adaptive neural fuzzy inference system (anfis)

The purpose of this research is to design a model to evaluate the level of digitization of the innovation process centered on artificial intelligence in knowledge-based companies, so that the digital maturity of the innovation process in an organization can be measured. The results of 188 indicators were distributed in the form of a 5-point Likert questionnaire and by Delphi method in two times among 18 experts in this field. The result of the work was 5 components as input to the model, which was sent in the form of a questionnaire to 230 knowledge-based companies of Pardis Technology Park. 198 companies completed it and sent it back. From this number of samples, 150 data were separated for training data and 48 data as model test based on a random function. In the last stage, i.e. modeling, the adaptive neural-fuzzy inference method was used for the model. The method of grid separation or lookup table (PG) in MATLAB 2023 software was used to evaluate the performance of the model using root mean square, error (RMSE) and relative error (E). This research was able to provide an intelligent model with a very low error. As a result, it was able to achieve effective indicators in the degree of digitization of the innovation process.

In today's competitive world where innovation is a condition for the survival of any organization, it is important to know the level of innovation capacity of the organization's resources, which is related to organizational policy, technology transfer, life and competition of the organization. The main purpose of this research is to design a model to determine and predict the level of innovation of organizational resources. After reviewing the available sources and interviewing experts, using confirmatory factor analysis, 12 main indicators in the form of 3 dimensions were determined as input to the fuzzy inference system. Among the new modeling methods, fuzzy systems have a special place in various sciences. Neuro-adaptive fuzzy inference system (ANFIS) is a good way to solve nonlinear problems. This method is a combination of fuzzy inference and artificial neural network that uses the ability of both to model. Using three types of model design methods in the fuzzy system and comparing the results, the best result for presentation was determined. To evaluate the performance of the model, the parameters of squared mean square error (RMSE), relative error percentage (ε), mean absolute error (MAE) and coefficient of determination (R2) were used, which were 0.047, 1.02%, 0.046 and 989 / Is achieved and indicates the accuracy and reliability of the model. This research is applied in terms of purpose and survey type according to the data collection method. The output of this study is ANFIS.

This paper aims to design and regulate the Adaptive Neural Fuzzy Inference Systems (ANFIS) of supplier development, determine the importance of different categories of supplier development (SD), and suggest appropriate activities based on the results for the development of suppliers in the automotive industry.

To design ANFIS, Grid Partitioning, Subtractive Clustering, and FCM have been used. Then, they have been regulated using Back Propagation (BP), Hybrid, Ant Colony Optimization (ACO), Differential Evolution (DE), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO) methods. A five-step procedure has been used for sensitivity analysis of the supplier development categories. By comparing the results of the regulated systems, the most appropriate ones were selected. Also, based on the supplier development score in different categories separately, the supplier development score was predicted for 53 strategic suppliers in the automotive industry. By sensitivity analysis, SD-related categories were prioritized to guide automotive industry manufacturers to use SD-related activities.

Findings indicated that the FCM compared to the other two methods; meta-heuristic regulation methods compared to BP and Hybrid, and ACO, DE, and GA compared to PSO led to better results. The ACO in all systems, the DE in four systems, and the GA in two categories were identified as the dominant methods, while the PSO was not dominant in any of the categories. This finding implies the priority of meta-heuristic algorithms as ACO> DE> GA> PSO, based on the data of this study. The results of the correlation between the scores of the ANFIS and the average scores of the experts show that the designed ANFIS has high accuracy.Practical implications: The results of this study will direct manufacturers' investments and direct involvement in SD. The findings encourage manufacturers and suppliers of the Iranian automotive industry first to activities related to the development of environmental capabilities and then activities related to the development of three other categories. The managers of Iran's automotive industry are suggested to apply the activities related to the development of suppliers' environmental capabilities. These activities include evaluating the supplier's environmental performance and feedback, sharing environmental information, ethics and social responsibility, obtaining environmental and social certifications, developing programs to improve the quality of life of target communities, green procurement, and environmental awareness, logistics activities Inversion, and joint efforts to improve performance are sustainable.

This study was one of the first in-house studies to compare the results of meta-heuristic algorithms compatible with ANFIS in the field of SD. In addition, in terms of implementation, it offered suitable SD activities to car manufacturers.

In recent years, knowledge management has become a vital issue in all organizations. Knowledge management is one of the effective factors in creating and expanding innovation. With innovation, the long-term advantages of the organization are maintained in the competitive arena. Evaluating and predicting the level of knowledge management for managers is very important. Among the new methods of modeling, fuzzy systems have a special place in different fields of science. The purpose of this research is applied and according to data collection method is survey. The Neural-Adaptive Fuzzy Inference System (ANFIS) is a good method for solving nonlinear problems. This method combines fuzzy inference method and artificial neural network which benefits from both methods. In this study, five main components were selected as inputs for fuzzy inference system to measure and predict the level of knowledge management of the organization. For evaluating the model performance, the parameters of mean square error of error (RMSE), percentage of relative error (ε), mean absolute error (MAE) and coefficient of explanation (R2) were used. Their values are 0.12, 0.0152%, 0.036 and 0.995. This indicates the accuracy and reliability of the model. The output of this study is the neural-adaptive fuzzy inference system (ANFIS).