Journal articles: 'Neuro-fuzzy logic'

1

Thakur, Amey. "Neuro-Fuzzy: Artificial Neural Networks & Fuzzy Logic." International Journal for Research in Applied Science and Engineering Technology 9, no. 9 (2021): 128–35. http://dx.doi.org/10.22214/ijraset.2021.37930.

Full text

Abstract:

Abstract: Neuro Fuzzy is a hybrid system that combines Artificial Neural Networks with Fuzzy Logic. Provides a great deal of freedom when it comes to thinking. This phrase, on the other hand, is frequently used to describe a system that combines both approaches. There are two basic streams of neural network and fuzzy system study. Modelling several elements of the human brain (structure, reasoning, learning, perception, and so on) as well as artificial systems and data: pattern clustering and recognition, function approximation, system parameter estimate, and so on. In general, neural networks and fuzzy logic systems are parameterized nonlinear computing methods for numerical data processing (signals, images, stimuli). These algorithms can be integrated into dedicated hardware or implemented on a general-purpose computer. The network system acquires knowledge through a learning process. Internal parameters are used to store the learned information (weights). Keywords: Artificial Neural Networks (ANNs), Neural Networks (NNs), Fuzzy Logic (FL), Neuro-Fuzzy, Probability Reasoning, Soft Computing, Fuzzification, Defuzzification, Fuzzy Inference Systems, Membership Function.

APA, Harvard, Vancouver, ISO, and other styles

2

Titov, Andrei P. "SOFTWARE IMPLEMENTATION OF THE CO-ACTIVE NEURO-FUZZY INFERENCE SYSTEM." RSUH/RGGU Bulletin. Series Information Science. Information Security. Mathematics, no. 2 (2024): 26–43. http://dx.doi.org/10.28995/2686-679x-2024-2-26-43.

Full text

Abstract:

The article deals with the implementation of a neural network with fuzzy logic based on the Co-Active Neuro-Fuzzy Inference System (CANFIS) model. The CANFIS model is an adaptive neuro-fuzzy system that combines neural networks and fuzzy logic for processing data with uncertainty and fuzziness. CANFIS uses fuzzy rules and output mechanisms to convert input data into output values. It consists of several layers, including an input layer, hidden layers and an output layer, where each layer contains neurons performing fuzzy activation and output of results. The relevance of the work lies in the fact that the software implementation of the CANFIS model, based on the STL of the C++ language, is of great importance in the field of machine learning, artificial intelligence and data analysis. The work’s results can be applied in various fields, including when making decisions based on fuzzy logic. Special feature of the studied and developed model is to create an adaptive model capable of modeling systems with uncertainty and blurriness. The developed model is able to process data and make decisions based on fuzzy rules. CANFIS finds applications in various fields, including forecasting, management, classification and data analysis. It can be concluded that the developed neural network with fuzzy logic can be effectively applied in various fields where time series forecasting, system management and decision-making based on fuzzy information are used.

APA, Harvard, Vancouver, ISO, and other styles

3

Katayama, Ryu. "Applications of Neuro Fuzzy Technology in Consumer Electronics Products." Journal of Robotics and Mechatronics 7, no. 1 (1995): 2–8. http://dx.doi.org/10.20965/jrm.1995.p0002.

Full text

Abstract:

In recent years, intelligent industrial systems and consumer electronic products have been widely and intensively developed. Fuzzy logic, neural network, and neuro fuzzy technology, which integrates both approaches, are now regarded as an effective method to realize such intelligent features. In this paper, a review of the fuzzy boom in the consumer electronics market of Japan is presented. Typical applications of home appliances using fuzzy logic and neuro fuzzy technology are then described. Finally, methods and tools for developing fuzzy systems such as self-tuning and fuzzy modeling are reviewed.

APA, Harvard, Vancouver, ISO, and other styles

4

Chandrasekhar, Tadi, and Ch Sumanth Kumar. "Improved Facial Identification Using Adaptive Neuro-Fuzzy Logic Inference System." Indian Journal Of Science And Technology 16, no. 13 (2023): 1014–20. http://dx.doi.org/10.17485/ijst/v16i13.1833.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Titov, Andrei P. "ANALYSIS OF MODELS OF ADAPTIVE NEURO-FUZZY SYSTEMS." RSUH/RGGU Bulletin. Series Information Science. Information Security. Mathematics, no. 1 (2024): 21–35. http://dx.doi.org/10.28995/2686-679x-2024-1-21-35.

Full text

Abstract:

The article deals with the study of basic methods for models of adaptive neuro-fuzzy systems. Based on the analysis, the strengths of neural networks and fuzzy logic were found, that became powerful tools for solving complex modeling and forecasting issues. There is studying and analyzing the adaptive neural network, which is a class of neural networks that have the ability to change their structure and parameters in the process of learning and adaptation to new data and conditions and besides the article studies the Gaussian membership function, also known as the normal membership function or the Gauss-type membership function, which is a valuable tool in the f ield of fuzzy logic and fuzzy systems. The paper provides as well an analysis of the generalized Bell membership function, also known as the Bell type membership function or Bell function, which plays an important role in the field of fuzzy logic and fuzzy systems. Furthermore it analyzes the Tsukamoto model, which is one of the main models of fuzzy logic. The author opted to choose the Co-Active Neuro-Fuzzy Inference System model, which is an adaptive neuro-fuzzy system that combines neural networks and fuzzy logic for processing data with uncertainty and fuzziness. With the further implementation of the combined model based on the abovelisted models based on the STL of the C++ language, thus the neural network model is obtained, the model with versatility, that is achieved by using a combination of those models. That will facilitate its easy modification and adaptation to various tasks.

APA, Harvard, Vancouver, ISO, and other styles

6

Jindal, Nikita, Jimmy Singla, Balwinder Kaur, et al. "Fuzzy Logic Systems for Diagnosis of Renal Cancer." Applied Sciences 10, no. 10 (2020): 3464. http://dx.doi.org/10.3390/app10103464.

Full text

Abstract:

Renal cancer is a serious and common type of cancer affecting old ages. The growth of such type of cancer can be stopped by detecting it before it reaches advanced or end-stage. Hence, renal cancer must be identified and diagnosed in the initial stages. In this research paper, an intelligent medical diagnostic system to diagnose renal cancer is developed by using fuzzy and neuro-fuzzy techniques. Essentially, for a fuzzy inference system, two layers are used. The first layer gives the output about whether the patient is having renal cancer or not. Similarly, the second layer detects the current stage of suffering patients. While in the development of a medical diagnostic system by using a neuro-fuzzy technique, the Gaussian membership functions are used for all the input variables considered for the diagnosis. In this paper, the comparison between the performance of developed systems has been done by taking some suitable parameters. The results obtained from this comparison study show that the intelligent medical system developed by using a neuro-fuzzy model gives the more precise and accurate results than existing systems.

APA, Harvard, Vancouver, ISO, and other styles

7

Ashigwuike, Evans Chinemezu, and Stephen Adole Benson. "Optimal Location and Sizing of Distributed Generation in Distribution Network Using Adaptive Neuro-Fuzzy Logic Technique." European Journal of Engineering Research and Science 4, no. 4 (2019): 83–89. http://dx.doi.org/10.24018/ejers.2019.4.4.1237.

Full text

Abstract:

The growing gap between electric power generated and that demanded is of utmost concern especially in developing economy, hence calling for measures to argument the existing power generated of which DG is a more viable aspect to explore in curtailing this challenges; although been confronted with issue of location and sizing. This research applied Adaptive neuro fuzzy logic technique to optimize DG location and size. A 24 bus radial network was used to demonstrate this process and having a suitable location and size at optimal position reduces power losses and also improves the voltage profile at the buses. The method was simulated using ANFIS toolbox MATLAB R2013b (8.2.0.701) 64-bit software and tested using Gwagwalada injection sub-station feeder 1 system. The results obtained were compared to that obtained using ANN. It was observed that adaptive neuro fuzzy logic technique performed better in terms of reducing power losses compared to ANN technique. The percentage reduction in the power loss at the buses cumulatively is 48.96% for ANN while adaptive neuro fuzzy logic technique is 49.21%. The voltage profile of the networks after optimizing the DG location and sizes using adaptive neuro fuzzy logic technique were also found to be much improved with the lowest bus voltage improved from 0.9284 to 1.05pu.

APA, Harvard, Vancouver, ISO, and other styles

8

Ashigwuike, Evans Chinemezu, and Stephen Adole Benson. "Optimal Location and Sizing of Distributed Generation in Distribution Network Using Adaptive Neuro-Fuzzy Logic Technique." European Journal of Engineering and Technology Research 4, no. 4 (2019): 83–89. http://dx.doi.org/10.24018/ejeng.2019.4.4.1237.

Full text

Abstract:

The growing gap between electric power generated and that demanded is of utmost concern especially in developing economy, hence calling for measures to argument the existing power generated of which DG is a more viable aspect to explore in curtailing this challenges; although been confronted with issue of location and sizing. This research applied Adaptive neuro fuzzy logic technique to optimize DG location and size. A 24 bus radial network was used to demonstrate this process and having a suitable location and size at optimal position reduces power losses and also improves the voltage profile at the buses. The method was simulated using ANFIS toolbox MATLAB R2013b (8.2.0.701) 64-bit software and tested using Gwagwalada injection sub-station feeder 1 system. The results obtained were compared to that obtained using ANN. It was observed that adaptive neuro fuzzy logic technique performed better in terms of reducing power losses compared to ANN technique. The percentage reduction in the power loss at the buses cumulatively is 48.96% for ANN while adaptive neuro fuzzy logic technique is 49.21%. The voltage profile of the networks after optimizing the DG location and sizes using adaptive neuro fuzzy logic technique were also found to be much improved with the lowest bus voltage improved from 0.9284 to 1.05pu.

APA, Harvard, Vancouver, ISO, and other styles

9

Biswas, Saroj, Monali Bordoloi, and Biswajit Purkayastha. "Review on Feature Selection and Classification using Neuro-Fuzzy Approaches." International Journal of Applied Evolutionary Computation 7, no. 4 (2016): 28–44. http://dx.doi.org/10.4018/ijaec.2016100102.

Full text

Abstract:

This research article attempts to provide a recent survey on neuro-fuzzy approaches for feature selection and classification. Feature selection acts as a catalyst in reducing computation time and dimensionality, enhancing prediction performance or accuracy and curtailing irrelevant or redundant data. The neuro-fuzzy approach is used for feature selection and for providing some insight to the user about the symbolic knowledge embedded within the network. The neuro–fuzzy approach combines the merits of neural network and fuzzy logic to solve many complex machine learning problems. The objective of this article is to provide a generic introduction and a recent survey to neuro-fuzzy approaches for feature selection and classification in a wide area of machine learning problems. Some of the existing neuro-fuzzy models are also applied on standard datasets to demonstrate the applicability of neuro-fuzzy approaches.

APA, Harvard, Vancouver, ISO, and other styles

10

Болгов, А. А. "RISK ASSESSMENT USING ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM." ИНФОРМАЦИЯ И БЕЗОПАСНОСТЬ, no. 4(-) (December 23, 2022): 521–30. http://dx.doi.org/10.36622/vstu.2022.25.4.006.

Full text

Abstract:

В работе предлагается использование адаптивной нейро-нечеткой системы вывода для оценки риска. Проводится подробный обзор адаптивной нейро-нечеткой системы вывода, выделяя основные свойства этой системы в области методов оценки рисков. Приведены основные преимущества использования адаптивной нейро-нечеткой системы вывода. Рассматривается архитектура адаптивной нейро-нечеткой системы вывода. Выделены и рассмотрены основные методы обучения системы. Предложены методы оценки эффективности модели на основе адаптивной нейро-нечеткой системы вывода для оценки риска. Представлен алгоритм внедрения адаптивной нейро-нечеткой системы вывода. Проводятся эксперименты, которые показывают влияние процесса обучения на форму функций принадлежности системы нечеткой логики. Выполнено сравнение результатов оценки риска, полученных с помощью нечеткой логики и при использовании адаптивной нейро-нечеткой системы выводы. The work proposes the use of an adaptive neuro-fuzzy inference system for risk assessment. A detailed review of the adaptive neuro-fuzzy inference system is carried out, highlighting the main properties of this system in the field of risk assessment methods. The main advantages of using an adaptive neuro-fuzzy inference system are given. The architecture of an adaptive neuro-fuzzy inference system is considered. The main methods of teaching the system are highlighted and considered. Methods for evaluating the effectiveness of the model based on an adaptive neuro-fuzzy inference system for risk assessment are proposed. An algorithm for implementing an adaptive neuro-fuzzy inference system is presented. Experiments are being conducted that show the influence of the learning process on the form of the membership functions of the fuzzy logic system. The results of risk assessment obtained using fuzzy logic and using adaptive neuro-fuzzy inference system are compared.

APA, Harvard, Vancouver, ISO, and other styles

11

Simiński, Krzysztof. "Rough subspace neuro-fuzzy system." Fuzzy Sets and Systems 269 (June 2015): 30–46. http://dx.doi.org/10.1016/j.fss.2014.07.003.

Full text

APA, Harvard, Vancouver, ISO, and other styles

12

Ozguven, Omer Faruk, Mehmet Salih Mamis, and Arif Memmedov. "An experimental fuzzy logic application of position control using ST52 microcontroller." UNEC Journal of Engineering and Applied Sciences 4, no. 2 (2024): 76–90. https://doi.org/10.61640/ujeas.2024.1208.

Full text

Abstract:

Position control is required in many industrial applications. In this paper, several control methods; namely servo, fuzzy logic and neuro-fuzzy position controls implemented in ST52 microcontroller and laboratory test results of these methods are introduced. Fuzzystudio3.0 and Adaptive Fuzzy Modeller software packages have been used for the program development. The response of designed control systems to any desired position changes is measured, and the performance and speed for fuzzy, neuro-fuzzy and servo controllers in setting a desired position are examined. The designed software and installation steps are described and structure and listings of the control programs are presented.

APA, Harvard, Vancouver, ISO, and other styles

13

Chang, Wen-Jer. "Special Issue “Application of Fuzzy Control in Computational Intelligence”." Processes 10, no. 12 (2022): 2522. http://dx.doi.org/10.3390/pr10122522.

Full text

Abstract:

Due to the fitted structure of fuzzy logic, neural networks and evolutionary computing, neuro-fuzzy systems, evolutionary-fuzzy systems, and evolutionary neural systems, we can study computational intelligence [...]

APA, Harvard, Vancouver, ISO, and other styles

14

Smoczek, Jarosław, and Janusz Szpytko. "The Application of a Neuro-Fuzzy Adaptive Crane Control System." Journal of Konbin 14-15, no. 1 (2010): 247–58. http://dx.doi.org/10.2478/v10040-008-0182-8.

Full text

Abstract:

The Application of a Neuro-Fuzzy Adaptive Crane Control SystemThe unconventional methods, mostly based on fuzzy logic, are often addressed to a problem of anti-sway crane control. The problem of practical application of those solutions is important owing to come the growing expectations for time and precision of transportation operations and exploitation quality of material handling devices. The paper presents the designing methods of an adaptive anti-sway crane control system based on the neuro-fuzzy controller, as well as the software and hardware equipments used to aid the programming realization the fuzzy control algorithm on a programmable logic controller (PLC). The proposed application of control system was tested on the laboratory model of an overhead traveling crane.

APA, Harvard, Vancouver, ISO, and other styles

15

Parhi, D. R., and M. K. Singh. "Navigational path analysis of mobile robots using an adaptive neuro-fuzzy inference system controller in a dynamic environment." Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science 224, no. 6 (2010): 1369–81. http://dx.doi.org/10.1243/09544062jmes1751.

Full text

Abstract:

This article focuses on the navigational path analysis of mobile robots using the adaptive neuro-fuzzy inference system (ANFIS) in a cluttered dynamic environment. In the ANFIS controller, after the input layer there is a fuzzy layer and the rest of the layers are neural network layers. The adaptive neuro-fuzzy hybrid system combines the advantages of the fuzzy logic system, which deals with explicit knowledge that can be explained and understood, and those of the neural network, which deals with implicit knowledge that can be acquired by learning. The inputs to the fuzzy logic layer include the front obstacle distance, the left obstacle distance, the right obstacle distance, and target steering. A learning algorithm based on the neural network technique has been developed to tune the parameters of fuzzy membership functions, which smooth the trajectory generated by the fuzzy logic system. Using the developed ANFIS controller, the mobile robots are able to avoid static and dynamic obstacles and reach the target successfully in cluttered environments. The experimental results agree well with the simulation results; this proves the authenticity of the theory developed.

APA, Harvard, Vancouver, ISO, and other styles

16

Nguyen, Khoa Dang, and Duong Quang Do. "EXTRACTING CAUSE-EFFECT RELATIONSHIPS IN PHARMACY PRODUCTS USING NEURO-FUZZY SYSTEM COMBINED TO VISUALIZATION TECHNIQUE." Science and Technology Development Journal 13, no. 1 (2010): 35–42. http://dx.doi.org/10.32508/stdj.v13i1.2093.

Full text

Abstract:

Neuro-fuzzy system is a fusion functionalities in neural networks and fuzzy logic in order to model and extract knowledge from data. This research presents an application of neuro-fuzzy combined to visualization approach for extracting cause-effect relationships between ingredients and properties in formulation. This result will lead formulators to understanding their products more precisely and saving a lot of time and labor in R&D process.

APA, Harvard, Vancouver, ISO, and other styles

17

Karthikeyan, R., K. Manickavasagam, Shikha Tripathi, and K. V. V. Murthy. "Neuro-Fuzzy-Based Control for Parallel Cascade Control." Chemical Product and Process Modeling 8, no. 1 (2013): 15–25. http://dx.doi.org/10.1515/cppm-2013-0002.

Full text

Abstract:

Abstract This paper discusses the application of adaptive neuro-fuzzy inference system (ANFIS) control for a parallel cascade control system. Parallel cascade controllers have two controllers, primary and secondary controllers in cascade. In this paper the primary controller is designed based on neuro-fuzzy approach. The main idea of fuzzy controller is to imitate human reasoning process to control ill-defined and hard to model plants. But there is a lack of systematic methodology in designing fuzzy controllers. The neural network has powerful abilities for learning, optimization and adaptation. A combination of neural networks and fuzzy logic offers the possibility of solving tuning problems and design difficulties of fuzzy logic. Due to their complementary advantages, these two models are integrated together to form more robust learning systems, referred to as adaptive neuro-fuzzy inference system (ANFIS). The secondary controller is designed using the internal model control approach. The performance of the proposed ANFIS-based control is evaluated using different case studies and the simulated results reveal that the ANFIS control approach gives improved servo and regulatory control performances compared to the conventional proportional integral derivative controller.

APA, Harvard, Vancouver, ISO, and other styles

18

Timene, Aristide, Ndjiya Ngasop, and Haman Djalo. "Tractor-Implement Tillage Depth Control Using Adaptive Neuro-Fuzzy Inference System (ANFIS)." Proceedings of Engineering and Technology Innovation 19 (May 25, 2021): 53–61. http://dx.doi.org/10.46604/peti.2021.7522.

Full text

Abstract:

This study presents a design of an adaptive neuro-fuzzy controller for tractors’ tillage operations. Since the classical controllers allows plowing depth errors due to the variations of lands structure, the use of the combined neural networks and fuzzy logic methods decreases these errors. The proposed controller is based on Adaptive Neuro-Fuzzy Inference System (ANFIS), which permits the generation of fuzzy rules to cancel the nonlinearity and disturbances on the implement. The design and simulations of the system, which consist of a hitch-implement mechanism, an electro-hydraulic actuator, and a neuro-fuzzy controller, are conducted in SolidWorks and MATLAB software. The performance of the proposed controller is analyzed and is contrasted with a Proportional Integral Derivative (PID) controller. The obtained results show that the neuro-fuzzy controller adapts perfectly to the dynamics of the system with rejection of disturbances.

APA, Harvard, Vancouver, ISO, and other styles

19

Astuti, Winda Try, Much Aziz Muslim, and Endang Sugiharti. "The Implementation of The Neuro Fuzzy Method Using Information Gain for Improving Accuracy in Determination of Landslide Prone Areas." Scientific Journal of Informatics 6, no. 1 (2019): 95–105. http://dx.doi.org/10.15294/sji.v6i1.16648.

Full text

Abstract:

The accuracy of information is increasing rapidly as technological development. For the example, the information in determination of disaster severity. The disasters that can be determined is landslide. This determination can be conducted using the fuzzy method. One of method is neuro fuzzy. Neuro fuzzy is a combined method of two systems, fuzzy logic and artificial neural network. The accuracy of neuro fuzzy method can be increased by applying the information gain. The purpose of this study is to implement and to know the accuracy of the implementation of information gain as the selection of landslide data features. It conducted to the neuro fuzzy method in determining landslide prone areas. The distribution of training data and testing data was using 20 k-fold cross validation. The implementation of the neuro fuzzy method on landslide data was obtained an accuracy of 81.9231%. In the implementation of the neuro fuzzy method with information gain was conducted in classification process. The process will stop when the accuracy has decreased. The highest accuracy result was obtained of 88.489% by removing an attribute. So, it can be concluded the accuracy increase of 6.5659% in the implementation of the neuro fuzzy method and information gain in determination of landslide prone areas.

APA, Harvard, Vancouver, ISO, and other styles

20

Petković, Biljana, Dalibor Petković, Boris Kuzman, et al. "Neuro-fuzzy estimation of reference crop evapotranspiration by neuro fuzzy logic based on weather conditions." Computers and Electronics in Agriculture 173 (June 2020): 105358. http://dx.doi.org/10.1016/j.compag.2020.105358.

Full text

APA, Harvard, Vancouver, ISO, and other styles

21

Nilashi, Mehrbakhsh, Fausto Cavallaro, Abbas Mardani, Edmundas Zavadskas, Sarminah Samad, and Othman Ibrahim. "Measuring Country Sustainability Performance Using Ensembles of Neuro-Fuzzy Technique." Sustainability 10, no. 8 (2018): 2707. http://dx.doi.org/10.3390/su10082707.

Full text

Abstract:

Global warming is one of the most important challenges nowadays. Sustainability practices and technologies have been proven to significantly reduce the amount of energy consumed and incur economic savings. Sustainability assessment tools and methods have been developed to support decision makers in evaluating the developments in sustainable technology. Several sustainability assessment tools and methods have been developed by fuzzy logic and neural network machine learning techniques. However, a combination of neural network and fuzzy logic, neuro-fuzzy, and the ensemble learning of this technique has been rarely explored when developing sustainability assessment methods. In addition, most of the methods developed in the literature solely rely on fuzzy logic. The main shortcoming of solely using the fuzzy logic rule-based technique is that it cannot automatically learn from the data. This problem of fuzzy logic has been solved by the use of neural networks in many real-world problems. The combination of these two techniques will take the advantages of both to precisely predict the output of a system. In addition, combining the outputs of several predictors can result in an improved accuracy in complex systems. This study accordingly aims to propose an accurate method for measuring countries’ sustainability performance using a set of real-world data of the sustainability indicators. The adaptive neuro-fuzzy inference system (ANFIS) technique was used for discovering the fuzzy rules from data from 128 countries, and ensemble learning was used for measuring the countries’ sustainability performance. The proposed method aims to provide the country rankings in term of sustainability. The results of this research show that the method has potential to be effectively implemented as a decision-making tool for measuring countries’ sustainability performance.

APA, Harvard, Vancouver, ISO, and other styles

22

Chen, Minyou, and D. A. Linkens. "A hybrid neuro-fuzzy PID controller." Fuzzy Sets and Systems 99, no. 1 (1998): 27–36. http://dx.doi.org/10.1016/s0165-0114(96)00401-0.

Full text

APA, Harvard, Vancouver, ISO, and other styles

23

Arafeh, L., H. Singh, and S. K. Putatunda. "A neuro fuzzy logic approach to material processing." IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews) 29, no. 3 (1999): 362–70. http://dx.doi.org/10.1109/5326.777072.

Full text

APA, Harvard, Vancouver, ISO, and other styles

24

Tserkovny, Alex. "A Neuro T-Norm Fuzzy Logic Based System." Journal of Software Engineering and Applications 17, no. 08 (2024): 638–63. http://dx.doi.org/10.4236/jsea.2024.178035.

Full text

APA, Harvard, Vancouver, ISO, and other styles

25

Rowe, Raymond C., and Christopher G. Woolgar. "Neuro-fuzzy logic in tablet film coating formulation." Pharmaceutical Science & Technology Today 2, no. 12 (1999): 495–97. http://dx.doi.org/10.1016/s1461-5347(99)00224-2.

Full text

APA, Harvard, Vancouver, ISO, and other styles

26

Theisen, M., A. Steudel, M. Rychetsky, and M. Glesner. "Fuzzy Logic and Neuro-Systems Assisted Intelligent Sensors." Sensors Update 3, no. 1 (1998): 29–59. http://dx.doi.org/10.1002/1616-8984(199801)3:1<29::aid-seup29>3.0.co;2-4.

Full text

APA, Harvard, Vancouver, ISO, and other styles

27

R. Wade, Cooper, Daniel Kelly-B Danquah, Hossein Salehfar, and Olusegun S. Tomomewo. "Neuro-Fuzzy Logic Applications for Grid Energy Management." American Journal of Systems and Software 6, no. 1 (2023): 1–10. http://dx.doi.org/10.12691/ajss-6-1-1.

Full text

APA, Harvard, Vancouver, ISO, and other styles

28

Senivarapu Ankit Reddy and Dr. Vustelamuri Padmavathi. "Integration of Neuro-Fuzzy Systems in Medical Diagnostics and Data Security - A Review." International Journal of Scientific Research in Science, Engineering and Technology 11, no. 5 (2024): 196–200. http://dx.doi.org/10.32628/ijsrset24115113.

Full text

Abstract:

Adaptive Neuro-Fuzzy Systems (ANFS) have become increasingly prevalent in a variety of fields due to their ability to process complex and uncertain data with high accuracy. This research article reviews three major contributions of ANFS: their application in deep neuro-fuzzy systems (DNFS) for healthcare and industrial systems, neuro-fuzzy logic controllers for paralysis estimation, and ANFIS-based solutions for secure cloud storage in medical IoT (MIoT). The findings emphasize the importance of ANFS in improving decision-making, diagnosis, and data security. This paper concludes with a discussion on challenges, future research directions, and the need for optimization in real-time applications.

APA, Harvard, Vancouver, ISO, and other styles

29

Nebot, Àngela, and Francisco Mugica. "Forest Fire Forecasting Using Fuzzy Logic Models." Forests 12, no. 8 (2021): 1005. http://dx.doi.org/10.3390/f12081005.

Full text

Abstract:

In this study, we explored hybrid fuzzy logic modelling techniques to predict the burned area of forest fires. Fast detection is crucial for successful firefighting, and a model with an accurate prediction ability is extremely useful for optimizing fire management. Fuzzy Inductive Reasoning (FIR) and the Adaptive Neuro-Fuzzy Inference System (ANFIS) are two powerful fuzzy techniques for modelling burned areas of forests in Portugal. The results obtained from them were compared with those of other artificial intelligence techniques applied to the same datasets found in the literature.

APA, Harvard, Vancouver, ISO, and other styles

30

Krichevsky, Mikhail, Artyr Bydagov, and Julia Martynova. "Assessment of the efficiency of educational project management using neuro-fuzzy system." E3S Web of Conferences 110 (2019): 02070. http://dx.doi.org/10.1051/e3sconf/201911002070.

Full text

Abstract:

The project represents the introduction of elements and methods of artificial intelligence in the work programs of disciplines in the direction of “Management”. To assess the efficiency of such project management, it was proposed to use tools related to machine learning methods that include neural networks and fuzzy logic. The results of such an assessment are obtained using a neuro-fuzzy anfis (adaptive neuro-fuzzy inference system) type system, which is implemented using the MATLAB R2018b software package.

APA, Harvard, Vancouver, ISO, and other styles

31

Fan, Ya-Jun, Hai-tong Xu, and Zhao-Yu He. "Smoothing the output power of a wind energy conversion system using a hybrid nonlinear pitch angle controller." Energy Exploration & Exploitation 40, no. 2 (2021): 539–53. http://dx.doi.org/10.1177/01445987211041779.

Full text

Abstract:

Wind energy has been developed and is widely used as a clean and renewable form of energy. Among the existing variety of wind turbines, variable-speed variable-pitch wind turbines have become popular owing to their variable output power capability. In this study, a hybrid control strategy is proposed to implement pitch angle control. A new nonlinear hybrid control approach based on the Adaptive Neuro-Fuzzy Inference System and fuzzy logic control is proposed to regulate the pitch angle and maintain the captured mechanical energy at the rated value. In the controller, the reference value of the pitch angle is predicted by the Adaptive Neuro-Fuzzy Inference System according to the wind speed and the blade tip speed ratio. A proposed fuzzy logic controller provides feedback based on the captured power to modify the pitch angle in real time. The effectiveness of the proposed hybrid pitch angle control method was verified on a 5 MW offshore wind turbine under two different wind conditions using MATLAB/Simulink. The simulation results showed that fluctuations in rotor speed were dramatically mitigated, and the captured mechanical power was always near the rated value as compared with the performance when using the Adaptive Neuro-Fuzzy Inference System alone. The variation rate of power was 0.18% when the proposed controller was employed, whereas it was 2.93% when only an Adaptive Neuro-Fuzzy Inference System was used.

APA, Harvard, Vancouver, ISO, and other styles

32

Subudhi, B., and A. S. Morris. "Fuzzy and neuro-fuzzy approaches to control a flexible single-link manipulator." Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering 217, no. 5 (2003): 387–99. http://dx.doi.org/10.1177/095965180321700505.

Full text

Abstract:

In this paper, new fuzzy and neuro-fuzzy approaches to tip position regulation of a flexible-link manipulator are presented. Firstly, a non-collocated, proportional-dervative (PD) type, fuzzy logic controller (FLC) is developed. This is shown to perform better than typical model-based controllers (LQR and PD). Following this, an adaptive neuro-fuzzy controller (NFC) is described that has been developed for situations where there is payload variability. The proposed NFC tunes the input and output scale parameters of the fuzzy controller on-line. The efficacy of the NFC has been evaluated by comparing it with a fuzzy model reference adptive controller (FMRC).

APA, Harvard, Vancouver, ISO, and other styles

33

Kumar, Neeraj. "Comparative Analysis of Different Controllers for Tracking of Manipulator." Journal of Futuristic Sciences and Applications 5, no. 1 (2022): 36–41. http://dx.doi.org/10.51976/jfsa.512205.

Full text

Abstract:

Engineers have struggled to control robots since the 1950s, when the PID controller was first used to regulate complex systems. Since its release, this controller has been a top pick among manufacturers due to its low price and ease of assembly. For nonlinear systems, fuzzy logic controllers have been used by researchers and scientists to overcome the drawbacks of PID. However, as time goes on, new controlling techniques develop that are more powerful in terms of control than the previous ones. Complex, nonlinear, and dynamically ununderstood systems need neuro logic controllers, which, when paired with standard controls, comprise the neuro PID controller or neuro Fuzzy PID controller. This paper takes a comprehensive look at the many control systems utilised in the functioning of robotic manipulators, from the first controllers to the present.

APA, Harvard, Vancouver, ISO, and other styles

34

Et. al., T. Arul Raj,. "A Novel Genetic Convolutional Neuro Multi-Fuzzy Techniques for Newborn Face Recognition." Turkish Journal of Computer and Mathematics Education (TURCOMAT) 12, no. 6 (2021): 1037–46. http://dx.doi.org/10.17762/turcomat.v12i6.2416.

Full text

Abstract:

Advances in technology have made life simpler in today's society by supplying us with a variety of emerging demands lacking By assessing the progressive stability of biometric recognition accuracy for newborns, biometric recognition can be used to recognize missing newborns and prevent them from being switched in higher-level hospitals.. Recognizing and authenticating newborns is a major problem in many hospitals. The face recognition system does an outstanding job of identifying and authenticating the newborn. To answer these concerns, create a face recognition device for newborns. The proposed approach improves picture consistency on a newborn's face. Our objectives are to propose a genetic, convolutional neural network, and fuzzy logic-based automated framework for newborn face recognition. As a paradigm GCNMF is suggested for real-world newborn face recognition. Convolutional, pooling, and fully-connected layers, as well as a Neuro Fuzzy layer, form the Inherited Convolutional Neuro Multi-Fuzzy. The model employs hereditary, convolutional neural networks, and fuzzy logic to deal with ambiguity and imprecision in the input configuration representation. The efficacy and outcomes of the recommended method are then analyzed using newborn face datasets and the Genetic Convolutional Neuro Multi-Fuzzy (GCNMF) Approach.

APA, Harvard, Vancouver, ISO, and other styles

35

Braz-César, Manuel, and Rui Barros. "Optimization of a Fuzzy Logic Controller for MR Dampers Using an Adaptive Neuro-Fuzzy Procedure." International Journal of Structural Stability and Dynamics 17, no. 05 (2016): 1740007. http://dx.doi.org/10.1142/s0219455417400077.

Full text

Abstract:

Intelligent and adaptive control systems are naturally suitable to deal with dynamic uncertain systems with non-smooth nonlinearities; they constitute an important advantage over conventional control approaches. This control technology can be used to design powerful and robust controllers for complex vibration engineering problems such as vibration control of civil structures. Fuzzy logic based controllers are simple and robust systems that are rapidly becoming a viable alternative for classical controllers. Furthermore, new control devices such as magnetorheological (MR) dampers have been widely studied for structural control applications. In this paper, we design a semi-active fuzzy controller for MR dampers using an adaptive neuro-fuzzy inference system (ANFIS). The objective is to verify the effectiveness of a neuro-fuzzy controller in reducing the response of a building structure equipped with a MR damper operating in passive and semi-active control modes. The uncontrolled and controlled responses are compared to assess the performance of the fuzzy logic based controller.

APA, Harvard, Vancouver, ISO, and other styles

36

Saatchi, Reza. "Fuzzy Logic Concepts, Developments and Implementation." Information 15, no. 10 (2024): 656. http://dx.doi.org/10.3390/info15100656.

Full text

Abstract:

Over the past few decades, the field of fuzzy logic has evolved significantly, leading to the development of diverse techniques and applications. Fuzzy logic has been successfully combined with other artificial intelligence techniques such as artificial neural networks, deep learning, robotics, and genetic algorithms, creating powerful tools for complex problem-solving applications. This article provides an informative description of some of the main concepts in the field of fuzzy logic. These include the types and roles of membership functions, fuzzy inference system (FIS), adaptive neuro-fuzzy inference system and fuzzy c-means clustering. The processes of fuzzification, defuzzification, implication, and determining fuzzy rules’ firing strengths are described. The article outlines some recent developments in the field of fuzzy logic, including its applications for decision support, industrial processes and control, data and telecommunication, and image and signal processing. Approaches to implementing fuzzy logic models are explained and, as an illustration, Matlab (version R2024b) is used to demonstrate implementation of a FIS. The prospects for future fuzzy logic developments are explored and example applications of hybrid fuzzy logic systems are provided. There remain extensive opportunities in further developing fuzzy logic-based techniques, including their further integration with various machine learning algorithms, and their adaptation into consumer products and industrial processes.

APA, Harvard, Vancouver, ISO, and other styles

37

Djelamda, Imene, and Ilhem Bochareb. "Field-oriented control based on adaptive neuro-fuzzy inference system for PMSM dedicated to electric vehicle." Bulletin of Electrical Engineering and Informatics 11, no. 4 (2022): 1892–901. http://dx.doi.org/10.11591/eei.v11i4.3818.

Full text

Abstract:

Permanent magnet synchronous motor (PMSM) speed control is generally done using flux-oriented control, which uses conventional proportional-integral (PI) current regulators, but still remain the problem of calculating the coefficients of these regulators, particularly in the case of control hybridization, the development of artificial intelligence has simplified many calculations while giving more accurate, and improved results, this paper presents and compares the performance of the flux oriented control (FOC) of a PMSM powered by pulse width modulation (PWM) using PI regulator, fuzzy logic control (FLC) and adaptive neuro-fuzzy inference system (ANFIS), in this work we present another approach of a neuro ANFIS using the hybrid combination of fuzzy logic and neural networks. This ANFIS is a very powerful tool and can be applied to various engineering problems. To make up for the deficiency of fuzzy logic controller. To understand the performance, characteristics, and influence of each controller on the system response, we use MATLAB/Simulink to model a PMSM (0.5 kW) powered by a three-phase inverter and controlled by the FOC, FOC-FLC, and FOC-ANFIS.

APA, Harvard, Vancouver, ISO, and other styles

38

Imene, Djelamda, and Bouchareb Ilhem. "Field-oriented control based on adaptive neuro-fuzzy inference system for PMSM dedicated to electric vehicle." Bulletin of Electrical Engineering and Informatics 11, no. 4 (2022): 1892~1901. https://doi.org/10.11591/eei.v11i4.3818.

Full text

Abstract:

Permanent magnet synchronous motor (PMSM) speed control is generally done using field oriented control, which uses conventional proportionalintegral (PI) current regulators, but still remain the problem of calculating the coefficients of these regulators, particularly in the case of control hybridization, the development of artificial intelligence has simplified many calculations while giving more accurate, and improved results, this paper presents and compares the performance of the flux oriented control (FOC) of a PMSM powered by pulse width modulation (PWM) using PI regulator, fuzzy logic control (FLC) and adaptive neuro-fuzzy inference system (ANFIS), in this work we present another approach of a neuro ANFIS using the hybrid combination of fuzzy logic and neural networks. This ANFIS is a very powerful tool and can be applied to various engineering problems. To make up for the deficiency of fuzzy logic controller. To understand the performance, characteristics, and influence of each controller on the system response, we use MATLAB/Simulink to model a PMSM (0.5 kW) powered by a three-phase inverter and controlled by the FOC, FOC-FLC, and FOCANFIS.

APA, Harvard, Vancouver, ISO, and other styles

39

Carvalho, Lucimar M. F. de, Silvia Modesto Nassar, Fernando Mendes de Azevedo, Hugo José Teixeira de Carvalho, Lucas Lese Monteiro, and Ciciliana M. Zílio Rech. "A neuro-fuzzy system to support in the diagnostic of epileptic events and non-epileptic events using different fuzzy arithmetical operations." Arquivos de Neuro-Psiquiatria 66, no. 2a (2008): 179–83. http://dx.doi.org/10.1590/s0004-282x2008000200007.

Full text

Abstract:

OBJECTIVE: To investigate different fuzzy arithmetical operations to support in the diagnostic of epileptic events and non epileptic events. METHOD: A neuro-fuzzy system was developed using the NEFCLASS (NEuro Fuzzy CLASSIfication) architecture and an artificial neural network with backpropagation learning algorithm (ANNB). RESULTS: The study was composed by 244 patients with a bigger frequency of the feminine sex. The number of right decisions at the test phase, obtained by the NEFCLASS and ANNB was 83.60% and 90.16%, respectively. The best sensibility result was attained by NEFCLASS (84.90%); the best specificity result were attained by ANNB with 95.65%. CONCLUSION: The proposed neuro-fuzzy system combined the artificial neural network capabilities in the pattern classifications together with the fuzzy logic qualitative approach, leading to a bigger rate of system success.

APA, Harvard, Vancouver, ISO, and other styles

40

Ibemezie, Ndubuisi Paul-Darlington, Julius Egwu Arua, Igwe Lazarus Uduma, John Ukanu, Ali, Uche Egwu, and Ukoima Katoubokmelek Thompson. "Comparative Evaluation of Intelligent Agent Based Improved Control Designs of Electro-pneumatic Clutch Actuation System for Heavy Duty Vehicles." Journal of Engineering Research and Reports 27, no. 5 (2025): 138–53. https://doi.org/10.9734/jerr/2025/v27i51499.

Full text

Abstract:

The comparative performances of electro-pneumatic clutch actuation system in heavy-duty vehicles using intelligent agent-based control adaptation technique is presented. Conventional control techniques in clutch actuation uses on/off, servo mechanism and other non-intelligent methods of actuation control. These techniques demand for calibration of clutch actuators. To eliminate calibration and its defects, intelligent control methods of clutch actuation are implemented. The specific methodology was predicated on three intelligent agent systems of Fuzzy logic, Neural Network and Hybrid Neuro-Fuzzy. The design started with the development of an intelligent agent-based actuation control rule modelled in a forty-nine fuzzy logic rules pattern for improving the clutch actuation process. A backpropagation standard training algorithm of weight adjustment in a neural network architecture was also designed. The developed fuzzy and neural network models were combined in a hybrid neuro-fuzzy model. Simulink models for Conventional, Fuzzy Logic, ANN and hybrid Neuro-Fuzzy controllers were also developed. Finally, the models were simulated in a Simulink platform and the levels and percentages of improvements determined and compared in order to justify the study. The mean improvements on Conventional controllers compared to that of the Neuro-Fuzzy improved controllers stood at an error reduction in clutch travel from 0.720mm to 0.0244mm given a percentage decrease of 96.6% thereby reducing error to a tolerable level of only 3.39 % while that for torque was increased from 0.1786 NM to 0.4166 NM given a percentage increase of 133.26%. Similarly, increases were recorded for angular speed which also increased from 1005 RPM to 2344 RPM given an increase of 133.23% and power which increased from 16.88 kilowatts to 26.03 kilowatts resulting in 54.21% increase. The fuzzy and ANN controllers also recorded some degrees of improvements over the conventional controllers but to a lesser extent comparatively. It is thus recommended that the use of intelligent agent-based controllers be adopted in the design of clutch actuator system control for its effective improvements.

APA, Harvard, Vancouver, ISO, and other styles

41

KOPRINKOVA-HRISTOVA, PETIA. "BACKPROPAGATION THROUGH TIME TRAINING OF A NEURO-FUZZY CONTROLLER." International Journal of Neural Systems 20, no. 05 (2010): 421–28. http://dx.doi.org/10.1142/s0129065710002504.

Full text

Abstract:

The paper considers gradient training of fuzzy logic controller (FLC) presented in the form of neural network structure. The proposed neuro-fuzzy structure allows keeping linguistic meaning of fuzzy rule base. Its main adjustable parameters are shape determining parameters of the linguistic variables fuzzy values as well as that of the used as intersection operator parameterized T-norm. The backpropagation through time method was applied to train neuro-FLC for a highly non-linear plant (a biotechnological process). The obtained results are discussed with respect to adjustable parameters rationality. Conclusions are made with respect to the appropriate intersection operations too.

APA, Harvard, Vancouver, ISO, and other styles

42

Gennady, Kaniuk, Vasylets Tetiana, Varfolomiyev Oleksiy, Mezerya Andrey, and Antonenko Nataliia. "Development of neuralnetwork and fuzzy models of multimass electromechanical systems." Eastern-European Journal of Enterprise Technologies 3, no. 2(99) (2019): 51–63. https://doi.org/10.15587/1729-4061.2019.169080.

Full text

Abstract:

The study objective was to construct models of multimass electromechanical systems using neural nets, fuzzy inference systems and hybrid networks by means of MATLAB tools. A model of a system in a form of a neural net or a neuro-fuzzy inference system was constructed on the basis of known input signals and signals measured at the system output. Methods of the theory of artificial neural nets and methods of the fuzzy modeling technology were used in the study. A neural net for solving the problem of identification of the electromechanical systems with complex kinematic connections was synthesized using the Neural Network Toolbox application package of the MATLAB system. A possibility of solving the identification problem using an approximating fuzzy system using the Fuzzy Logic Toolbox package was considered. A hybrid network was synthesized and implemented in a form of an adaptive neuro-fuzzy inference system using the ANFIS editor. Recommendations for choosing parameters that have the most significant effect on identification accuracy when applying the methods under consideration were given. It was shown that the use of neural nets and adaptive neuro-fuzzy inference systems makes it possible to identify systems with accuracy of 2 to 4%. As a result of the conducted studies, efficiency of application of neural nets, fuzzy inference systems and hybrid nets to identification of systems with complex kinematic connections in the presence of "input-output" information was shown. The neural-network, fuzzy and neuro-fuzzy models of two-mass electromechanical systems were synthesized with the use of modern software tools. The considered approach to using artificial intelligence technologies, that is neural nets and fuzzy logic is a promising line of construction of appropriate neural-network and neuro-fuzzy models of technical objects and systems. The study results can be used in synthesis of regulators for the systems with complex kinematic connections to ensure their high performance.

APA, Harvard, Vancouver, ISO, and other styles

43

Li, Jun Wei, Hai Yan Shen, and Huian Sun. "The Design of Neuro-Fuzzy Controller for Active Suspension System." Applied Mechanics and Materials 330 (June 2013): 673–76. http://dx.doi.org/10.4028/www.scientific.net/amm.330.673.

Full text

Abstract:

A neuro-fuzzy control (NFC) system is developed to control the suspension system of vehicle due to its nonlinearity and parameter variations. A neural network (NN) is used to adjust the premise parameters and the consequent parameters in fuzzy logic control (FLC). Simulation results by using NFC are compared with those of the conventional PID controller and passive suspension system. Based on the simulation, it can be concluded that the neuro-fuzzy controller shows a good performance in both passenger comfort and vehicle handing in comparison to the conventional PID controller and passive suspension system.

APA, Harvard, Vancouver, ISO, and other styles

44

Pandey, Arun Kumar, and Avanish Kumar Dubey. "Neuro Fuzzy Modeling of Laser Beam Cutting Process." Applied Mechanics and Materials 110-116 (October 2011): 4109–17. http://dx.doi.org/10.4028/www.scientific.net/amm.110-116.4109.

Full text

Abstract:

Laser Beam Cutting (LBC) being a complex cutting process needs a reliable model for prediction of the process performance. This research work presents a modeling study of LBC process. A hybrid approach of Artificial Neural Network (ANN) and Fuzzy Logic (FL) has been used for developing the Kerf width model. The developed Neuro Fuzzy model of Kerf width has also been compared with Response Surface Methodology (RSM) based model and it has been found that the values of Kerf width predicted by the Neuro Fuzzy Model are more closer to the experimental values.

APA, Harvard, Vancouver, ISO, and other styles

45

Zhang, Dong, Xiao-Li Bai, and Kai-Yuan Cai. "Extended neuro-fuzzy models of multilayer perceptrons." Fuzzy Sets and Systems 142, no. 2 (2004): 221–42. http://dx.doi.org/10.1016/s0165-0114(03)00244-6.

Full text

APA, Harvard, Vancouver, ISO, and other styles

46

Paiva, Rui Pedro, and António Dourado. "Interpretability and learning in neuro-fuzzy systems." Fuzzy Sets and Systems 147, no. 1 (2004): 17–38. http://dx.doi.org/10.1016/j.fss.2003.11.012.

Full text

APA, Harvard, Vancouver, ISO, and other styles

47

Banakar, Ahmad, and Mohammad Fazle Azeem. "Parameter identification of TSK neuro-fuzzy models." Fuzzy Sets and Systems 179, no. 1 (2011): 62–82. http://dx.doi.org/10.1016/j.fss.2011.05.003.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

Ogutu, Patrick O. M., Nicholas Oyie, and Dr Winston Ochieng Ojenge. "CHICKEN BANDA PERFORMANCE IMPROVEMENT UTILIZING NEURO-FUZZY LOGIC TECHNIQUE." Journal of Research in Engineering and Applied Sciences 7, no. 3 (2023): 362–67. http://dx.doi.org/10.46565/jreas.202273362-367.

Full text

Abstract:

This study is on improvement of performance of the chicken Banda, using indoor change in environmental conditions for temperature control. The differential change in climatic conditions is technically used to put on the fan and the Banda so as to realize the right comfortable indoor conditions. The chicken chicks’ Banda Mathematical model is created, prototype designed, temperature controller to depict a two systems simulation of neuro fuzzy logic and fuzzy logic .The performance is analyzed by the use of Matlab Simulink latest edition. To monitor the temperature of the Chicken cage the neural fuzzy logic technique is utilized. As far as the prototype is concerned the chicks’ cage set temperature is fixed at 26.50C. The study will show that the reference input can be kept on track by the process controller hence proving the principle that the neural fuzzy control is much superior in optimizing performance compared to the fuzzy only controllers. The Back propagation (BP) and least square estimator (LSE) are the hybrid optimization methods which are used. For data training the gradient descent method (GDM) is used. The research reveal that there is drastic performance improvement in the behavior response where result show that there settling time is reduced from 0.75 to 0.48 seconds while the percentage overshoot is also reduced down from 29.9% to 0.9345%.

APA, Harvard, Vancouver, ISO, and other styles

49

Shi, Yan, and Masaharu Mizumoto. "An improvement of neuro-fuzzy learning algorithm for tuning fuzzy rules." Fuzzy Sets and Systems 118, no. 2 (2001): 339–50. http://dx.doi.org/10.1016/s0165-0114(98)00440-0.

Full text

APA, Harvard, Vancouver, ISO, and other styles

50

Ломакина, Л. С., and И. Д. Чернобаев. "Neuro-fuzzy classifiers." МОДЕЛИРОВАНИЕ, ОПТИМИЗАЦИЯ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ 9, no. 4(35) (2021): 27–28. http://dx.doi.org/10.26102/2310-6018/2021.35.4.027.

Full text

Abstract:

В статье рассматривается проблема повышения точности искусственных нейронных сетей при решении задач классификации состояний объектов различной физической природы. Эту проблему предлагается сформулировать как проблему выбора типа функции активации в искусственных нейронных сетях и рассматривать ее с позиции теории нечетких множеств. В этой связи разработана математическая модель адаптивной функции активации искусственного нейрона, использующая нечеткую логическую систему с интервальными нечеткими множествами второго типа. Эта функция отличается от обыкновенных функций активации, применяемых в нейросетевых моделях тем, что область ее входных значений ограничена, и при этом позволяет оптимизировать параметры, определяющие форму кривой в процессе обучения искусственной нейронной сети. С целью снижения вычислительной сложности нейро-нечеткой модели с нечеткой функцией активации предложена ее модификация, заключающаяся в применении математической функции гиперболического тангенса для нормализации значений вектора, подаваемого на вход нечеткой функции. Разработано алгоритмическое обеспечение для двух архитектур нейро-нечетких классификаторов – рекуррентного нейро-нечеткого классификатора и сверточного нейро-нечеткого классификатора. Проведено два эксперимента по классификации медико-биологических и текстовых объектов, в которых сравнивались показатели точности моделей нейро-нечетких классификаторов и аналогичных по структуре классификаторов без нечеткой функции активации, и при этом подтверждено повышение точности искусственных нейронных сетей, в составе которых используются нечеткие функции активации. This paper considers the problem of increasing the accuracy of artificial neural networks in the tasks of states classification of objects with different physical nature. It is proposed to define this problem as a problem of choosing the activation function type in artificial neural networks and to consider it from the perspective of the fuzzy sets theory. In this regard, a mathematical model of the artificial neuron adaptive activation function has been developed, using a fuzzy logic system with interval fuzzy sets of the second type. This function differs from ordinary activation functions used in neural network models in that the range of its input values is limited, and, at the same time, such a function allows to optimize the parameters that determine the shape of the curve in the process of training an artificial neural network. To reduce the computational complexity of a neuro-fuzzy model with a fuzzy activation function, its modification is proposed, which involves the use of mathematical function of the hyperbolic tangent to normalize the values of the vector supplied to the input of the fuzzy function. Algorithmic support has been developed for two architectures of neuro-fuzzy classifiers - a recurrent neuro-fuzzy classifier and a convolutional neuro-fuzzy classifier. Two experiments on the classification of biomedical and text objects were carried out, in which the accuracy indicators of models of neuro-fuzzy classifiers and classifiers similar in structure without a fuzzy activation function were compared; additionally, an increase in the accuracy of artificial neural networks, which used fuzzy activation functions, was confirmed.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Neuro-fuzzy logic'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles