Fuzzy Rule Base Research Articles

DEVELOPMENT OF FUZZY INFERENCE SYSTEM FOR COVID-19 DATA ANALYSIS

As COVID-19 Pandemic and related data is very recent. COVID-19 infected most of the population from entire globe with different impact. It disclosed the limitation of access of health and care resources. Various parameters like different symptoms, different existing health conditions, different age, diagnosis level and great uncertainties made the condition vaguer. Fuzzy can handle such vagueness and uncertainty of such voluminous data of patients and can support to medical stakeholders, experts, hospitals, pharmaceuticals etc. Fuzzy Logic is widely used to address so many uncertainties, incompleteness or imprecision. The current experiment implements Fuzzy Inference System for pattern identification and classification by applying fuzzy approach with Fuzzy Logic in R for performance improvement. This focuses on designing Fuzzy Rule base, Model and inference for COVID 19 data analysis.

Interval Type-2 Fuzzy Analysis and Comprehensive Evaluation for Neonatal Pathological Jaundice

Neonatal pathological jaundice (NPJ) is easy to cause bilirubin encephalopathy, which has high mortality and sequelae rate. Therefore, accurate risk evaluation can help clinicians take appropriate measures to timely intervene in neonatal jaundice level and avoid complications. In this article, five indexes are extracted as the factor set for the risk evaluation of NPJ, and the diagnostic criteria are determined. Then, five index sets are described by interval type-2 fuzzy sets, and the corresponding membership functions and membership function figures are provided. The feasibility of interval type-2 fuzzy comprehensive evaluation in risk evaluation of NPJ is demonstrated through example, and the fuzzy rule bases of prevention and treatment for NPJ are constructed according to the results of risk evaluation. Finally, this article demonstrates that the proposed risk evaluation and treatment process of NPJ is actually a dynamic closed-loop control process, which is consistent with the clinical treatment process. This article provides a new solution for the aided diagnosis and decision-making treatment of NPJ, which is of great significance in reducing neonatal mortality and alleviating the pressure of medical staff.

Optimizing deep neuro-fuzzy classifier with a novel evolutionary arithmetic optimization algorithm

Deep Neuro-Fuzzy System has been successfully employed in various applications. But, the model faces two issues: (i) dataset with many features exponentially increases the fuzzy rule-base, (ii) parameters in the fuzzy rule-base are optimized using the gradient descent approach, which has the drawback of local minima. Therefore, this study aims on improving the model’s accuracy by proposing Arithmetic Optimization Algorithm. The outcomes using the Arithmetic Optimization Algorithm for feature selection have not only reduced the burden of implementing a huge dataset, but the Arithmetic Optimization-based deep neuro-fuzzy system has outperformed with 95.14% accuracy compared to the standard method with 94.52%.

Operational safety risk assessment of water diversion infrastructure based on FMEA with fuzzy inference system

Abstract Water diversion infrastructure is characterized by a wide range of impacts and complex geological conditions. There are a large number of risk factors that affect its operational safety. Accidents that have occurred during operation have caused devastaing disasters to water diversion infrastructure. In this study, the failure modes for the operational risks of water diversion infrastructure are identified from four aspects, i.e.,environment, engineering technology, operation management, and society. A failure mode and effect analysis (FMEA) risk poiorization model is established based on the fuzzy inference system (FIS). A fuzzy rule base is established according to IF-THEN rules, and the risk priority is calculated and ranked via FIS. Lastly, a case study of the Huixian section of the Middle Route of the South-to-North Water Transfer Project is carried out to verify the proposed method. The results show that the risks of rainstorms, floods, and foundation failure are regarded as high priority. The validity and applicability of the proposed method are tested via comparison with traditional FMEA. These findings provide valuable information for the operational safety of water diversion infrastructure.

A novel service robot assignment approach for COVID-19 infected patients: a case of medical data driven decision making

Coronavirus Disease-19 (COVID-19) is a major concern for the entire world in the current era. Coronavirus is a very dangerous infectious virus that spreads rapidly from person to person. It spreads in exponential manner on a global scale. It affects the doctors, nurse and other COVID-19 warriors those who are actively involved for the treatment of COVID-19 infected (CI) patients. So, it is very much essential to focus on automation and artificial intelligence (AI) in different hospitals for the treatment of such infected patients and all should be very much careful to break the chain of spreading this novel virus. In this paper, a novel patient service robots (PSRs) assignment framework and a priority based (PB) method using fuzzy rule based (FRB) approach is proposed for the assignment of PSRs for CI patients in hospitals in order to provide safety to the COVID-19 warriors as well as to the CI infected patients. This novel approach is mainly focused on lowering the active involvement of COVID-19 warriors for the treatment of high asymptotic COVID-19 infected (HACI) patients for handling this tough situation. In this work, we have focused on HACI and low asymptotic COVID-19 infected (LACI) patients. Higher priority is given to HACI patients as compared to LACI patients to handle this critical situation in order to increase the survival probability of these patients. The proposed method deals with situations that practically arise during the assignment of PSRs for the treatment of such patients. The simulation of the work is carried out using MATLAB R2015b.

An adaptive fuzzy logic controller for intelligent drying

A systematic approach to the design of an adaptive fuzzy logic controller (AFLC) for intelligent drying with a computer vision system (CVS) in a feedback loop is proposed. Developed AFLC is based on an artificial neural network (ANN), geno-fuzzy algorithm, and multi-objective fuzzy cost function. Fuzzy sets for the moisture content and product quality are automatically generated by using principal component analysis (PCA) and fuzzy clustering. In addition, the concept of fuzzy time is introduced to optimize the duration of each control step. The fuzzy rule base for the controller was constructed through a two-stage process of (i) warming-up based on simulation and optimization (offline) and (ii) fine-tuning during real-time drying (online). The application of AFLC for shrimp drying showed advantages of the unsupervised fuzzy logic control, such as decreased drying time, less quality degradation, and smaller energy consumption.

Horizontal Federated Learning of Takagi–Sugeno Fuzzy Rule-Based Models

In this article, we elaborate on a design and realization of fuzzy rule-based model in the horizontal federated learning framework. Traditional machine learning in distributed environment often involves sharing sensitive information with other sites or transferring data to a central server on which a global model is trained. These situations increase the communication overhead and pose serious threats to the privacy of sensitive data. Federated learning opens up the possibility for collaboratively training a global model on a basis of distributed on-site data without sacrificing data privacy. While fuzzy rule-based models have been used in system modeling due to their substantial modeling abilities and good interpretability, the implementation of fuzzy rule-based models in a distributed environment without compromising data privacy still requires careful consideration. This article proposes a two-step federated learning approach to train a global model on a basis of private data located across different sites without their centralization. The first step concerns the determination of the structure of the data through federated collaborative clustering. Subsequently, a shared global model is trained jointly by all the participating clients. An advantage of the proposed method is that it achieves high accuracy without violating data privacy. A series of experimental studies are conducted to gain a detailed insight into the realization steps and demonstrate the effectiveness of the proposed method.

Towards utilization of rule base structure to support fuzzy rule interpolation

AbstractFuzzy rule interpolation (FRI) offers a reliable approach for providing an interpretable approximate decision with a sparse rule base, when a new observation does not match any existing rules. As the mainstream application of a fuzzy rule base is to extract valuable approximate information from each individual rules, existing FRI methods typically work by postulating that the more rules used to implement the interpolation the better the reasoning outcomes. Yet, empirical results have shown that using a large number of rules in an FRI process may adversely lead to worsening the accuracy of the inference outcomes, not just degrading efficiency. The objective of this work is to set a firm theoretical foundation for the eventual establishment of a novel FRI approach. It achieves this goal by mapping the structural patterns within a given fuzzy rule base onto a mathematically isomorphic data space, such that the essential information embedded in the original rule base can be effectively captured, represented and analysed. The resulting mathematically mapped patterns enable the production of a theorem that determines the upper limit of the number of rules required to effectively and efficiently perform FRI. The experimental investigations reported herein demonstrate that the number of required rules to perform FRI obeys the theorem discovered in this work.

On solvability of systems of partial fuzzy relational equations

Systems of fuzzy relational equations belong to key mathematical problems related to the correct behavior of fuzzy systems, especially of fuzzy inference systems. Indeed, if we find a fuzzy relation that solves a given system of fuzzy relational equations, we found a model of a fuzzy rule base related to the given system that will behave correctly in the sense that it will preserve the fundamental modus ponens property. This problem with numerous results becomes absolutely unexplored as soon as we allow partiality in the system. Partial fuzzy sets have only partially defined membership degrees, i.e., for some elements, the membership degree is undefined, i.e., partial propositions have only partially defined truth-values. There are many origins from which we may obtain propositions with undefined truth-values, e.g., non-denoting or irrelevant terms, inconsistent (both true and false) propositions, or truth-values are simply unknown. Partial logics belong to classical topics in logic so, the extensions to partial fuzzy logic in recent years were not surprising. However, we should not dare to deal with partial fuzzy sets in fuzzy systems without any guarantee of the preservation of fundamental properties such as modus ponens. This article is focusing on filling this gap.

A fuzzy-based flood warning system using 19-year remote sensing time series data in the Google Earth Engine cloud platform

Many Flood Warning Systems (FWS) have been developed to date to reduce flood risk and properly manage this natural disaster. This study presents a novel method to create an FWS based on anomaly detection in remote sensing climate data from western Lorestan, Iran, from 2001-to 2019. To this end, the monthly time series of climate products related to floods (e.g., precipitation, soil moisture, soil and air temperatures, vegetation, snow, and evapotranspiration) were first processed in Google Earth Engine (GEE). Then, three algorithms – Median-Interquartile range (M−IQR), Multi-Layer Perceptron (MLP), and Recurrent Neural Network (RNN) – were applied to detect anomalies in the time series of each parameter. Finally, a rule-based Fuzzy Inference System (FIS) was designed to estimate the potential of floods per month by establishing the relationship between the observed anomalies and the occurrence of floods. The results of the proposed Fuzzy-based Flood Warning System (FFWS) using all three anomaly detection methods accurately showed the very high potential for floods in March and April 2019 (i.e., actual flood events). Two other floods occurred in October 2015 and April 2016 were also considered for further evaluation of the proposed method. The results indicated that the RNN method achieved the highest performance in flood forecasting with the overall accuracy and Kappa coefficient of 93.85% and 0.93, respectively. Moreover, the potential of floods at the beginning of 2019 (i.e., January and February) was also high, although not to the extent as in March and April, indicating that the proposed method correctly identified the potential of flooding in later months and can thus provide a warning to help mitigate the impact of flood damage.

Adaptive Parameters Based Fuzzy Control Approaches Applied to a Single Inverted Pendulum System

This paper deals with adaptive fuzzy approaches for controlling a cart-pendulum system. In fact, it suggests the use of a conventional Fuzzy Proportional-Integral-Derivative (FPID) controller to control the angle of the pendulum and an unconventional fuzzy controller which is an interesting idea to control the cart position. For that, two Adaptive FPID (AFPID) controllers and a Self-Tunable Fuzzy Inference System (STFIS) controller are used. To sweep all the output space of these controllers, a set-point very rich in information is applied to cart displacement. The conclusions of the fuzzy rules of STFIS controller are on-line fitted by using an adaptive learning algorithm. The conclusions obtained are sorted and then are clustered in intervals. Simulation results show the interpretability of STFIS controller behavior in form of decision rules. Moreover, the STFIS controller is compared to the two AFPID controllers. This comparison shows that a FIS based on a best self-tuning of fuzzy rule base, i.e. STFIS controller, can replace correctly and more perfectly the role of a FPID controller with self-tuning scaling factors. So, the STFIS controller might be used to improve performances and robustness of a control system.

Bacterial Evolutionary Algorithm-Trained Interpolative Fuzzy System for Mobile Robot Navigation

This paper describes the process of building a transport logic that enables a mobile robot to travel fast enough to reach a desired destination in time, but safe enough to prevent damage. This transport logic is based on fuzzy logic inference using fuzzy rule interpolation, which allows for accurate inferences even when using a smaller rule base. The construction of the fuzzy rule base can be conducted experimentally, but there are also solutions for automatic construction. One of them is the bacterial evolutionary algorithm, which is used in this application. This algorithm is based on the theory of bacterial evolution and is very well-suited to solving optimization problems. Successful transport is also facilitated by proper path planning, and for this purpose, the so-called neuro-activity-based path planning has been used. This path-planning algorithm is combined with interpolative fuzzy logic-based speed control of the mobile robot. By applying the described methods, an intelligent transport logic can be constructed. These methods are tested in a simulated environment and several results are investigated.

ReNFuzz-LF: A Recurrent Neurofuzzy System for Short-Term Load Forecasting

A neurofuzzy system is proposed for short-term electric load forecasting. The fuzzy rule base of ReNFuzz-LF consists of rules with dynamic consequent parts that are small-scale recurrent neural networks with one hidden layer, whose neurons have local output feedback. The particular representation maintains the local learning nature of the typical static fuzzy model, since the dynamic consequent parts of the fuzzy rules can be considered as subsystems operating at the subspaces defined by the fuzzy premise parts, and they are interconnected through the defuzzification part. The Greek power system is examined, and hourly based predictions are extracted for the whole year. The recurrent nature of the forecaster leads to the use of a minimal set of inputs, since the temporal relations of the electric load time-series are identified without any prior knowledge of the appropriate past load values being necessary. An extensive simulation analysis is conducted, and the forecaster’s performance is evaluated using appropriate metrics (APE, RMSE, forecast error duration curve). ReNFuzz-LF performs efficiently, attaining an average percentage error of 1.35% and an average yearly absolute error of 86.3 MW. Finally, the performance of the proposed forecaster is compared to a series of Computational Intelligence based models, such that the learning characteristics of ReNFuzz-LF are highlighted.

Soft-sensing of effluent total phosphorus using adaptive recurrent fuzzy neural network with Gustafson-Kessel clustering

To address the issue of soft-sensing of effluent total phosphorus in wastewater treatment processes (WWTPs), a soft-sensing system based on an adaptive recursive fuzzy neural network with Gustafson-Kessel (GK) clustering and hierarchical adaptive second-order optimization algorithm (HAS) is proposed in this paper. In GK-ARFNN, first, the GK clustering algorithm was utilized to cluster the input–output dataset. Thus, the establishment of the initial fuzzy rule base and the determination of the parameter value of the fuzzy set membership function was realized. Then, the recursive layer was added into FNN to improve the dynamic mapping ability of the system. Finally, the HAS algorithm was developed based on the improved Levenberg-Marquardt (LM) optimization algorithm, and all the free parameters of the GK-ARFNN were adjusted online using HAS to improve the generalization capability and prediction accuracy of the soft-sensing system. In addition, the convergence of the proposed GK-ARFNN algorithm was also analyzed in this paper, which can ensure the effectiveness of the solutions to modelling issues for practical industrial processes. The simulation results demonstrate that the GK-ARFNN-based soft-sensing system introduced in this paper achieved satisfactory accuracy in the prediction of effluent total phosphorus in WWTPs. The source codes of GK-ARFNN and some competitors can be downloaded from https://github.com/hyitzhb/GK-ARFNN.

DEVELOPMENT OF A FUZZY MODEL OF A STUDENT INTELLIGENT TEACHING SYSTEM OF TECHNICAL DISCIPLINE

The development of computer technology provides great opportunities for modernizing the learning process. Teachers are actively introducing various electronic learning systems, the leading positions among which are occupied by intelligent learning systems. One of the tasks of developing an intelligent learning system is the implementation of dynamic adaptation of educational material to the level of knowledge of students. Therefore, it is necessary that it includes a student model that reflects the characteristics of the student that are important for managing the learning process. The paper describes the development of a fuzzy model of a student in teaching intelligent systems. This model is based on the concept of “student status”, the parameters of which are the level of mastering the discipline and the student’s personal qualities. A distinctive feature of the proposed fuzzy model is the joint use of the stereotypical and overlay models of the student. In addition, the developed fuzzy model is based not only on the assessment of student’s knowledge, but takes into account the personal qualities of students (responsibility, desire for self-learning and development, perseverance, attentiveness, stress tolerance). The paper proposes the use of a fuzzy expert system as a tool for decision support in determining the status of a student. During the operation of the expert system, the characteristics of students are evaluated, which are compared with the rules of the fuzzy rule base. When implementing a logical inference, a student is assigned one of the possible status values (beginner, trainee, master, professional and expert). At the final step, the student is offered to study the theoretical material of the discipline adapted to his characteristics.

Dynamic Energy Management for Perpetual Operation of Energy Harvesting Wireless Sensor Node Using Fuzzy Q-Learning

In an energy harvesting wireless sensor node (EHWSN), balance of energy harvested and consumption using dynamic energy management to achieve the goal of perpetual operation is one of the most important research topics. In this study, a novel fuzzy Q-learning (FQL)-based dynamic energy management (FQLDEM) is proposed in adapting its policy to the time varying environment, regarding both the harvested energy and the energy consumption of the WSN. The FQLDEM applies Q-learning to train, evaluate, and update the fuzzy rule base and then uses the fuzzy inference system (FIS) for determining the working duty cycle of the sensor of the EHWSN. Through the interaction with the energy harvesting environment, the learning agent of the FQL will be able to find the appropriate fuzzy rules in adapting the working duty cycle for the goal of energy neutrality such that the objective of perpetual operation of the EHWSN can be achieved. Experimental results show that the FQLDEM can maintain the battery charge status at a higher level than other existing methods did, such as the reinforcement learning (RL) method and dynamic duty cycle adaption (DDCA), and achieve the perpetual operation of the EHWSN. Furthermore, experimental results for required on-demand sensing measurements exhibit that the FQLDEM method can be slowly upgraded to meet 65% of the service quality control requirements in the early stage, which outperforms the RL-based and DDCA methods.

DEVELOPING A FUZZY RISK ASSESSMENT MODEL FOR ERPSYSTEMS

Context. Because assessing information security risks is a complex and complete uncertainty process, and uncer-tainties are a major factor influencing valuation performance, it is advisable to use fuzzy methods and models that are adaptive to non-calculated data. The formation of vague assessments of risk factors is subjective, and risk assessment depends on the practical results obtained in the process of processing the risks of threats that have already arisen during the functioning of the organization and experience of information security professionals. Therefore, it will be advisable to use models that can adequately assess fuzzy factors and have the ability to adjust their impact on risk assessment. The greatest performance indicators for solving such problems are neuro-fuzzy models that combine methods of fuzzy logic and artificial neural networks and systems, i.e. “human-like” style of considerations of fuzzy systems with training and simulation of mental phenomena of neural networks. To build a model for calculating the risk assessment of information security, it is proposed to use a fuzzy product model. Fuzzy product models (Rule-Based Fuzzy Models/Systems) this is a common type of fuzzy models used to describe, analyze and simulate complex systems and processes that are poorly formalized.
 Objective. Development of the structure of a fuzzy model of quality of information security risk assessment and protection of ERP systems through the use of fuzzy neural models.
 Method. To build a model for calculating the risk assessment of information security, it is proposed to use a fuzzy product model. Fuzzy product models are a common kind of fuzzy models used to describe, analyze and model complex systems and processes that are poorly formalized.
 Results. Identified factors influencing risk assessment suggest the use of linguistic variables to describe them and use fuzzy variables to assess their qualities, as well as a system of qualitative assessments. The choice of parameters is substantiated and the structure of the fuzzy product model of risk assessment and the basis of the rules of fuzzy logical conclusion is developed. The use of fuzzy models for solving problems of information security risk assessment, as well as the concept and construction of ERP systems and analyzed problems of their security and vulnerabilities are considered.
 Conclusions. A fuzzy model has been developed risk assessment of the ERP system. Selected a list of factors affecting the risk of information security. Methods of risk assessment of information resources and ERP-systems in general, assessment of financial losses from the implementation of threats, determination of the type of risk according to its assessment for the formation of recommendations on their processing in order to maintain the level of protection of the ERP-system are proposed. The list of linguistic variables of the model is defined. The structure of the database of fuzzy product rules – MISO-structure is chosen. The structure of the fuzzy model was built. Fuzzy variable models have been identified.

Fuzzy Logic Design to Control the Duration of Irrigation Time in the Greenhouse

Automatic irrigation is not new, this method has been invented by mankind to irrigate large areas of land through drip irrigation systems. The system is implemented to reduce water wastage in irrigation. In greenhouse irrigation control, computerized control is very important to increase productivity. On the other hand, conventional irrigation control in greenhouses is not effective, because it is based on on-off or proportional control. This paper presents a solution to control irrigation time duration based on fuzzy logic method. Fuzzy logic controller (FLC) was developed using the Mamdani method. FLC is built on the NodeMCU ESP8266 board mounted with a DHT22 and soil moisture sensor. Temperature and water content in the soil parameters are used as input for fuzzy logic to determine the duration of irrigation time. The linguistic values used as fuzzy membership functions include soil moisture (water, wet, dry), temperature (cold, normal, hot), and watering time (zero, short, medium, long). Based on the membership function, 9 fuzzy rule bases are determined. The testing results on fuzzy logic built on NodeMCU ESP8266 with fuzzy logic built on MATLAB software obtained an average error of 0.59%.

Industry 4.0 Roadmapping: A Fuzzy Linguistic Approach

Background: The industry 4.0 transition is becoming crucial for organizations. The lit-erature reviewed showed that whilst there are many studies on industry 4.0 assessment that help organizations to evaluate their current state, limited studies exist for road-mapping activities. Objective: The main aim of this study is to construct a model that leads organizations to their fourth industrial revolution transition. Companies, especially small and medium-sized ones (SMEs) need clear, agile and efficient road maps because of their limited resources. Lack of a procedure that guides organizations in the right way is the motivation of this study. Method: A linguistic fuzzy inference system is used in this study. Concepts are determined and relations between concepts with if-then rules have been constructed according to the expert opin-ion. MATLAB R2015a is used for the inference system. Results: An exemplary case is considered and the results show that the inference system can pro-vide company-specific roadmaps. To which extend an industry 4.0 concept should be taken into account for a company can be seen with the proposed method. Conclusion: The proposed method showed that specific and agile roadmaps could be obtained. Be-cause of the dependency of expert opinion for the fuzzy rule base, different methods for obtaining rules and relations may be a future research direction.

Query-focused multi-document text summarization using fuzzy inference

The present paper proposes a fuzzy inference system for query-focused multi-document text summarization (MTS). The overall scheme is based on Mamdani Inferencing scheme which helps in designing Fuzzy Rule base for inferencing about the decision variable from a set of antecedent variables. The antecedent variables chosen for the task are from linguistic and positional heuristics, and similarity of the documents with the user-defined query. The decision variable is the rank of the sentences as decided by the rules. The final summary is generated by solving an Integer Linear Programming problem. For abstraction coreference resolution is applied on the input sentences in the pre-processing step. Although designed on the basis of a small set of antecedent variables the results are very promising.