGA algorithm 2) using the PSOGA algorithm in order to optimize the Adaptive Neuro Fuzzy Inference Systems (ANFIS) network and providing the ANFIS-PSOGA method. Next, by identifying the parameters affecting on the discharge coefficient of the circular side orifices, 11 different combinations were provided. Then, the sensitivity analysis conducted by ANFIS showed that the Froude number and the ratio of the flow depth to the orifice diameter (Ym/D) were identified as the most effective parameters in modeling the discharge coefficient. Also, the best combination including the Froude number (Fr), the ratio of the main channel width to the side orifice diameter (B/D), the ratio of the orifice crest height to its diameter (W/D) and the ratio of the flow depth to the orifice diameter (Ym/D) for estimating the discharge coefficient was introduced. For this model, the values of Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE) and correlation coefficient (R) were obtained 0.021, 0.020 and 0.871, respectively. Additionally, the performance of the ANFIS-PSOGA method was compared with the ANFIS-PSO and ANFIS methods. The results showed that the ANFISPSOGA method for predicting the discharge coefficient was the superior model [ABSTRACT FROM AUTHOR]

In plasma cutting, a noble gas at high speed is blown from the nozzle and ionized with the help of a frequency spark at high voltage and an electric arc is created which cause the gas changes to the plasma state. Plasma cutting is an ideal process for cutting of the hard metals. In this research, the effect of the input parameters and their optimization in plasma cutting of AISI 309 stainless steel were studied. By conducting the different experimental tests, the effect of input parameters including amperage, gas pressure and the cutting speed of torch on the three output parameters of the width of cut (Kerf), heat-affected zone (HAZ) and surface roughness (Ra) were investigated. Analysis of the results showed that the amperage, cutting speed and gas pressure have the highest impact on the output parameters, respectively. The artificial neural network (ANN)-genetic algorithm was used to predict and optimize the output parameters. The results indicate that the artificial neural networks model trained by the genetic algorithm are able to predict the output parameters accurately. Finally, the optimization of output parameters to achieve the best cutting conditions was carried out using the genetic algorithm. The artificial neural network models were considered as the objective function and also, the parameters of the heat-affected zone, surface roughness, and the width of cut were introduced as inputs of the algorithm. According to results, a combination of the neural network and genetic algorithm is an efficient method for optimization of the plasma cutting process. This method can be easily modified and utilized for other advanced cutting methods. [ABSTRACT FROM AUTHOR]

Shape memory alloys (SMAs) are a new generation of smart materials which was the subject of researches in recent years. In this study, SMAs are employed to improve the vibrational and structural behavior of composite beams. A numerical solution was presented for natural frequency analysis of the clamped-clamped beam and the obtained results were validated with results of available references. Two main goals were followed in this study: first, analysis the influences of effective design parameters of embedded SMA wires on natural frequencies of composite beams and second, optimal design of SMAs to improve the vibrational and structural behavior of composite beam. In the first step, the effect of design parameters of shape memory alloy wires including the number and the diameter of wires on natural frequencies and total mass of structure was studied. In the second step, maximization of the first natural frequency of the structure and minimization of the total weight of the structure was the objective function of multi-objective optimization process which was performed by employing the genetic algorithm and weighted sum optimization approach. The obtained results of optimization processes confirmed the high efficiency of the proposed approach to improve the vibrational and structural properties of Shape memory alloys composite beam. [ABSTRACT FROM AUTHOR]

The present paper applies a multi-objective genetic algorithm for optimally design of a vehicle suspension. The vehicle model considers three-dimensional movements of vehicle body. In this full vehicle model having 8 degrees of freedom, vertical movement of passenger seat, vehicle body, and 4 tires as well as rotational movements of vehicle body create the degrees of freedom of the model. In this paper, applicable suspension parameters, consisting of passenger seat acceleration, vehicle body pitch angle, vehicle body roll angle, dynamic tire force, tire velocity, and suspension deflections are considered and optimized in optimization process. Different pairs of these parameters are selected as objective functions and optimized in multi-objective optimization processes, and Pareto solutions are obtained for pair of objective functions. In final optimization process, the Pareto solution related to the summation of dimensionless parameters in one suspension parameters group versus other group, is derived. In these Pareto solutions, there are important optimum points and designers can choose any optimum points for a particular purpose. Pareto optimization is better than other multi-objective optimization methods because there are more optimum points on Pareto front, where each point represents a level of optimization for the pairs of objective functions, and designers can choose any of the points to specific purpose. [ABSTRACT FROM AUTHOR]

In this research, taking into account the pressure drop of the streams, a simple and useful method is presented for finding the proper path of hot and cold streams inside shell-tube heat exchangers in the synthesis of heat exchangers networks (HENs). Generally, the HENs synthesis by mathematical programming leads to the problems which are answered by Mixed Integer Non Linear Programming (MINLP) methods. Optimization of such formulations results convergence difficulties due to the existence of both continuous and integer variables. In this study, instead of solving simultaneously integer and continuous variables, the genetic algorithm was used to find optimal HEN structure (integer variables). To find optimal values for continuous variables of the network, by categorizing this type of variables into two groups and using Quasi Linear Programming (QLP) instead of the nonlinear programming model (NLP), the complexity of the NLP model solution is also greatly reduced. The optimal values of continuous and integer variables are obtained with respect to a common objective function that reaches the minimum annual cost of the HEN. The comparison of the proposed method with the references shows that this method has the ability to reduce the cost of pumping flows to about 0.76%. [ABSTRACT FROM AUTHOR]

Estimation of discharge as one of the major issues in water resource management and flood control has a key role in the success of water construction design and efficiency of Bio-Mechanical proceeding in catchments. In this research, discharge Peak of Yalphan River has been simulated using three main methods of artificial intelligence (MLP neural network model, subtractive clustering and ANFIS model, and the combination of neural network and genetic algorithm). For this purpose, 8 parameters have been prepared as input data (2001-2012) including precipitation in the event day, precipitations during 5 days before the event day, base flow in the event day and CN map. Peak of flow has been considered as output data of models. RSME, MAE and NSE indicators has been used to assess the artificial intelligence models. Output data of neural network model have been imported to the combined model of neural network and genetic algorithm. Also, output data of subtractive clustering model have been imported to ANFIS model. Finally three models have been assessed using the mentioned indicators. The results showed that the combined model of neural network and genetic algorithm is better than the other models in Yalphan Catchment. [ABSTRACT FROM AUTHOR]

Nowadays distributed generation has been given considerable attention due to the increase in energy consumption and the need for using renewable energies. So, the concept of the micro grids for connecting and coordinating different distributed resources via the local power control systems has been introduced. A micro grid connects to the network at normal condition of the operation but in order to increase the system reliability and to promote the generated power quality to feed the sensitive loads, they can operate in the islanding mode too. In the islanding mode of operation in order to supply the whole load and to maintain the balance between the supply and demand, these resources use the conventional droop methods. Generally, using the conventional voltage droop control due to the difference in the impedance of the feeder connect to the resources and also the asymmetrical nature of the network, dose not lead to an appropriate reactive power sharing between the resources. In fact, using conventional droop control creates an intrinsic compromise between the accuracy of reactive power sharing and voltage regulation of micro grid buses. Therefore, in the proposed method of this paper, the coefficients of the voltage droops characteristics of the grid resources are determined by solving an optimization problem using the genetic algorithm (GA). Also in order to improve the reactive power sharing, a novel control strategy based on the adaptive virtual impedance is presented. In this method the ideal reactive power sharing is achieved by using the virtual impedance and compensating the voltage drop of the lines. The virtual impedance setting is done through the data of the voltage of PCC bus in microgrid and sending via a low bandwidth communicational link to the local controller of each resource. The proposed method is robust against the network structure changes, presence of local loads, and interruption in the communication link. Simulation results show the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Objective: This paper is an attempt to explain the relationship between social factors and tendency to addiction and determine the relationship of this tendency with social insecurity. In addition, the contribution of each of the social factors that lead to social insecurity is determined. Method: The current research method is descriptive. At first the relationship between the research indices (family, neighborhood, unemployment, etc.) and tendency to addiction was described. Then, the relation of this tendency with social insecurity has been expressed. In the following, the contribution of each of these factors in the estimation of social insecurity has been determined. Results: The results showed that the indices under study are significantly correlated with tendency towards addiction and social insecurity. The most important predictors of social insecurity were respectively as follows: other factors (extent of border with Pakistan and Afghanistan, international and regional trafficking activities, the booming market of drugs, etc.), anomic situation, industrialization, family, friends and peers, access to drugs, unemployment, and finally neighborhood. Conclusion: Such variables as family, neighborhood, friends and peers, anomic situation, access to drugs, industrialization, and unemployment play a significant role in social security.

Ongoing sanctions on Iranian economy have proved to be very harmful and detrimental to Iranian economic affairs and social welfare. Evaluating the unfair impacts of these sanctions on Gross Domestic Product (GDP) and social welfare is the aim of this paper. Firstly, we have developed a generalized growth model in the presence of sanctions while treating exchange rate as a random variable. Secondly, three different forms of sanctions are introduced into the model and their bearings on national product and social welfare is studied. The first tier of the sanctions is imposed on consumption, intermediary and capital goods while exchange rate is assumed to have a random behavior. Then sanctions are also imposed on Iranian oil and gas production. We have devised several scenarios using stochastic Hamilton Bellman Jacobian value function (SHBJ) and genetic algorithm optimization methods. Our results of the first and second scenario imply that the level of social welfare is mostly affected by oil and gas sanctions while goods embargo has targeted goods production. The effects of sanctions on GDP and social welfare is represented by a concave curve. This curvature shows that the impact of sanctions on GDP and social welfare is stronger at the beginning than later on when further sanctions are introduced. In the third scenario oil, gas and goods sanctions are imposed simultaneously. Our results also show that the third scenario effects is stronger than the other two. According to the Gross Domestic Product data acquired for year 1390, oil and gas sanctions have lowered the GDP by 30 percent, while the overall reduction in GDP through all sanction collectively is estimated between 30 to 50 Percent.

Actual scheduling problems may necessitate the decision maker to consider a variety of criteria prior to make any decision. This research considers a single machine scheduling problem, with the objective of minimizing a combination of total tardiness and waiting time variance criteria in which the idle time is not allowed. Minimizing total tardiness is always regarded as one of the most important performance criteria in practical systems to avoid penalty costs of tardiness and waiting time variance is an important criterion in establishing Quality of Service (QoS) in many systems. Each of these criteria is known to be NP-hard and therefore the linear combination of them will be NP-hard as well. For this problem, we developed a genetic algorithm by utilizing its general structure. Two types of heuristic and random initial population and two distinct fitness functions are applied to genetic algorithms. The GA is shown experimentally to perform well by testing on various instances.

Given the growth and development of urbanization, natural and man-made disasters, and their impact on metropolitan development, it is essential to provide an innovative solution to preserve the human life. Providing a dynamic model for emergency evacuation of the population in a short time, the scene management, and increased speed and quality of service delivery during and after a crisis are of particular importance. The purpose of this study is to identify and find the best route for evacuation since the chaos caused by the crisis makes serious problems for evacuation. The main problem is that the urban streets are disrupted during an event or disaster and cannot solve the emerged crisis, because in these conditions, most of the routes have been blocked or have lost their effectiveness. The method used in this study is descriptive – analytical. In order to identify effective measures for emergency evacuation, experts’ opinions were used and for ranking the criteria, Expert Choice software was applied in GIS. Genetic algorithm is used because of its simplicity and high speed in analysis of high dimensions networks in order to determine the optimal route to reach the safe areas. To prepare data layers of streets and city blocks and suitable spaces for emergency evacuation with population data of blocks and street widths, GIS database of Kerman municipality was used. The results show that the proposed method finds the shortest path to reach safe areas while taking into account the population density and width of streets. Thus, it can be effectively used for emergency evacuation.

This paper focuses upon the development of an efficient method for conceptual design optimization of a satellite. There are many option for a satellite subsystems that could be choice, as acceptable solution to implement of a space system mission. Every option should be assessment based on the different criteria such as cost, mass, reliability and technology contraint (complexity). In this research, mass and technology constraints, which have a direct impact on the satellite life cycle cost, are considerd as system level objective function to obtain the system optimal solution during the coceptual design phase. The approach adopted in this paper is based on a distributed collaborative optimization (CO) framework. At system level, multiobjective optimization goal is to minimize the dry mass of the satellite and, simultaneously, minimize the system technology complexity which is subject to equality constraints. The use of equality constraints at the system level in CO to represent the disciplinary feasible regions, introduces numerical and computational difficulties as the discipline level optima are non-smooth and noisy functions of the system level optimization parameters.To address these difficulties robust optimization algorithms such as genetic algorithms (GA) are used at the system level. The results show that the CO framework has the same level of accuracy as the conventional All-At-Once approaches.

In this paper, a bi-objective integrated of production distribution planning problem model in a multi echelon supply chain is presented. This model is considered in a four echelon supply chain includes suppliers, manufactures, distribution centers and customers with several types of raw material and product in multi-time period. In addition to minimize the total cost of supply chain including transportation and supply of materials costs, preparation and production of products, inventory holding of materials and products in manufacture and distribution centers, transportation and purchase of products for distributors and customers, and backorder cost, the second objective is to decrease the transfer time of products in order to increasing the service level for customers. Two Pareto-based multi-objective metaheuristic algorithms namely non-dominated sorting genetic algorithm (NSGA-II) and nondominated ranking genetic algorithm (NRGA) are proposed to solve the model. Since the solution quality of all meta-heuristic algorithms severely depended on their parameters, Taghuchi method has been utilized to tune the parameters of algorithms. Finally, computational results obtained by implementing the algorithms on several problems of different sizes demonstrate the performance of proposed methodologies. [ABSTRACT FROM AUTHOR]

Introduction: Early detection of coronary artery disease is critical. Previous studies show that new methods of artificial intelligence for prediction and diagnosis of diseases have been widely considered by the researchers. The purpose of this paper is the classification of angiography to normal and abnormal by using Artificial Intelligent methods. Methods: In this diagnostic study, the datasets were collected from 152 patients who had been undergoing the coronary angiography, and for classification of the angiography results, a combination of fuzzy neural network and genetic algorithm is used. The proposed system was implemented and evaluated by MATLAB software. Results: In implementation of the proposed system, 85% of the data was used for the training phase and the remaining 15 percent was used for the test phase. The results of the simulation in accuracy, sensitivity and specificity indicators on average state were 0.9496, 0.9253, 0.9435 and 0.9569, respectively. Under optimum conditions, an estimate of 1 was obtained for each indicator. Conclusion: The use of genetic algorithms in ANFIS training phase led to improved speed of the simulation. Also the high performance indicators prove that the proposed system is effective for classifying and diagnosing patients with coronary heart disease. [ABSTRACT FROM AUTHOR]

Introduction: Meta-heuristic and combined algorithms have a great capability in modelling medical decision making. This study used neural networks in order to predict Type 2 Diabetes (T2D) among high risk individuals. Methods: This study was an applied research. Data from 545 individuals (diabetic and nondiabetic), in Diabetes Clinic of Hamedan University of Medical Sciences, were used to develop predictive diabetes models. Memetic algorithms which are a combination of genetic algorithm (GA), local search algorithm, and neural networks were applied to update weights and improve predictive accuracy of neural network models. In the first step, optimum parameters for neural networks such as momentum rate, transfer functions, and error functions were examined through trial and error and other studies. Results: The preliminary analysis showed that the accuracy of neural networks was 88 percent. The use of memetic algorithm improved its accuracy to 93.2 percent. Among models, regression model had the least accuracy. For the memetic algorithm model the amount of sensitivity, specificity, positive predictive value, negative predictive value, and area under the curve were 96.2, 95.3, 93.8, 92.4, and 0.958, respectively. These parameters for GA were 98.0, 84.8, 88.6, 98.2, and 0.952 and for the logistic regression model were 95.6, 84.5, 94.7, 87.0, and 0.916, respectively. Conclusions: Models developed by neural networks have a higher predictive accuracy than the regression model. The results of this study can contribute to risk management and planning of health services by providing healthcare decision makers with more accurate predictive models based on clinical and life style characteristics of individuals. [ABSTRACT FROM AUTHOR]

Bankruptcy predication is one of the main matters in classifying the bankrupt corporations. Investors, Owners, Managers, Creditors, Governmental Agencies are interested in evaluating the financial conditions of the companies. Since in the case of bankruptcy, it will cost them a lot. This research intended to study the bankruptcy prediction in Tehran Stock Exchange (TSE) by using the Altman’s Z-model, Genetic Algorithms and finally intends to determine efficiency of the best model. The samples under the investigation were 36 bankrupt companies and 36 non-bankrupt companies during fiscal years of 1384 – 1386. The variables used in Genetic Algorithms Model and Altman’s Z- Model were 5 variables. The Genetic Algorithms Model had respectively an equivalent accuracy between 90, 91.5 percent in average during one year and two years before the indicator year (base year).The Altman‘s Z-Model had equivalent accuracy of 83.32 and 83.32 percent. According to the finding, Genetic Algorithms Model (GAM) was more accurate in predicting bankruptcy as a result; it is an appropriate means for predicting bankruptcy.

Generally, investors consider simultaneously conflicting objectives such as rate of return, risk and liquidity in portfolio selection. On the other hand, every investor has his own specific preferences about objectives. Therefore, we can use Multi Objective Decion Making (MODM) techniques in order to solve portfolio selection problem. The Studies shows that a MODM technique by nonlinear goals such as minimization of nonsystematic risk and skewness maximization isn’t employed for portfolio selection, so a new approach is applied. We employ MODM model to select a best portfolio in 50 superior companies in Tehran stock exchange with regards to optimization objectives of return, systematic risk, nonsystematic risk, skewness, liquidity and sharp ratio. This model is non-convexed, so operational research algorithms can not find the best solution; therefore we use Genetic Algorithms (GA) for achieving nonlinear multi-objective model. In the end, the result of GA is comprised with Markwitz classic model and goal programming (containing linear and nonlinear objectives). The comparison indicates that although return of the portfolio of GA model is less than the other models, but GA has the best results in decreasing risk criteria which completely cover the return and lead to best results. The other advantage of using GA is a higher diversification in its proposed portfolio in comparison with other models.

Active portfolio management is a famous strategy in capital markets. A problem with this strategy is that it ignores the overall portfolio risk. For solving this problem, we examine the impact of adding a new Value at Risk (VaR) constraint to the active management model. In this study, we use Genetic Algorithms for optimization of this model, Sharp Ratio and Return to VaR Ratio for performance measurement of the models. Results show that the new model, in comparison to active model without VaR constraint, has significantly better performance.

In this paper, the continuous Ant Colony Optimization Algorithm (ACOR) is used to investigate the optimum operation of complex multi-reservoir systems. The results are compared with those of the well-known Genetic Algorithm (GA). For this purpose, GA and ACOR are used to solve the long-term operation of a three-reservoir system in Karkheh Basin, southwestern Iran. The solution must determine monthly releases from the three reservoirs and their optimum allocations among the four agricultural demand areas. Meanwhile, a minimum discharge must be maintained within the river reaches for environmental concerns. Review of past research shows that only a few applications of Ant Colony have been generally made in water resources system problems; however, up to the time of initiating this paper, we found no other application of the ACOR in this area. Therefore, unlike GA, application of Ant-Colony-based algorithms in water resources systems has not been thoroughly evaluated and deserves serious study. In this paper, the ACOR is stuided as the most recent Ant-Colony-based algorithm and its application in a multi-reservoir system is evaluated. The results indicate that with when the number of decision variables increases, a longer computational time is required and the optimum solutions found are inferior. Therefore, the ACOR would be unable to solve complex water resources problems unless some modifications are considered. To overcome a part of these drawbacks, a number of techniques are introduced in this paper that considerably improve the quality of the method by decreasing the required computation time and by enhancing optimum solutions found.

To obtain the maximum output power of a fast-axial-flow CW-CO2 laser, gas flow velocity can be optimized by using genetic algorithms. Our theoretical approach shows that the gas flow velocity after optimization increases the laser output power substantially from 500W, obtained in our present system, to 2203W.