fuzzy inference system

Upper-limb exoskeleton robots have a significant impact on rehabilitation, assistive technology, and human augmentation, as they can restore or enhance human physical abilities. This paper presents a novel control approach, called Adaptive Fractional Integral Terminal Sliding Mode (AFITSM), which combines an exponential reaching law with a unique interval type-2 Fuzzy Inference System (FIS). This controller is designed to achieve zero-force control of a 5-degree-of-freedom upper-limb exoskeleton robot, even in the presence of bounded uncertainties. The controller's integral terminal sliding surface ensures that the system converges in a finite time, allowing the exoskeleton to reach its desired state quickly, which is critical in time-sensitive applications. The exponential switching control term reduces chattering and tracking errors, while the AFITSM controller's adaptability, enabled by the interval type-2 FIS, allows it to adjust its parameters in real-time to handle uncertainties and external disturbances. Numerical simulations demonstrate the effectiveness and superiority of the proposed control method over traditional control approaches.

Due to the complexity of operating conditions, predicting corrosion in natural gas pipelines is a challenge, and therefore its use in the gas industry is problematic. So, the present study employs corrosion risk management in control systems and decision prediction with fuzzy inference systems to address the uncertain phenomena of critical factors affecting natural gas pipelines. In the study, 84 factors were derived and 14 critical factors were identified using the Lawshe approach. The Boehm risk management framework was used and the factors were analysed in pairs in a fuzzy inference system. The probability and consequences of each factor were determined according to the API 581 standard and the weight coefficient of each factor was determined using the FUCOM method. In this study, a fuzzy inference system with two fuzzy inference subsystems was developed to comprehensively address both aspects of evaluation and response. First, the system uses the API 581 standard risk matrix to identify the risk level, followed by the risk response strategy determination through the sensitivity risk priority index chart. The results show that at the first level of the system, the highest risk was classified as severe and harsh, while at the second level of the system, the maximum output behavior occurred during the wear-out phase of the pipeline. The proposed fuzzy inference system has the potential to significantly contribute to the effective management of pipeline corrosion risk and the economic productivity of the gas industry.

Credit scoring is one of the fundamental concepts in bank industry, used for analysing and evaluating all of the customers requesting for facilities. Because of its importance to banks’ profitability, especially in the developing countries, this study aims to propose a fuzzy inference system (FIS) model for credit scoring of legal clients. This research is applied in terms of purpose and survey in terms of method. In the first step, after reviewing the literature, the evaluation criteria for legal client’s appraisal were identified, and 29 out of them were selected. In the next step, these criteria were analysed by the research experts and using a Delphi method, and 12 more important criteria were selected and organized in 4 categories for FIS modelling. Then, a researcher made questionnaire was developed to constitute rules for Main FIS and its 4 sub-FISs. Performance measure (Sub-FIS1) has four inputs: return of asset, fixed assets to equity, average customer account and customer capital. Leverage measure (Sub-FIS2) has two inputs: debt ratio and equity ratio. Borrowing measure (Sub-FIS3) has four inputs: ratio of deferred amount to current assets, amount of received facilities, borrowing capacity and amount of requested facilities, and finally, credit risk measure (Sub-FIS4) has two inputs; type of guarantee and the credit risk of the previous period. The proposed system designed based on Gaussian membership function and implemented in MATLAB. Finally, model’s validity was tested by extreme condition test. Comparing the results of the proposed FIS and the bank validation system, shows the proposed model can be considered suitable for credit scoring.

Due to developments in printing technology, the number of counterfeit banknotes is increasing every year. Finding an effective method to detect counterfeit banknotes is an important task in business. Finding a reliable method to detect counterfeit banknotes is a crucial challenge in the world of economic transactions. Due to technological development, counterfeit banknotes may pass through the counterfeit banknote detection system based on physical and chemical properties undetected. In this study, an intelligent counterfeit banknote detection system based on a Genetic Fuzzy System (GFS) is proposed to detect counterfeit banknotes efficiently. GFS is a hybrid system that uses a network architecture to fine-tune the membership functions of a fuzzy inference system. The learning algorithms Fuzzy Classification, Genetic Fuzzy Classification, ANFIS Classification, and Genetic ANFIS Classification were applied to the dataset in the UCI machine learning repository to detect the authenticity of banknotes. The developed model was evaluated based on Accuracy (ACC), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Error Mean, Error STD, and confusion matrix. The experimental results and statistical analysis showed that the classification performance of the proposed model was evaluated as follows: Fuzzy = 97.64%, GA_Fuzzy = 98.60%, ANFIS = 80.83%, GA_ANFIS = 97.72% accuracy (ACC). This shows the significant potential of the proposed GFS models for fraud detection.

COVID-19, an epidemic disease, has challenged human lives all over the world. Governments and scientific communities are trying their level best to help the masses. This disease which is caused by corona virus majorly attacks the upper respiratory system rendering the human immunity incapacitated and, in some cases, proving fatal. Therefore, it is very much important to identify the infected people quickly and accurately, so that it can be prevented from spread. Early addressal of the symptoms can help to prevent the disease to become severe for all mankind. This calls for the development of a decision-making system to help the medical fraternity for the timely action. This proposed fuzzy based system predicts Covid-19 based on individuals’ symptoms and parameters. It receives input parameters as fever, cough, breathing difficulty, muscle ache, sore throat, travel history, age, medical history in the form of different membership functions and generates one output that predicts the likelihood of a person being infected with COVID-19 using Mamdani fuzzy inference system. The timely prognosis of the disease at home isolation or at the security checks can help the patient to seek the medical treatment as early as possible. Patient case studies, real time observations, cluster cases were studied to create the rule base for FDMS. The results are validated by using real-time individuals test cases on the proposed system which yields 97.2% accuracy, 100% sensitivity and 96.2% specificity.

Always the decision of the government to the private sector is faced with the challenges and high level of importance, because these decisions should be taken at the meeting of standards and functional requirements to overcome investors' interests. These decisions include education, and due to the governance nature of education and the governments' strategies in this area, the private sectors who act in it, have been affected by the consequences of different decisions. \In this paper, our motivation is to propose a system to decide on how to develop applied academic educations at the Applied ScienceEducation Centers (ASEC's) which are supervised by the University of Applied Science and Technology (UAST) in Iran. The method used is theFuzzy Inference System (FIS) to reach this goal. The model performed in this study consists of a two-part FIS for two purposes straight ahead.The first concerns the quantitative development of higher applied education, including the number of Course Request (CR) for each ASEC with 4 inputs and 242 rules. The latter, is related to the qualitative development of higher applied education, including the assessment of the capability and competence of each ASEC for specific CR with the course and student admission background, specialty, committee's and council’s opinion, and frequency of course in city or province with 9 inputs, 350 rules, and an output. Each section has its inputs and rules that are determined and used by experts in this domain. \Our results show that using this method, provides some cost and time savings. This model analyzes in less than 2 minutes, while in practice it could be gain within 1650 person /hours work in different committees that all of them have their costs. Also, results are very close to reality with the advantage that there is no way to apply personal preferences, which largely meets the needs of research.

Environmental pollution has become a green motivation to control the pollution increase in countries which its purpose is to reduce the negative effects of environmental pollution; hence, green chain supply management has an important role in the environmental impact of organizations. Therefore, the purpose of this study is to evaluate the green supply chain of small and medium manufacturing companies based on green productivity indicators. This research is based on practical purposes and quantitative research approaches. The statistical sample was designated by 297 small and medium manufacturing companies in East Azerbaijan province. In order to data collection, a researcher-made questionnaire based on the research literature has been used. The validity of the questionnaire was determined based on the validity of the structure and its reliability using Cronbach's alpha coefficient. To evaluate the green supply chain through green productivity indicators, a fuzzy inference system based on triangular membership functions, Mamdani inference and dependency rules has been used. The results show that the designed inference system based on green productivity indicators to evaluate the green supply chain with 43 dependency rules is able to evaluate the greenness measure of the supply chain of companies based on numerical values and linguistic words

Toxicity of 38 aliphatic carboxylic acids was studied using non-linear quantitative structure-toxicity relationship (QSTR) models. The adaptive neuro-fuzzy inference system (ANFIS) was used to construct the nonlinear QSTR models in all stages of study. Two ANFIS models were developed based upon different subsets of descriptors. The first one used log ow K and LUMO E as inputs and had good prediction ability; for the training set of 28 compounds 2 Training R was 0.86 and for the test set of 10 compounds, the corresponding statistic was 2 Test R =0.97. Two outliers were detected for this ANFIS model and removing them improved the quality of the model. Another ANFIS model was constructed based on PEOE_VSA_FPNEG and G3u descriptors chosen by exhaustive search of all two combinations of calculated descriptors by Dragon and MOE softwares. The later ANFIS model showed better performance than the former ( 2 Training R =0.92 and 2 Test R =0.90) and no outlier was detected.