Fuzzy Logic Method Research Articles

Logic mining with hybridized 3-satisfiability fuzzy logic and harmony search algorithm in Hopfield neural network for Covid-19 death cases

<abstract> <p>Since the beginning of the Covid-19 infections in December 2019, the virus has emerged as the most lethally contagious in world history. In this study, the Hopfield neural network and logic mining technique merged to extract data from a model to provide insight into the link between factors influencing the Covid-19 datasets. The suggested technique uses a 3-satisfiability-based reverse analysis (3SATRA) and a hybridized Hopfield neural network to identify the relationships relating to the variables in a set of Covid-19 data. The list of data is to identify the relationships between the key characteristics that lead to a more prolonged time of death of the patients. The learning phase of the hybridized 3-satisfiability (3SAT) Hopfield neural network and the reverse analysis (RA) method has been optimized using a new method of fuzzy logic and two metaheuristic algorithms: Genetic and harmony search algorithms. The performance assessment metrics, such as energy analysis, error analysis, computational time, and accuracy, were computed at the end of the algorithms. The multiple performance metrics demonstrated that the 3SATRA with the fuzzy logic metaheuristic algorithm model outperforms other logic mining models. Furthermore, the experimental findings have demonstrated that the best-induced logic identifies important variables to detect critical patients that need more attention. In conclusion, the results validate the efficiency of the suggested approach, which occurs from the fact that the new version has a positive effect.</p> </abstract>

Research on Fuzzy Logic Approach to Cost-Benefit Analysis of Multimodal Transportation for China-Europe Liner Game

Abstract The implementation of the “Belt and Road” initiative provides unprecedented development opportunities for China-Europe liner multimodal transportation. In this paper, we constrain the cost-effectiveness of multimodal transportation between China and Europe using linear games from three perspectives: transportation cost, transportation time, and cargo time value. We also establish a cost-effective decision-making model. At the same time, a simulated annealing algorithm is introduced on the basis of a genetic algorithm, an adaptive genetic algorithm based on simulated annealing is designed to solve the model, and the optimal cost-benefit path assessment of China-Europe liner multimodal transportation is carried out based on the fuzzy logic method. Example analysis is carried out with three demands, and the advantages and disadvantages of the set of transportation route schemes are obtained. The optimal cost-effective scheme is selected as Scheme III, which has the highest scheme sticker schedule of 0.841, which verifies the feasibility of the model. The sensitivity analysis of transportation costs and transportation time shows that different transportation costs and times have certain influences on the transportation route selection of other goods. The cost-benefit analysis method for China-European liner multimodal transportation constructed in this paper provides scientific and reasonable guidance for multimodal transportation operators on path selection, which is of certain practical significance.

Correction of the movement of the mobile robot using the modified algorithm

Currently, automation of processes in which a robot can replace a human is widespread. To solve this problem, robots must be able to move independently from one position to another. Currently, many different approaches have been developed to solve this problem, such as neural networks, the method of potential fields, fuzzy logic methods, genetic algorithms, and computer vision. One of the most effective methods of solving the navigation problem is the method of building a navigation system based on the use of algorithms for localization, mapping, and automatic obstacle avoidance. One of the most effective obstacle avoidance algorithms is the D-star algorithm, which, despite its effectiveness, has some drawbacks. The method of potential fields and neural networks also showed good results, but each of them separately has several significant drawbacks. Based on the method of building a navigation system, the method of potential fields and neural networks, a modified method has been developed that allows a mobile robot to perform autonomous movement in an environment with obstacles. This modification eliminates some of the problems that arise when implementing the navigation system and combines the advantages of the methods used.

ОПРЕДЕЛЕНИЕ РАЦИОНАЛЬНОГО ВАРИАНТА ПРОГРАММЫ ПОДГОТОВКИ КАНДИДАТОВ В ВОДИТЕЛИ НА ОСНОВЕ ТЕОРИИ НЕЧЕТКИХ МНОЖЕСТВ

The article considers the issue of choosing the rational program for training driver candidates using the theory of fuzzy sets. Fuzzy logic methods are used to account for various uncertainties and fuzzy concepts, in this case, related to the driver training process. The article presents the basic principles of the theory of fuzzy sets and their application to the issue under study. The results obtained can be useful and informative in the development of effective and adaptive driver candidate training programs that take into account the individual characteristics of student.

СИСТЕМА УПРАВЛЕНИЯ НАКОПИТЕЛЯМИ ЭЛЕКТРИЧЕСКОЙ ЭНЕРГИИ НА ПРИНЦИПАХ НЕЧЕТКОЙ ЛОГИКИ

In rapidly developing world, the complexity of electric energy storage management systems and a significant data flow affect the development of technologies and contribute to the transition from classical to more efficient control methods based on fuzzy logic, which are able to function with complex structures and incomplete information. (Research Purpose) The research purpose is developing the optimal structure of the control system according to the criterion of minimizing the number of rules of fuzzy logic and increasing the energy efficiency of the electric power storage and justifying further research and implementation of this system in the software package. (Materials and methods) Used the methods of analysis, synthesis and modeling used to create the structure of the control system being developed based on the fuzzy logic method. (Results and discussion) The final structure of the power storage management system was determined on the basis of the fuzzy logic method, which is presented as a list of rules. The main variables on which the work of the control system being developed is based have been formulated. (Conclusions) The results obtained are the basis for further research and development of a control system based on a software package capable of influencing the controls of an electric power storage device.

The method of protecting information resources based on the semiotic model of cyberspace

The subject of research in the article is the processes of ensuring the protection of information resources in the cyber-physical space. The goal is to develop a model for implementing a method of information protection in cyber-physical space. The development is based on a semiotic model of cyberspace. The task is to develop effective strategies for protecting information resources and managing cyber security in cyberspace, taking into account social and perceptual aspects. Used methods: methods of analytical modeling and fuzzy logic. The following results were obtained. It is shown that the complex, multifaceted presentation of information in the network requires a complex approach with the separation of mixed content of information into interconnected levels. A semiotic approach is proposed, which allows for a more in-depth analysis of the interaction between people and technologies, which is especially important for understanding and managing complex information security systems. A six-level model of cyberspace was developed with a method of assessing the level of security for each of the levels of the developed model, and an integral indicator of potential threats to the owners of network information resources was proposed. The developed model was verified. The developed semiotic model of cyberspace and the integrated indicator of potential threats make it possible to improve the monitoring and management of cyber security of the owners of network information resources by taking into account various factors, including taking into account social and perceptual aspects, which is a key factor for the development of effective strategies for the protection of information resources in cyberspace.

Multi-Variable Location Assessment for Building Modified Stone Concrete Dams in the Drainage Basin of Golpayegan through Fuzzy Logic and Boolean Method, Isfahan, Iran

Multi-Variable Location Assessment for Building Modified Stone Concrete Dams in the Drainage Basin of Golpayegan through Fuzzy Logic and Boolean Method, Isfahan, Iran

РАЗРАБОТКА И ТЕСТИРОВАНИЕ НЕЧЕТКОГО ЛОГИЧЕСКОГО АЛГОРИТМА ДЛЯ ОБЕСПЕЧЕНИЯ БЕЗОПАСНОГО СУДОХОДСТВА АРКТИЧЕСКОГО ТРАНСПОРТА В ПЕЧОРСКОМ МОРСКОМ РАЙОНЕ

Arctic shipping impacts climate change, human health and the environment. The introduction of alternative fuels in Arctic shipping can significantly reduce emissions and impacts, as well as the risk associated with the use and transport of heavy fuel oil. Around the world, alternative fuels are becoming viable alternatives to petroleum-based fuels. There are plans to increase the adoption of alternative fuels, especially ultra-low sulfur fuels, to fuel ships sailing in the Arctic. However, the risk of transport activities on the Arctic shelf is associated with incredibly harsh climatic conditions. A deterministic approach to risk assessment does not provide a complete assessment of transport activities, so the authors propose to use the fuzzy logic method to assess the risks of transport accessibility of ships using fuel with ultra-low sulfur content in the Pechora Sea.

Analysis of multi-criteria decision-making methods for selecting a regulation system for a modular hydraulic turbine

In the work, an analysis and selection of the power regulation system for a modular straight flow hydro turbine with a capacity of 250 kW for a small hydropower plant. Initial data consisted of empirically specified quality indicators in the form of expert assessments. During the analysis, several multi-criteria analysis methods were employed, including the fuzzy logic method, implemented using the Fuzzy Logic Toolbox extension within the MATLAB environment, as well as a method based on the principle of morphological combinatorics, with results analyzed using a radar diagram.

Nutrition control in nutrient film technique hydroponic system using fuzzy method

Hydroponics is a method of growing crops without using soil media, instead, it utilizes water or other porous materials. The automation system is applied to control the nutrient quality of the water. Some sensors were used for measuring nutrient concentration, water level, water supply, and water volume. Temperature, TDS, and ultrasonic sensors are installed on the microcontroller for data measurement. The results of the data are processed using the Mamdani fuzzy logic method. The fuzzy logic results are used in controlling nutrition and water volume. The system can be monitored remotely with the aid of the Blynk app. The results of the automation system concluded that the desired condition reaches an average time of 13 minutes 49 seconds. Finally, the results of the fuzzy logic processing of the system have an accuracy value of 94.24% after being compared with the software simulation.

Development of a simulation model for assessing the technical condition of the magnetic circuit of oil power transformers by measuring the temperature of the tank and the external environment

In the article, the authors analyzed how oil-filled power transformers ensure reliable and stable operation of power transmission systems by providing efficient transmission of electricity of different voltages. In the article, the authors found that the main elements of oil-filled power transformers - the magnetic circuit, the coil and the technical condition of the oil - directly determine the performance of oil-filled power transformers. In this work, a simulation model was developed to evaluate the magnetic circuit of power oil transformers based on the measured temperature of the tank and the external environment during express diagnosis. A simulation model has been developed that allows to calculate the technical condition of oil power transformers operating in city power networks. It is shown that the developed model allows to calculate the value of the technical condition of the oil power transformer with the help of diagnostic parameters. In order to represent the technical state of the magnetic circuit of the oil power transformer, the functions of changing the state value of the output variable in the Mamdani fuzzy logic method are shown and the block diagrams are drawn up. Author’s using the Mamdani fuzzy logic method, express diagnosis of the technical condition of the “Magnetic core of the oil power transformer” was carried out in the Matlab simulink program. During the evaluation, the value of the output parameter is taken from 0 to 100, and each step is divided by 10, the smallest value is 0, and the largest is 100.

Construction of Comprehensive Evaluation Model for Financial Risk Management in Colleges and Universities Based on Fuzzy Logic

Abstract Among the many risks faced by colleges and universities, financial risk is one of the most important risks and has a large complexity. This paper evaluates the financial risk management level of colleges and universities using the fuzzy logic method based on the four dimensions of financial risk. The affiliation function is used to quantitatively describe fuzzy logic, and weighted summation is used to ensure the accuracy of fuzzy propositions. After selecting the evaluation indexes, the weights of the evaluation index system are determined, and a comprehensive evaluation system for financial risk management of colleges and universities is constructed. Taking Q colleges and universities in G city as the research object, the comprehensive evaluation coefficient of financial risk management of the subject colleges and universities is calculated, and the average value of the extensive risk coefficient of the subject colleges and universities in 2015–2017 is between 0 and 0.4, which belongs to the level of significant risk. The test university ranked second among 7 universities, but the comprehensive score index coefficient is 0.4898. However, there is still a large financial risk possibility. We need to formulate a corresponding risk management policy slightly.

A Comprehensive Survey of Fuzzy Logic Utilization in Different Agricultural Sectors

Fuzzy logic (FL) has emerged as a pivotal component within the realm of Expert Systems, demonstrating its efficacy in addressing real-life challenges that had previously eluded resolution. Its versatile applications span a multitude of domains, with this paper specifically delving into the successful utilization of fuzzy logic methods to tackle various agricultural issues. This comprehensive review explores instances where fuzzy logic has been seamlessly integrated into expert systems to provide innovative solutions within the field of agricultural sciences. The examined applications encompass a spectrum of challenges encountered in agriculture, showcasing the adaptability and effectiveness of fuzzy logic in addressing complex issues. This paper serves not only as an insightful examination of existing applications but also as a valuable contribution to the literature survey, laying the groundwork for future research endeavours. Particularly, it provides a foundational reference for those undertaking research aimed at developing expert systems tailored for specific crops in designated regions of our country. As a part of the broader landscape, this study acts as a cornerstone, offering a starting point for further investigations and advancements in the intersection of fuzzy logic and agricultural sciences.

Performance Evaluation of Multilayer Perceptron Neural Network and Adaptive Neuro-Fuzzy Inference Systems for Reservoir Operation Optimization: a Case Study of Cheffia Reservoir, Algeria

Artificial Intelligence based prediction has wide applications, including hydrology, water resources management and particularly reservoir operation. Thus, two black box models based on Artificial Neural Networks and Fuzzy Logic methods are implemented and tested in forecasting reservoir operation; the first is a Multilayer Perceptron Neural Network and the second is an Adaptive Neuro-Fuzzy Inference System combining the two methods. The developed models consist of predicting evaporation, inflows and reservoir storage from their historical records and that, with aim of providing the best fit between predicted and observed values and of improving operating rules on storage and releases. The performance of achieved results demonstrated the pertinence of Artificial Neural Networks and fuzzy Logic methods in predicting cyclical state variables, such as evaporation and storage, while the prediction of inflows to reservoir generally gave better results compared to other research works available in open literature on one hand. On other hand, it is deduced from testing different prediction models that these methods are unable to predict random variables.

Comparison of Artificial Neural Networks and Fuzzy Logic Methods in the Hazelnut Shell Drying Process

Drying and storing food products have been widely used techniques for extending shelf life for many years. In recent times, there has been a focus on the drying of food residues, similar to the preservation of foods by drying. The process of drying a product involves reducing the moisture content within the product. However, the devices established to reduce moisture content are often costly and rely heavily on experience-based systems for determining the drying ratio. Therefore, in recent years, there has been significant interest in the mathematical modeling of drying processes and the creation of a model for system behavior using artificial intelligence methods. This study aims to model the drying process of hazelnut shells using artificial intelligence techniques, specifically artificial neural networks and fuzzy logic methods. The proximity of the models created to the experimental results of the drying ratio is examined.

Seismic Damage Prediction of Buildings Using Fuzzy Logic, The Case of Ambarlı Neighborhood at Avcılar

The Kocaeli 1999 earthquake caused great damage of buildings in Istanbul, Avcılar district was the most affected region than any other nearby districts even though they are located further near to the epicenter. In Ambarlı Neighborhood at Avcılar, where the total number of buildings at the time of earthquake was 1338, damage assessment work was carried out on a total of 505 buildings. As a result, 222 buildings were categorized damaged to varying degrees which forms 16.59% of the total buildings in the area. Damage due to an earthquake is an important element of the earthquake risk concept, especially for areas previously suffered critical hazard. Therefore, for such situations with relatively complicated condition involving certain degrees of uncertainty, further investigations using simple but effective tools can lead to better understanding of such events and the consequences. In this study, a model has been developed using Fuzzy Logic method considering four parameters; Ground motion, ground condition, building number of floors and building age. The degree of damage is obtained as a result of the analysis. A post-earthquake damage database of reinforced concrete buildings within a selected zone at Ambarlı neighborhood due to 1999 Kocaeli earthquake has been used to investigate the applicability of the proposed method. The model results were found to reasonably presenting the distribution of damage of the buildings in the area when compared with the recorded damage distribution. The results also show that the model is capable of predicting damage distribution of the existing reinforced concrete buildings against possible earthquakes of large magnitude.

Aeolian Liquid Vibrations in Conical Tanks with Baffles under Wind Loading with Fuzzy Parameters

The Aeolian liquid vibrations in conical reservoirs caused by low-velocity, steady winds have been under consideration. Both amplitudes and dominant frequencies of wind loadings have been constantly changed, so to adequately describe the vibration process, fuzzy logic methods have been applied. At the first stage, the crisp initial value problem for conical shells with and without baffles has been considered. The liquid inside the reservoirs has been supposed to be an incompressible and ideal one, and its flow induced by the forced harmonic excitation, has been considered as potential. So, there exists a potential to satisfy the Laplace equation. The impermeable condition has been used at wetted surface boundaries of the shell, whereas the dynamic and kinematic boundary conditions have been set on the free liquid surface. A system of singular integral equations has been obtained for values of the velocity potential and the function describing the free surface rise. Its solution has been gained by boundary element methods. The crisp boundary value problem has been reduced to the second-order system of differential equations. After receiving the crisp solution of this system, the initial data have been fuzzified, involving triangular fuzzy numbers, and the fuzzy initial value problem has been formulated. The numerical solution to this problem with uncertain intervals involved has been obtained and analyzed.

Modeling and Control of a PEM Fuel Cell Hybrid Energy System Used in a Vehicle with Fuzzy Logic Method

PEM (Proton Exchange Membrane) fuel cells, which are commonly used in vehicles, are critical for sustainable transportation in the future. In this study, it is aimed to en-hance the system efficiency of the PEM fuel cell and provide fuel economy. To achieve this goal, the hybrid energy system with a PEM fuel cell and battery pack is controlled with two different strategies. The first control strategy is designed using Fuzzy Logic (FL), while the other control strategy is designed with the classical on-off method with the 'Relay' block. Power output of the fuel cell is determined depending on the change in the charging state of the battery pack and the power consumed by the electric vehicle in this study. The aim is to provide that the fuel cell operates in a high-efficiency range and can generate enough power when needed. Vehicle and fuel cell modeling were per-formed in Matlab/Simulink environment. NEDC (New European Driving Cycle) and WLTP (Worldwide Harmonized Light Vehicles Test Procedure) driving cycles were considered and fuel cell efficiency and hydrogen consumption were compared at dif-ferent state of charge values of the battery. The analyses were carried out over long dis-tances by repeating the driving cycles. It was observed that fuzzy logic control provid-ed 11.6% less fuel consumption than classic on-off control in NEDC and WLTP driving cycles repeated five times. The values obtained as a result of the study showed that fuzzy logic control is more advantageous to increase the energy efficiency of fuel cells.

A Real Estate Appraisal Model with Artificial Neural Networks and Fuzzy Logic: A Local Case Study of Samsun City

There have been great innovations in the field of real estate appraisal which have replaced the classical methods by recently established modern methods that involve computer technologies known as artificial intelligence. here are several artificial intelligent methods like fuzzy logic and artificial neural networks. In this study, two different real estate appraisal applications that are based on the artificial neural network and fuzzy logic methods are compared. An actual data set is taken from real estate agencies to develop a real estate appraisal model in Samsun city in Turkey. All of the real estate data belong to a certain time interval in May 2020. The selected parameters are scored by a valuation expert and the scores are then subjected to normalization. The obtained values are inputted into a fuzzy logic and artificial neural networks editor in MATLAB software and the valuation model is created. The values we obtain from the artificial neural networks and fuzzy logic are compared with actual sales data. It is observed that using these methods in real estate appraisal provides advantages in terms of time, cost and tangibility, as well as the means to create large database for real estate appraisal in a certain region.

ФОРМАЛІЗАЦІЯ ТА ІЄРАРХІЧНА КЛАСИФІКАЦІЯ ПАРАМЕТРІВ ВПЛИВУ НА ЕНЕРГОЕФЕКТИВНІСТЬ ОГОРОДЖУВАЛЬНИХ КОНСТРУКЦІЙ БУДІВЕЛЬ

Based on the results of the analysis of research on the development of scientific and methodological foundations and practical experience of organizing and managing the technological process to increase the energy efficiency of buildings, the main factors influencing the amount of energy costs during the life cycle to ensure the standard sanitary and hygienic parameters of the premises were identified. The necessity of identifying the regularities of the methodological foundations of optimization of factors influencing the energy efficiency of the enclosing structures of buildings is emphasized. It is pointed out the expediency of taking into account the total energy consumption during all stages of the life cycle of buildings when determining the energy efficiency of the enclosing structures of buildings.
 Mathematical modeling of multi-parameter assessment of energy efficiency of building enclosing structures is expedient to be performed using the method of fuzzy logic and linguistic variables. The proposed hierarchical classification and formalization of the parameters influencing the energy efficiency of the enclosing structures of buildings, which are a fuzzy knowledge base combining linguistic assessments of input and output factors that affect the target function, are given.
 The total energy expenditure for the entire life cycle to ensure the energy efficiency of the enclosing structures of buildings at the system level as a linguistic variable is characterized by functional dependence on the linguistic variables that characterize the energy expenditure for capital construction, operation and recycling of materials. The generalized model of the relationship between the parameters of influence at the system level on ensuring the energy efficiency of the enclosing structures of buildings as their hierarchical classification is presented in the form of a logical conclusion tree. The root of the logical conclusion tree determines the total energy consumption to ensure the energy efficiency of the enclosing structures of buildings, and the hanging vertices are the determining parameters of influence, the variation of which allows finding the optimal value of the objective function according to the specified criteria.