In recent years, using fuzzy sets theory in modeling of complex and uncertain hydrological phenomena has attracted research workers. For this reason, in this research for river flow forecasting, we have used models of FIS and ANFIS which are based on fuzzy logic. Data of daily flow discharges were provided from Lighvanchay watershed for 6 years. For considering the randomness of data, return points test was used. Then correlogram of data was employed to determine the input optimum models and finally 5 models of discharge forecasting designed based on previous days' discharge. The results showed that ANFIS was more precise and less disperse (RMSE=0.0234) with compare to FIS (RMSE=0.1982). The ANFIS was also more precise in peak discharges simulation than FIS.

Rainfall-runoff process is physical phenomena that their investigation is very difficult due to effectiveness of different parameters. Various methods have so far introduced to analyze these phenomena. This study has been aimed to investigate performance of wavelet-Adaptive neuro-fuzzy inference system (wavelet-ANFIS) and Adaptive neuro-fuzzy inference system (ANFIS) for simulation of rainfall-runoff process involved with snow water equivalent (SWE) in Latyan watershed located in Tehran province. For this reason, 92 MODIS images have provided by NASA website during three water years 2003-2005, snow cover area in all images has been extracted and finally SWE values have been calculated for the mentioned years. Also, the rainfall, temperature and discharge data for the mentioned years is available which has been used for modeling. The results showed that wavelet-ANFIS with rainfall, temperature and discharge inputs and 1-day delay these inputs with root mean (RMSE) of 0.006 and coefficient of determination (R2) of 0.97 had more effeciency than ANFIS by grid partitioning with rainfall, temperature and discharge inputs with RMSE of 0.059 and R2 of 0.62 and ANFIS by subtractive clustering with rainfall, temperature and discharge inputs with RMSE of 0.059 and R2 of 0.65. The results Also showed that SWE involvement causes to increase the accuracy of models.

One of the most significant threats of a national economy is the bankruptcy of its firms. Assessment of bankruptcy provides valuable information on which governments, investors and shareholders can base their financial decisions in order to prevent possible losses. The aim of this study was to model bankruptcy by using Adaptive Neuro fuzzy inference system (ANFIS). Statistical society for performing of this research is companies which were listed at Tehran Stock Exchange since 2001 up to 2010 and according to article 141 of commercial code, including 40 bankrupt companies and 40 non bankrupt companies. These companies were divided randomly in three sets: train set for creating model, test set and check set for validating model. financial ratios of the companies in the year before bankruptcy were considered as input variables ANFIS. The result of this study points out that percentage of success predictions one year before bankruptcy is 83.75. Finally, according to this study, the ANFIS selection is helpful to predict the financial distress situation for companies which were listed at Tehran Stock Exchange.

fuzzy inference systems have been successfully applied for different pattern recognition problems. However, in some real-world applications such as facial expression recognition, the uncertainties related to the feature space may be so high that it is hard to model the feature space by fuzzy membership functions. On the other hand, it is believed that type-2 fuzzy sets have high potentials of uncertainty management in the space of features. However, adjusting the parameters of Type 2 membership functions is a difficult task. In this paper, we analyze the effect of incorporating type-2 fuzzy system into facial expression recognition problem. In this regard, two Adaptive type-2 fuzzy models are proposed. The first model employs interval type-2 Mamdani fuzzy system for constructing fuzzy face space and uses Genetic Algorithm for optimizing the membership functions parameters. The second model is an interval type-2 Neuro-fuzzy system which contains interval type-2 fuzzy sets as membership functions. In this case, the gradient descent algorithm is utilized for tuning the parameters of this system. Numerical results demonstrate the superiority of type-2 fuzzy systems with respect to the corresponding type 1 systems and show that the proposed systems can better cope with the uncertainties in facial expression recognition.

Nowadays, in turbulent and violate global markets, agility has been considered as a fundamental characteristic of a supply chain needed for survival. To achieve the competitive edge, companies must align with suppliers and customers to streamline operations, as well as agility beyond individual companies. Consequently Agile Supply Chain (ASC) is considered as a dominant competitive advantage. However, so far a little effort has been made for designing, operating and evaluating agile supply chain in recent years. Therefore, in this study a new approach has been developed based on Adaptive Neuro fuzzy inference system (ANFIS) for evaluating agility in supply chain considering agility capabilities such as Flexibility, Competency, Cost, Responsiveness and Quickness. This evaluation helps managers to perform gap analysis between existent agility level and the desired one and also provides more informative and reliable information for decision making. Finally the proposed model has been applied to a leading car manufacturing company in Iran to prove the applicability of the model.

This paper employs Adaptive Neuro-fuzzy inference system (ANFIS) to predict water level that leads to flood in coastal areas. ANFIS combines the verbal power of fuzzy logic and numerical power of neural network for its action. Meteorological and astronomical data of Santa Monica, a coastal area in California, U. S. A., were obtained. A portion of the data was used to train the ANFIS network, while other portions were used to check and test the generalization ability of the ANFIS model. Water level predictions were made for 24 hours, 48 hours and 72 hours, in which training, checking and testing of the model were performed for each of the prediction periods. The model results from the training, checking and testing data groups show that 48 hours prediction has the least Root Mean Square Error (RMSE) of 0. 05426, 0. 06298 and 0. 05355 for training, checking and testing data groups respectively, showing that the prediction is most accurate for 48 hours.