جستجوی مقالات مرتبط با کلیدواژه "anfis" در نشریات گروه "علوم انسانی"

By employing urban growth and development modeling, it is feasible to delineate a developmental trajectory that aligns with the specific circumstances of a city, considering environmental factors, natural elements, and population dynamics. The aim of this research is to propose an urban development model for Shushtar, which can serve as a valuable tool for analyzing the intricate processes of urban transformations. To accomplish this objective, two datasets were utilized: urban land use maps (including educational spaces, healthcare facilities, residential areas, etc.) and Landsat satellite imagery for key land uses such as rivers, barren lands, and forests, spanning three time periods: 1991, 2004, and 2014. These datasets were processed using GIS and MATLAB software. Existing urban land use maps were digitized and subsequently updated using Landsat satellite imagery. Subsequently, influential parameters in urban development were introduced as inputs to the Adaptive Neuro-Fuzzy Inference System (ANFIS) algorithm. After training the model for the years 1991 and 2004, the predicted results of urban development using the algorithm were compared with the actual situation in 2014, demonstrating a high accuracy of 93.7%. The land use change map, resulting from the change detection process, can be generated based on multi-temporal remote sensing images and their integration with urban land use maps, enabling an analysis of the associated consequences. The use of intelligent algorithms in this research has facilitated modeling with a high level of accuracy. The obtained results are deemed acceptable, and this development has also been predicted for the upcoming years.

In geodesy, three levels are considered: the physical surface of the earth on which mapping measurements are made, the ellipsoidal reference surface (geometric datum) which is the basis of mathematical calculations, the geoid physical surface (physical datum) which is the basis for measuring heights. Satellite positioning systems measure the height of points relative to the ellipsoid surface. The geoid is one of the equipotential surfaces of the earth's gravity field, which approximates the mean sea level (MSL) by least squares. Geoid is very important in geodesy as a representative of the physical space or the space of observations made on the earth and also as the base level of elevations. The separation between the geoid and the geocentric reference ellipse is called geoid height (N). Although there is only one equipotential surface called geoid, various methods are used to determine it. These methods include: geometric method, geoid determination by satellite method, Gravimetric methods and geoid determination using GPS/leveling.

In this paper, the aim is to estimate the height of the local geoid using machine learning models. To do this, artificial neural network (ANN), adaptive neuro-fuzzy inference model (ANFIS), support vector regression (SVR) and general regression neural network (GRNN) models are used. The geodetic coordinates of 26 GPS stations in the north-west of Iran along with their orthometric height (H0) and normal height (h) were obtained from the national cartographic center of Iran. In all stations, the difference of orthometric height and normal height is considered as geoid height (N). Therefore, the geodetic longitude and latitude of the GPS stations are considered as the input of the machine learning models, and the corresponding geoid height was considered as the output. In order to test the results of machine learning models, two modes of 4 and 7 test stations are considered. Also, the output of the models is compared with the local geoid model IRG2016 presented by Saadat et al. for the Iranian region and also the global geoid model EGM2008.

Due to the availability of a complete set of observations of GPS stations along with orthometric height obtained from leveling in the north-west region of Iran, the study and evaluation of the models proposed in the paper has been carried out in this region. Observations of 26 GPS stations of North-west of Iran were prepared from the national cartographic center (https://www.ncc.gov.ir/). Two modes are considered for training and testing of ANN, ANFIS, SVR and GRNN models. In the first case, the number of training stations is 22 and the number of test stations is 4. But in the second case, by increasing the number of test stations to 7 stations, the error evaluation of the models has been done. It should be noted that the distribution of training and test stations is completely random. After the training step of machine learning models and choosing the optimal structure, the test step is performed in two different modes (4 and 7 stations). At this step, the value of the geoid height in the test stations is estimated and compared with the value obtained from the difference of orthometric height and normal height as a basis. Two statistical indices of relative error in percentage and RMSE in centimeters were calculated for all models and presented in Table (1) for the first case.Table 1. Relative error (%) of ANN, ANFIS, SVR, GRNN and IRG2016 models in the test stations considered for the first case According to the results of Table (1) and comparing the relative error values of all models in the test stations, it shows that the ANFIS model was more accurate than other models. After ANFIS model, IRG2016 model has higher accuracy than ANN, SVR and GRNN models. It should be noted that the IRG2016 local model uses the observations of all Iranian plateau stations to model the local geoid, and therefore it is expected that this model will be more accurate in the study area than other models.

The evaluations show that in the case of 22 training stations and 4 test stations, the RMSE of ANN, ANFIS, SVR, GRNN and IRG2016 models in the test step are 37.32, 19.83, 49.34, 53.82 and 29.65 cm, respectively. However, in the case of 19 training stations and 7 test stations, the error values of the models are 36.63, 58.31, 39.64, 41.29 and 24.68 cm, respectively. Comparison of RMSE shows that ANN model with less number of training stations provides higher accuracy than ANFIS, SVR and GRNN models. The results of this paper show that by using ANN and ANFIS models, geoid height can be estimated and used with high accuracy locally in civil and surveying applications.

The spillover of defense technologies in commercial businesses has an effective role in the development of technology, production, employment and economic growth of the country. The main purpose of this study is to design a model to evaluate and forecasting of defence technologies spillover to civillian with ANFIS. The research statistical population includes experts in the field of defence and civillian. The research is applied research in terms of method and according to the use of fuzzy inference system for modeling, it is of mathematical modeling type. The difference between the output values of ANFIS and the input data to an acceptable level of 6.6252*10-7 (the average error calculated in the model training stage) indicates the approximate compliance of the real data with the predicted data and implies It is designed on the lack of over-fitting phenomenon in ANFIS. In other words, the obtained model has a high power of prediction and we see a positive effect on the modeling ability to generalize. policies and laws with a weight criterion of 28.82% have the highest impact on the research model and it is necessary to consider the necessary policies and laws to make optimal use of the technological capabilities of the defense sector in the civilian sector. Also, communication factors, technological capability, environmental factors, socio-cultural factors, economic-financial factors and technological characteristics affect the model, respectively.

Financing is one of the factors of future success for small and medium-sized technology businesses. Because of the immaturity of these businesses, the majority of their assets are intangible, rely on technical knowledge, and lack significant financial and credit records. To control the probable risks, financing systems traditionally rely on patterns based on maximum authentication of physical assets, which do not fulfill the needs of these firms and must be altered. The fundamental purpose of this research is to create a model for assessing and determining the collaterals of technical projects and knowledge-based firms so that finances could be more easily obtained and the risk of non-refunding could be managed. In this research, in the first step, the criteria for evaluating and assessing the intended project and company were defined. By using a fuzzy expert system, the appropriate method of dealing with companies was determined. In the second step, in order to create a learning system, the results of the first step were used as input data in the form of three neural network algorithms implemented in MATLAB software and ANFIS algorithm, with 93% accuracy compared to the input data.

The final neuro-fuzzy model was tested according to the repayment data available in Iran National Innovation Fund. The statistical population included knowledge-based firms receiving facilities. By using The Cochran formula, 103 companies were selected as a sample. The results obtained by testing and evaluating the model, in 85% of cases, could correctly identify the companies' performance in repaying resources and suggest appropriate collateral (Real estate collateral or Bank Guarantees).

The model presented in this study can be used to evaluate, validate, and determine the collaterals of technological projects and knowledge-based firms. It can facilitate their access to financial resources and also help them with managing the attendant risks. It also employs new optimization methods and has the ability to learn.

Iran Stock Exchange has developed a lot in recent years. Today, the importance of forecasting and its benefits for decision-making and policy-making from various dimensions, especially in the field of investment, is not hidden from anyone. Risk is one of the first concerns of investors and is an important criterion in decision making. Value at risk as a risk measure has given way to measuring a variety of risks, but despite the high efficiency of this model due to some shortcomings, including the lack of aggregation feature of a coherent risk measure. Conditional Risk Value (CvaR) is considered as a coherent risk measure that has recently been welcomed and has been proposed as a useful tool for measuring risk.To predict the risk, various models have been presented so far, each of which has its strengths and weaknesses. Some of them are weak in terms of lack of appropriate theoretical foundations and others have not shown proper efficiency in practice despite using appropriate theoretical foundations. Provide adequate empirical risk assessment that helps both investors and anticipate unexpected risks that may threaten companies. In recent years, much attention has been paid to the application of neural network models and hybrid models. In the present study, a combined model of coherent risk prediction is presented and developed using fuzzy neural network inference system (ANFIS) based on Markov switching models and Garch family models.

In this research, the prediction of Peak Ground Acceleration (PGA) is investigated through training the Adaptive Neuro Fuzzy Inference System (ANFIS) network using data partitioned into inlier and outlier groups. The partitioning procedure is based on an automated method which uses K Nearest Neighbor (KNN) search and Local Linear Model Tree (LOLIMOT) methods. The mentioned proved to enhance the prediction procedure at least 36 percent with respect to normal training mode with no data partitioning. Hereafter, a PGA catalogue reported by the Iranian ground acceleration network with 1571 records was used and the trained network was used for predicting the PGA map around the Mormori, 2014 earthquake epicenter. We used spatial information of the epicenter and the site, earthquake magnitude, Vs30, depth of the hypocenters and the epicentral distance foe the sites. The resulted map adapts well to the official report of the mentioned earthquake for the PGA analysis published by the International Institute of Earthquake Engineering and Seismology (IIEES). Finally, it is concluded that using machine learning algorithms could be beneficial in the cases where adequate data-sets are not provided by the seismological networks specifically in the concept of the strong ground motion analysis.

The Earth's atmosphere (atmosphere) is divided into concentric layers with different chemical and physical properties. To study wave propagation, two layers called the troposphere and ionosphere are considered. The troposphere is the lowest part of the Earth's atmosphere and extends from the Earth's surface to about 40 kilometers above it. In this layer, wave propagation is mainly dependent on water vapor and temperature. Unlike the ionosphere, the troposphere is not a dispersive medium for GPS signals (seeber, 2003). As a result, the propagation of waves in this layer of the atmosphere does not depend on the frequency of the signals. The delay caused by the troposphere can be divided into two parts of hydrostatic delay and wet delay. The hydrostatic component of the tropospheric delay is due to the dry gases in this layer. In contrast, the wet component of tropospheric refraction is caused by water vapor (WV) in the troposphere. The study of atmospheric water vapor is important in two ways: First, short-term climate change is highly dependent on the amount of atmospheric water vapor. Water vapor has temporal and spatial variations that affect the climate of different regions. Second, long-term climate variation is reflected in the amount of water vapor. Obtaining water vapor using direct measurements and water vapor measuring devices is a difficult task. Radiosonde and radiometers are used to directly measure atmospheric water vapor, but the use of these devices will have problems and limitations, for example, the maintenance cost of these devices is expensive and also these devices do not have a suitable station cover. The best way to get information about water vapor changes indirectly is to use GPS measurements. GPS meteorological technology can provide continuous and almost instantaneous observations of the amount of water vapor around a GPS station.Estimation of precipitable water vapor (PWV) and water vapor density using voxel-based tomography method has disadvantages. The coefficient matrix of tomography method has a rank deficiency. Initial value of water vapor must be available to eliminate it. Also, the amount of WV inside each voxel is considered constant, if this parameter has many spatial and temporal variations. In this method, the number of unknowns is very high and it is computationally difficult to estimate (Haji Aghajany et al., 2020). To overcome these limitations, this paper presents the idea of using learning-based models. To do this, in this paper, 3 models of artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS) and support vector regression model (SVR) have been used.

Due to the availability of a complete set of observations of GPS stations, radiosonde and meteorological stations in the north-west of Iran, the study and evaluation of the proposed models of the paper is done in this area. Observations of 23 GPS stations were prepared in 2011 for days of year 300 to 305 by the national cartographic center (NCC) of Iran. Out of 23 stations, observations of 21 stations are used to training of models and observations of the KLBR and GGSH stations are used to test the results of the models. In the first step, the observations of 21 GPS stations that are for training are processed in Bernese GPS software (Dach et al., 2007) and the total delay of the troposphere in the zenith direction (ZTD) is calculated. It should be noted that for every 15 minutes, a value for ZTD is calculated using the observations of each station. In the second step, the zenith hydrostatic delay (ZHD) is calculated. By subtracting ZHD from ZTD, zenith wet delay (ZWD) are obtained. ZWD values are converted to PWV values. The obtained PWV values are considered as the optimal output of all three models ANN, ANFIS and SVR. Also, the input observations of all three models will be the latitude and longitude values of each GPS station, day of the year and time.

After the training and achievement of the minimum cost function value for all three models, the PWV value is estimated by the trained models and compared at the location of the radiosonde station as well as the test stations. The mean correlation coefficient for the three models ANN, ANFIS and SVR in 6 days was 0.85, 0.88 and 0.89, respectively. Also, the average RMSE of the three models in these 6 days was to 2.17, 1.90 and 1.77 mm, respectively. The results of comparing the statistical indices of correlation coefficient and RMSE of the three models at the location of the radiosonde station show that the SVR model has a higher accuracy than the other two models. The average relative error of ANN, ANFIS and SVR models in KLBR test station was 14.52%, 11.67% and 10.24%, respectively. Also, the average relative error of all three models in the GGSH test station was calculated to be 13.91%, 12.48% and 10.96%, respectively. The results obtained from the two test stations show that the relative error of the SVR model is less than the other two models in both test stations.

The results of this paper showed that learning-based models have a very high capability and accuracy in estimating temporal and spatial variations in the amount of precipitable water vapor. Also, the analyzes showed that the SVR model is more accurate than the two models ANN and ANFIS. By estimating the exact amount of PWV, the amount of surface precipitation can be predicted. The results of this paper can be used to generate an instantaneous surface precipitation warning system if the GPS station data is available online.

In recent years, knowledge management has become a fundamental principle in the field of management. Since the introduction of knowledge management, many institutions have tried to measure the benefits of using this concept. Success in implementing knowledge management and continuing its usage largely depends on measuring knowledge management benefits. However, few studies were conducted on this issue. This study, by using the adaptive neural fuzzy inference method (ANFIS) via Matlab 2017 software, tried to provide a predictive model to measure the benefits of knowledge management in the organization. The study population consists of scientists and experts working in 15 branches of the Social Security Organization, with a minimum of five years of experience in knowledge management related tasks. Based on the results, the degree of compatibility of the estimates with the actual results and the predictability and accuracy of the results were discussed, and at the end, based on the results, guidelines were provided to the studied organization.

Choosing the appropriate distribution channel for companies is one of the main marketing activities in the supply chain. Accordingly, the purpose of this study is to design a system for predicting success of the distribution channel in the supply chain of the petroleum industry using ANFIS and the PSO algorithm for the national oil products distribution company in the two regions of West Azerbaijan Province. The research method was descriptive-modeling and the statistical population of this research included all the locators in the two regions (south and north) of West Azerbaijan.  We collected data in this research through a questionnaire and documents of the National Oil Distribution Company of West Azerbaijan.  We analyzed the data in this study through combining neuro.

Landslides are one of the most important environmental processes, especially in mountainous landscapes. Identifying sensitive areas and preparing a landslide risk zoning map is an important step in preventing and reducing the damage caused by this phenomenon. Hashtjin basin, with its mountainous face and considering the geological, lithological, climatic and human conditions, has the necessary conditions for the formation of landslides; therefore, the current study aims at landslide risk zoning in the given area. Therefore, landslide sensitivity analysis for Hashtjin watershed is evaluated according to the efficiency of the results obtained from two models of logistic regression and Anfis to achieve the research goal. Using the interpretation of aerial photographs and field visits, control areas, as a dependent variable, were recorded by GPS. Then, the factors affecting landslides in the area including slope, direction, elevation lines, distance from waterway, distance from fault, distance from road, geology, land use and rainfall were identified according to various sources, field studies and consultation with experts; Then, layers were prepared as independent variables in GIS Arc environment. Moreover, logistic and ANFIS regression models were implemented by entering the aforesaid layers into TERRSET and MATLAB software environment, respectively. The final landslide hazard map of the area was prepared in 5 hazard classes. In this study, 25% of the control samples were used as test data to measure the accuracy of the studied models. The results of validation of the performance of the mentioned models by performing the ROC curve showed that the accuracy of Anfis model and logistic regression were equal to 88.23 and 86.45%, respectively. The findings from Enfis model reveal that approximately 4854 hectares, equivalent to 20.6% of the Hashtjin area are in high and very high class in terms of landslide risk.

The effect economic variables at investment markets is the important subject in financial theory. Tehran stock exchange to have special position in country financial system and efficiency development investment market is dependent being active this constitution in country. Two important function Tehran exchange market are gathering small savings and available liquidity in society and guide them to production process in country. In this way presentation optimization portfolio model from market index prediction model and exchange return rate is impact. One of the tools with high accuracy and applicable for predicting was neural network why so accuracy isnot decrease with increasing thesis data and its accuracy was very higher than regeression, linear and non linear for prediction. After some tests from artificial neural network and adaptive neuro fuzzy inference system and support vector regression with matlab software has been done. We design a model with high accurancy for predicting rate of liquidity index and total return index and then we design Ideal optimization portfolio.

Over the past few decades, the number of universities has grown exponentially, but many of them are financially constrained. In the meantime, financial performance appraisal can support university administrators in making appropriate decisions by recognizing financial status. Accordingly, the purpose of this study was to codify a model for evaluating the financial performance of the university. This research has been applied in terms of the purpose, applied-developmental research and descriptive research in terms of the method which has been done intermittently. The statistical population of this research was all units of Islamic Azad University throughout the country. The statistical sample size was selected based on Morgan's table of 214 units of IAU. To collect data from the questionnaire, the Delphi method and the existing university documents were used. In order to analyze the research data, from Delphi methods and adaptive neuro-fuzzy inference system, adaptive neuro-fuzzy inference system combined with genetic algorithm and adaptive neuro-fuzzy inference system combined with a particle swarm optimization have been used. The research results show that among the designed systems, adaptive neuro-fuzzy inference system combined with a particle swarm optimization with the least error is able to evaluate and predict the financial performance of the university.

Social vulnerability is the creation of structural relationships between groups and forces of society against various pressures of nature and decisions and the capacity of society to respond and react to environmental hazards. Attracting immigrants with different geographical origins is one of the most important factors affecting the diversity of social structure and intensifying the sense of place in the city of Karaj. Research shows that in some areas of Karaj, such as Hesarak neighborhood (districts 5 and 6), due to the physical structure, especially the economic, social, cultural and marginal characteristics of residents, the opportunity for social harm is higher compared to other parts of the city. Due to the importance of this issue, the present study seeks to provide a model for social vulnerability indicators of this neighborhood to determine the pattern of these indicators and the impact of each of them on the satisfaction or dissatisfaction of residents of the neighborhood. The research method was analytical-exploratory in nature and the total population of households in the 5th and 6th districts of Karaj and the sample size were calculated using the Cochran's formula of 350 people.The research data were collected randomly from the study area through a query technique and using artificial neural network and infusion inference system to intelligent modeling (rule base) and tree regression model to estimate the factors affecting vulnerability. paid. The proposed model in this research is significant from several dimensions; The first result is the presentation of a methodology in this field that has been done with special architecture and the use of computational intelligence and environmental assessment knowledge base, and the second result is the creation of a knowledge base based on a set of criteria that can be intelligently Pay attention to the environmental conditions to assess the situation of the region as well as similar cases.

Introduction :

Drought is one of the most important natural disasters affecting agriculture and water resources, and its abundance is extremely high in arid and semi-arid regions (Shamsenya et al., 2008: 165). Drought is a natural phenomenon that has a complex process due to the interactions of various meteorological factors and occurs in all climatic conditions and in all regions of the planet (Samandianfard & Asadi, 2017). According to the domestic and foreign studies, many researchers have conducted research on drought monitoring and prediction, but the research that can show the drought phenomenon more accurately with the future vision is not takenhas not been conducted if both do not cover the issue adequately. According to the researchers, this study was conducted to model, monitor and predict drought with the new method in Iran in this study.

In this study, drought modelling in Iran was carried out using climatic data of rainfall, temperature, sunshine, relative humidity and wind speed monthly (for 6 and 12 months scale) for the period of 29 years (1990-2018). At 30 stations using the new TIBI architecture model, a fuzzy set of four indicators (SET, SPI, SEB, and MCZI) valid in the World Meteorological Organization was used. For modelling the new TIBI index, the climatic data were first normalized, then four indices (SET, SPI, SEB, and MCZI) were calculated separately and the fuzzy modelling of the four indices was performed in the Matlab software and eventually to prioritize the drought-affected areas, the multivariate decision-making model, TOPSIS was used.

In order to investigate the effect of drought fluctuations in drought conditions of stations, it is possible to determine the changes in the indicators (SET, SPI, SEB, and MCZI) in the TIBI index analysis. Considering the large number of stations studied, For better understanding, only the drought series diagrams were presented at Bojnourd station on two 6 and 12 month scales (Figures 7 and 8),, (in the mentioned figures, the red arrow shows the drought margin at a 6-month scale with a value of 0.44 and greater, and a value of 0.76 and greater within the 12-month scale. The analysis of these forms shows that at the 6-year and 12-month scale at Bojnourd station, the amount of evapotranspiration was similar in drought conditions, which decreased from April 1994 to February 1999, and after this month an increase was observed if the impact of rainfall on a 6-month scale is weaker than the 12-month scale. It means that from May 1993 to November 1997, an increasing trend followed by the same pattern, and the indicators (SET, SPI, SEB, and MCZI) affect the TIBI index and show some trends, indicating that the new TIBI fuzzy index reflects the four indicators well. The T.I.B.I index at the 6-month scale shows a sharper shape than the scale 12.Prioritization of the stations involved in drought in Iran was analyzed using the TOPSIS model. The results of the TOPSIS model implementation using the degree of importance of the criteria derived from the entropy method indicate that, in terms of drought, more and fewer places are involved with drought by combining the two 6 and 12-month scale. According to the TOPSIS multivariate decision-making model, it was determined that the three stations most affected by drought based on the TOPSIS model were Bandar Abbas, Ahvaz and Bushehr, respectively, in the south and southwest regions of Iran with priority points of score (1, 0.78, and 0.62 respectively), and the three stations of Gorgan, Shahrekord and Orumieh in the northern and western parts of Iran with the scores of 0.026, 0.033 and 0.035 had lower priorities for drought response, respectively (Table 6) and (Figure 11).

Drought is a natural disaster that is gradually evolving under the influence of climatic anomalies over a long period of time. In recent years, various parts of the Middle East have faced drought, including those regions of Iran in Southwest Asia. In this study, drought phenomenon was assessed at 6 and 12 months using the new fuzzy index T.I.B.I. The results of the research showed that the total frequency of droughts in the 12-month scale was more than 6 months but the severity of a 6-month-old drought is more than 12 months old. On a 12-month scale, the number of drought repetitions is more than 6 months. Drought persistence was higher at 12-month scale, droughts were shorter at short-term and affected by temperature parameter. However, the intensity of drought over a long period of time had a slower response to rainfall changes. The highest percentage of drought incidence in scale of 6 months; Bandar Abbas, Bushehr, Ahvaz and Zahedan stations in the southern half of the study area respectively with the of drought (16.62, 11.24, 14.13 and 62.6 and the lowest in the 6-month scale were Urmia and Ardebil stations, with the percentages of 1.10 and 1.88, Ilam and Yasuj with the drought frequency of 1.61 and 2.01, Rasht and Gorgan, with a high percentage of drought frequency (1.26 and 0.87) in the northern and western part of Iran. The highest percentage of drought occurrence in scale 12; Bandar Abbas and Bushehr stations respectively with drought frequency of 24.30 and 14.83, Ahvaz with drought severity of 18.47, Kerman with 6.74 percent of drought frequencies in the south and southwest of Iran and the lowest in the 6-month scale; stations of Birjand (1.70), Bojnurd (66.6), Urmia (1.17), and Tabriz (66.2) in the northwest of Iran, Rasht (0.58), Sari (0.78) in the northern part of Iran.

In this paper, Symbiotic organism search and memetic algorithms are used to solve constrained mean-semi variance portfolio problem. Then AR model, Neural network and ANFIS are compared to predict expected return of stocks. 23 active stocks from June 22, 2014 to Jan 21, 2016 are used as our sample. The results indicate that, memetic algorithm despite its longer time consuming has better performance than SOS algorithm. And ANFIS has more accurate prediction than others in predicting expected rate of return. Finally, we compare expected and real efficient frontier, the results indicate that, in lower risk, ANFIS has better prediction accuracy. So in that area, we can allocate our asset with higher certainty.

In recent years, there has been an increase in the likelihood of the occurrence of the risks and unexpected events. As a result, supply chains are more vulnerable to disruption and the risk to supply chain continuity has increased. The ability to manage risks and disruptions is one important aspect that differentiates successful business leaders from others. The present research therefore attempts to conceptualize the concept of supply chain continuity and design an Adaptive Neuro-Fuzzy Inference System (ANFIS) to evaluate the continuity of IKCO supply chain. Hence, a systematic literature review is conducted to identify and explore appropriate capabilities and strategies that can be employed to build continuity in a supply chain. Then, ANFIS approach is used to evaluate the continuity of IKCO supply chain. The results indicate an average condition based on the proposed model.

The results of model evaluation during training and testing demonstrated significant accuracy differences between various models. Results showed that in the ANFIS, minimum of R2 in SPI-3 was 0.59, in hyper-humid climates (Ramsar and Bandar-e-Anzali) and maximum of R2 in SPI-3 was 0.78, in hyper-arid climate (Zahedan) and humid climate (Yasuj). Also minimum of R2 in SPI-6 was 0.75, in semi-arid climate (Hamedan) and maximum of R2 in SPI-6 was 0.87, in hyper-arid and arid climates (Zahedan and Mashhad). In SPI-12, minimum of R2 was 0.88, in hype-arid and semi-arid climates (Zahedan and Hamedan) and minimum of R2 was 0.97 in arid climates (Mashhad). Also, results of ANFIS showed that membership functions type and climates type don't have effect on ANFIS performance and when model is using precipitation in two delay step and SPI in 3 delay step, it has acceptable and high accuracy results. In the GMDH, R2 is between 0.91-0.99 in all three SPI scales (SPI-3, SPI-6 and SPI-12) and in all climates which it indicates the acceptable accuracy of this model. In order to evaluate the results of GMDH models, the best models related to M4 and M9 that input variables are {SPI(t-1), SPI(t-2), SPI(t-3), SPI(t-4), SPI(t-5)} and {SPI(t-1), SPI(t-2), SPI(t-3), SPI(t-4), SPI(t-5), P(t-1), P(t-2)}. RMSE values indicated that it increases when climate type is changing. Hyper-humid and humid climates have RMSE more than other climates. It related to precipitation effect in models performance. M5 and M6 models that use just precipitation in the previous months have low performance in drought forecasting. Also results indicate that SPI is appropriate for 12-month scale. In fact, the performance of the models has direct relationship with the increasing of the SPI time scale. Finally, The results of the comparison of observed and calculated values of three SPI scales (SPI-3, SPI-6 and SPI-12) using the GMDH model in all climates showed that drought forecasting is reliable when this method used and it'll use possibility for future drought forecasting. In general, the results are accurate when using ANFIS and GMDH but the performance of the GMDH model is better than other model. Also, execution speed and GMDH calculations are far more than the ANFIS. Finally, in this study, GMDH propose as the best model for drought forecasting