Linguistic Rule Extraction Research Articles

Interval Linguistic-Valued Intuitionistic Fuzzy Concept Lattice and Its Application to Linguistic Association Rule Extraction

Interval Linguistic-Valued Intuitionistic Fuzzy Concept Lattice and Its Application to Linguistic Association Rule Extraction

Evaluation of fuzzy membership functions for linguistic rule-based classifier focused on explainability, interpretability and reliability

Objective:Decision support systems focus on their interpretability with a different caution. The majority of approaches utilize reliable optimization techniques to achieve high recognition accuracy. However, accuracy improvement is done at the cost of the readability of the decision support system. This paper proposes a novel technique of linguistic rule extraction focused on: explainability, interpretability, and reliability, called EasIeR. Methods:Proposed solution performs a direct analysis of the learning set without omitting real data imperfections. The proposed algorithm processes the imprecision of data with linguistic values described by fuzzy membership functions and the uncertainty of knowledge employing a fuzzy belief function. It describes the learning set with the most appropriate fuzzy if-then rules. For this purpose, a new method of evaluation of membership functions in a set of rules and their iterative refinement is proposed. Results:EasIeR achieves the best results of trade-off criteria between the generalization quality and the interpretability of the knowledge base when compared with state-of-art fuzzy rule-based classification approaches. Achieving the simplest rule base and competitive generalization quality is verified by cross-validation experiments with benchmark data sets. Significance:The new method of rule evaluation allows for better determination of their quality in decision support, and the selection algorithm quickly provides a clear and easy to interpret knowledge base. This rule evaluation technique will be proficient for all fuzzy rule-based classification systems.

A fuzzy mobile decision support system for diagnosing of the angiographic status of heart disease

In estimating the risk of heart disease due to non-deterministic risk factors, often diagnosis of angiographic disease is difficult for physicians. For modeling and application of this uncertain and imprecise modality, decision support systems based on fuzzy logic are appropriate and an effective approach. Smartphone-based applications can facilitate the efficient use of these systems in form of evidence-based medicine. The aim of this applied study was developing and evaluating an application to diagnose angiographic disease conditions and the severity of heart attacks through a smartphone-based clinical decision support system. Android application development environment was utilized after extraction of linguistic rules and definition of membership functions needed for decisions. A smartphone-based application was designed using these guidelines and utilizing fuzzy modeling. Then, the app was evaluated in terms of accuracy using the popular Cleveland dataset. According to the results, 10 fuzzy rules for modeling, seven input variables and one decision variable were extracted. Programming was done in Eclipse. The evaluation results indicate that the accuracy of the program was 94%. Decision support systems within the context of mobile health have become some of the most efficient and influential information technology tools in recent years. They can improve patient-care management, provide easier access to the information needed for healthcare decisions and ultimately reduce healthcare costs while improving its quality.

Towards the Automatic Recommendation of Musical Parameters based on Algorithm for Extraction of Linguistic Rules

In the present article the authors describe an analysis of data associated to the emotional responses to fractal generated music. This analysis is done via discovery of rules, and it constitutes the basis to elevate computer-assisted creativity: Our ultimate goal is to cre­ ate musical pieces by retrieving the right set of parame­ ters associated to a target emotion. This paper contains the description of (i) variables associated to fractal music and emotions; (ii) the data gathering method to obtain the tuples relating input parameters and emotional re­ sponses; (iii) the rules that where discovered by using an algorithm LR-FIR. Even though similar experiments whose intention is to elucidate emotional responses from music have been reported, this study stands because a connection is appointed between fractal-generated mu­ sic and emotional responses, all with the purpose of advancing in computer-assisted creativity.

Frequent Itemsets from Multiple Datasets with Fuzzy data

Association rules from large Data warehouses are becoming increasingly important. In support of this trend, the paper proposes a new model for finding frequent itemsets from large databases that contain tables organized in a star schema with fuzzy taxonomic structures. The study aims to incorporate the previous developed algorithms on mining fuzzy generalized association rules and Mining Association rules in Entity relationship Models to discover a new algorithm. The paper focuses on the extraction of multi level linguistic association rules from multiple tables and examines the performance of extracted rules. An example given in the study demonstrates that the proposed mining algorithm can derive multi level fuzzy association rules from multiple datasets in a simple and effective manner.

A fuzzy inference system for pump failure diagnosis to improve maintenance process: The case of a petrochemical industry

Pump operating problems may be either hydraulic or mechanical and there is interdependence between the failure diagnoses of these two categories. Consequently, a correct diagnosis of a pump failure needs to consider many symptoms and hydraulic or mechanical causes. But, due to nonlinear, time-varying behavior and imprecise measurement information of the systems it is difficult to deal with pumps failures with precise mathematical equations, while human operators with the aid of their practical experience can handle these complex situations, with only a set of imprecise linguistic if-then rules and imprecise system state, but this procedure is time consuming and needs the knowledge of human experts and experienced maintenance personnel. The purpose of this study is to provide a correct and timely diagnosis mechanism of pump failures by knowledge acquisition through a fuzzy rule-based inference system which could approximate human reasoning. The proposed fuzzy inference system by: (1) reduction of human error, (2) reduction of repair time (3) creation of expert knowledge which could be used for training (4) reduction of unnecessary expenditures for upgrades and finally, (5) reduction of maintenance costs, will improve the maintenance process. The novelty of this work is the knowledge acquisition (the extraction of linguistic rules) through the interactive impact of the critical failure modes on the both hydraulic and mechanical operating parameters including flow rate, discharge pressure, NPSHR (Net Positive Suction Head Required), BHP (Brake Horse Power), efficiency, vibration and temperature. The proposed approach is tested and applied to a petrochemical industry.

Soft computing approach for modeling power plant with a once-through boiler

In this paper, a soft computing approach is presented for modeling electrical power generating plants in order to characterize the essential dynamic behavior of the plant subsystems. The structure of the soft computing method consists of fuzzy logic, neural networks and genetic algorithms. The measured data from a complete set of field experiments is the basis for training the models including the extraction of linguistic rules and membership functions as well as adjusting the other parameters of the fuzzy model. The genetic algorithm is applied to the modeling approach in order to optimize the procedure of the training. Comparison between the responses of the proposed models with the responses of the plants validates the accuracy and performance of the modeling approach. A similar comparison between the responses of these models with the models obtained based on the thermodynamical and physical relations of the plant shows the effectiveness and feasibility of the developed model in terms of more accurate and less deviation between the responses of the models and the corresponding subsystems.

Multiple objective evolutionary algorithm for temporal linguistic rule extraction

Autonomous temporal linguistic rule extraction is an application of growing interest for its relevance to both decision support systems and fuzzy controllers. In the presented work, rules are evaluated using three qualitative metrics based on their representation on the truth space diagram. Performance metrics are then treated as competing objectives and the multiple objective evolutionary algorithm is used to search for an optimal set of nondominant rules. Novel techniques for data pre-processing and rule set post-processing are designed that deal directly with the delays involved in dynamic systems. Data collected from a simulated hot and cold water mixer are used to validate the proposed procedure.

Linguistic Rule Extraction From a Simplified RBF Neural Network

Representing the concept of numerical data by linguistic rules is often desirable. In this paper, we present a novel rule-extraction algorithm from the radial basis function (RBF) neural network classifier for representing the hidden concept of numerical data. Gaussian function is used as the basis function of the RBF network. When training the RBF neural network, we allow for large overlaps between clusters corresponding to the same class, thereby reducing the number of hidden units while improving classification accuracy. The weights connecting the hidden units with the output units are then simplified. The interval for each input in the condition part of each rule is adjusted in order to obtain high accuracy in the extracted rules. Simulations using some bench-marking data sets demonstrate that our approach leads to more accurate and compact rules compared to other methods for extracting rules from RBF neural networks.

Three-objective genetics-based machine learning for linguistic rule extraction

Abstract This paper shows how a small number of linguistically interpretable fuzzy rules can be extracted from numerical data for high-dimensional pattern classification problems. One difficulty in the handling of high-dimensional problems by fuzzy rule-based systems is the exponential increase in the number of fuzzy rules with the number of input variables. Another difficulty is the deterioration in the comprehensibility of fuzzy rules when they involve many antecedent conditions. Our task is to design comprehensible fuzzy rule-based systems with high classification ability. This task is formulated as a combinatorial optimization problem with three objectives: to maximize the number of correctly classified training patterns, to minimize the number of fuzzy rules, and to minimize the total number of antecedent conditions. We show two genetic-algorithm-based approaches. One is rule selection where a small number of linguistically interpretable fuzzy rules are selected from a large number of prespecified candidate rules. The other is fuzzy genetics-based machine learning where rule sets are evolved by genetic operations. These two approaches search for non-dominated rule sets with respect to the three objectives.

Linguistic Rule Extraction from Numerical Data for High-dimensional Classification Problems

We discuss the linguistic rule extraction from numerical data for high-dimensional classification problems. Difficulties in the handling of high-dimensional problems stem from the curse of dimensionality: the number of combinations of antecedent linguistic values exponentially increases as the number of attributes increases. Our goal is to extract a small number of simple linguistic rules with high classification ability. In this paper, the rule extraction is to find a set of linguistic rules using three criteria: its classification ability, its compactness, and the simplicity of each rule. Our approach consists of two phases: candidate rule generation and rule selection. We first propose a pre-screening method for generating a tractable number of promising candidate rules for high-dimensional classification problems where it is impossible to examine all combinations of antecedent linguistic values. Next we show how genetic algorithms can be applied to the rule selection. Then we combine a heuristic rule elimination procedure with genetic algorithms for improving their search ability. Finally, the performance of our approach is examined by computer simulations on commonly used data sets.