Fuzzy Rule-based Classification Research Articles

A genetic tuning to improve the performance of Fuzzy Rule-Based Classification Systems with Interval-Valued Fuzzy Sets: Degree of ignorance and lateral position

Fuzzy Rule-Based Systems are appropriate tools to deal with classification problems due to their good properties. However, they can suffer a lack of system accuracy as a result of the uncertainty inherent in the definition of the membership functions and the limitation of the homogeneous distribution of the linguistic labels. The aim of the paper is to improve the performance of Fuzzy Rule-Based Classification Systems by means of the Theory of Interval-Valued Fuzzy Sets and a post-processing genetic tuning step. In order to build the Interval-Valued Fuzzy Sets we define a new function called weak ignorance for modeling the uncertainty associated with the definition of the membership functions. Next, we adapt the fuzzy partitions to the problem in an optimal way through a cooperative evolutionary tuning in which we handle both the degree of ignorance and the lateral position (based on the 2-tuples fuzzy linguistic representation) of the linguistic labels. The experimental study is carried out over a large collection of data-sets and it is supported by a statistical analysis. Our results show empirically that the use of our methodology outperforms the initial Fuzzy Rule-Based Classification System. The application of our cooperative tuning enhances the results provided by the use of the isolated tuning approaches and also improves the behavior of the genetic tuning based on the 3-tuples fuzzy linguistic representation.

Interpretability assessment of fuzzy knowledge bases: A cointension based approach

Computing with words (CWW) relies on linguistic representation of knowledge that is processed by operating at the semantical level defined through fuzzy sets. Linguistic representation of knowledge is a major issue when fuzzy rule based models are acquired from data by some form of empirical learning. Indeed, these models are often requested to exhibit interpretability, which is normally evaluated in terms of structural features, such as rule complexity, properties on fuzzy sets and partitions. In this paper we propose a different approach for evaluating interpretability that is based on the notion of cointension. The interpretability of a fuzzy rule-based model is measured in terms of cointension degree between the explicit semantics, defined by the formal parameter settings of the model, and the implicit semantics conveyed to the reader by the linguistic representation of knowledge. Implicit semantics calls for a representation of user’s knowledge which is difficult to externalise. Nevertheless, we identify a set of properties – which we call “logical view” – that is expected to hold in the implicit semantics and is used in our approach to evaluate the cointension between explicit and implicit semantics. In practice, a new fuzzy rule base is obtained by minimising the fuzzy rule base through logical properties. Semantic comparison is made by evaluating the performances of the two rule bases, which are supposed to be similar when the two semantics are almost equivalent. If this is the case, we deduce that the logical view is applicable to the model, which can be tagged as interpretable from the cointension viewpoint. These ideas are then used to define a strategy for assessing interpretability of fuzzy rule-based classifiers (FRBCs). The strategy has been evaluated on a set of pre-existent FRBCs, acquired by different learning processes from a well-known benchmark dataset. Our analysis highlighted that some of them are not cointensive with user’s knowledge, hence their linguistic representation is not appropriate, even though they can be tagged as interpretable from a structural point of view.

Fuzzy Rule-based Classification of Human Tracking and Segmentation using Color Space Conversion

Fuzzy Rule-based Classification of Human Tracking and Segmentation using Color Space Conversion

A novel multi-model neuro-fuzzy-based MPPT for three-phase grid-connected photovoltaic system

This paper presents a novel methodology for Maximum Power Point Tracking (MPPT) of a grid-connected 20 kW photovoltaic (PV) system using neuro-fuzzy network. The proposed method predicts the reference PV voltage guarantying optimal power transfer between the PV generator and the main utility grid. The neuro-fuzzy network is composed of a fuzzy rule-based classifier and three multi-layered feed forwarded Artificial Neural Networks (ANN). Inputs of the network (irradiance and temperature) are classified before they are fed into the appropriated ANN for either training or estimation process while the output is the reference voltage. The main advantage of the proposed methodology, comparing to a conventional single neural network-based approach, is the distinct generalization ability regarding to the nonlinear and dynamic behavior of a PV generator. In fact, the neuro-fuzzy network is a neural network based multi-model machine learning that defines a set of local models emulating the complex and nonlinear behavior of a PV generator under a wide range of operating conditions. Simulation results under several rapid irradiance variations proved that the proposed MPPT method fulfilled the highest efficiency comparing to a conventional single neural network and the Perturb and Observe (P&O) algorithm dispositive.

A general framework for designing a fuzzy rule-based classifier

This paper presents a general framework for designing a fuzzy rule-based classifier. Structure and parameters of the classifier are evolved through a two-stage genetic search. To reduce the search space, the classifier structure is constrained by a tree created using the evolving SOM tree algorithm. Salient input variables are specific for each fuzzy rule and are found during the genetic search process. It is shown through computer simulations of four real world problems that a large number of rules and input variables can be eliminated from the model without deteriorating the classification accuracy. By contrast, the classification accuracy of unseen data is increased due to the elimination.

Analysis of an evolutionary RBFN design algorithm, CO 2RBFN, for imbalanced data sets

In the classification problem field, we often encounter many real application areas in which the data do not have an equitable distribution among the different classes of the problem. In such cases, we are dealing with the so-called imbalanced data sets. This scenario has significant interest since standard classifiers are often biased towards the majority classes, whereas the minority ones tend to have a higher reward as they usually define the concepts of interest from the learning point of view. The aim of this paper is to analyse the performance of CO 2RBFN, a evolutionary cooperative–competitive model for the design of radial-basis function networks applied to classification problems on imbalanced domains, and to study its cooperation with a well-known pre-processing method, the “synthetic minority over-sampling technique”. The good performance of CO 2RBFN is shown through an experimental study carried out on a large collection of imbalanced data sets where we compare, by means of a proper statistical study, the behaviour of our model with many representative neural networks algorithms, the C4.5 decision tree and a hierarchical fuzzy rule-based classification system.

A Fuzzy Rule-Based Approach for Islanding Detection in Distributed Generation

The proposed method develops a fuzzy rule-based classifier that was tested using features for islanding detection in distributed generation. In the developed technique, the initial classification boundaries are found out by using the decision tree (DT). From the DT classification boundaries, the fuzzy membership functions (MFs) are developed and the corresponding rule base is formulated for islanding detection. But some of the fuzzy MFs are merged based upon similarity the measure for reducing the fuzzy MFs and simplifying the fuzzy rule base to make it more transparent. The developed fuzzy rule-based classifier is tested using features with noise up to a signal-to-noise ratio of 20 dB and provides classification results without misdetection, which shows the robustness of the proposed approach for islanding detection for distributed generations in the distribution network.

HILK++: an interpretability-guided fuzzy modeling methodology for learning readable and comprehensible fuzzy rule-based classifiers

This work presents a methodology for building interpretable fuzzy systems for classification problems. We consider interpretability from two points of view: (1) readability of the system description and (2) comprehensibility of the system behavior explanations. The fuzzy modeling methodology named as Highly Interpretable Linguistic Knowledge (HILK) is upgraded. Firstly, a feature selection procedure based on crisp decision trees is carried out. Secondly, several strong fuzzy partitions are automatically generated from experimental data for all the selected inputs. For each input, all partitions are compared and the best one according to data distribution is selected. Thirdly, a set of linguistic rules are defined combining the previously generated linguistic variables. Then, a linguistic simplification procedure guided by a novel interpretability index is applied to get a more compact and general set of rules with a minimum loss of accuracy. Finally, partition tuning based on two efficient search strategies increases the system accuracy while preserving the high interpretability. Results obtained in several benchmark classification problems are encouraging because they show the ability of the new methodology for generating highly interpretable fuzzy rule-based classifiers while yielding accuracy comparable to that achieved by other methods like neural networks and C4.5. The best configuration of HILK will depend on each specific problem under consideration but it is important to remark that HILK is flexible enough (thanks to the combination of several algorithms in each modeling stage) to be easily adaptable to a wide range of problems.

Improving the performance of fuzzy rule-based classification systems with interval-valued fuzzy sets and genetic amplitude tuning

Among the computational intelligence techniques employed to solve classification problems, Fuzzy Rule-Based Classification Systems (FRBCSs) are a popular tool because of their interpretable models based on linguistic variables, which are easier to understand for the experts or end-users. The aim of this paper is to enhance the performance of FRBCSs by extending the Knowledge Base with the application of the concept of Interval-Valued Fuzzy Sets (IVFSs). We consider a post-processing genetic tuning step that adjusts the amplitude of the upper bound of the IVFS to contextualize the fuzzy partitions and to obtain a most accurate solution to the problem. We analyze the goodness of this approach using two basic and well-known fuzzy rule learning algorithms, the Chi et al.’s method and the fuzzy hybrid genetics-based machine learning algorithm. We show the improvement achieved by this model through an extensive empirical study with a large collection of data-sets.

A novel fuzzy rule base system for pose independent faces detection

Human face detection plays an important role in a wide range of applications such as face recognition, surveillance systems, video tracking applications, and image database management. In this paper, a novel fuzzy rule-based system for pose, size, and position independent face detection in color images is proposed. Subtractive clustering method is also applied to decide on the numbers of membership functions. In the proposed system, skin-color, lips position, face shape information and ear texture properties are the key parameters fed to the fuzzy rule-based classifier to extract face candidate in an image. Furthermore, the applied threshold on the face candidates is optimized by genetic algorithm. The proposed system consists of two main stages: the frontal/near frontal face detections and the profile face detection. In the first stage, skin and lips regions are identified in HSI color space, using fuzzy schemes, where the distances of each pixel color to skin-color and lips-color clusters are applied as the input and skin-likelihood and lips-like images are produced as the output. Then, the labeled skin and lips regions are presented to both frontal and profile face detection algorithms. A fuzzy rule-based containing the face and lips position data, along with the lips area and face shape are employed to extract the frontal/near frontal face regions. On the other hand, the profile face detection algorithm uses a geometric moments-based ear texture classification to verify its outcomes. The proposed method is tried on various databases, including HHI, Champion, Caltech, Bao, Essex and IMM databases. It shows about 98, 96 and 90% correct detection rates over 783 samples, in frontal, near frontal and profile face images, respectively.

SUBCLASS FUZZY-SVM CLASSIFIER AS AN EFFICIENT METHOD TO ENHANCE THE MASS DETECTION IN MAMMOGRAMS

This paper is concerned with the development of a novel classifier for automatic mass detection of mammograms, based on contourlet feature extraction in conjunction with statistical and fuzzy classifiers. In this method, mammograms are segmented into regions of interest (ROI) in order to extract features including geometrical and contourlet coecients. The extracted fea- tures benefit from the superiority of the contourlet method to the state of the art multi-scale techniques. A genetic algorithm is applied for feature weighting with the objective of increasing classification accuracy. Although fuzzy clas- sifiers are interpretable, the majority are order sensitive and suer from the lack of generalization. In this study, a kernel SVM is integrated with a nero- fuzzy rule-based classifier to form a support vector based fuzzy neural network ( SVFNN). This classifier benefits from the superior classification power of SVM in high dimensional data spaces and also from the ecient human-like reasoning of fuzzy and neural networks in handling uncertainty information. We use the Mammographic Image Analysis Society (MIAS) standard data set and the features extracted of the digital mammograms are applied to the fuzzy-SVM classifiers to assess the performance. Our experiments resulted in 95.6%,91.52%,89.02%, 85.31% classification accuracy for the subclass FSVM, SVFNN, fuzzy rule based and kernel SVM classifiers respectively and we con- clude that the subclass fuzzy-SVM is superior to the other classifiers.

GP-COACH: Genetic Programming-based learning of COmpact and ACcurate fuzzy rule-based classification systems for High-dimensional problems

In this paper we propose GP-COACH, a Genetic Programming-based method for the learning of COmpact and ACcurate fuzzy rule-based classification systems for High-dimensional problems. GP-COACH learns disjunctive normal form rules (generated by means of a context-free grammar) coded as one rule per tree. The population constitutes the rule base, so it is a genetic cooperative-competitive learning approach. GP-COACH uses a token competition mechanism to maintain the diversity of the population and this obliges the rules to compete and cooperate among themselves and allows the obtaining of a compact set of fuzzy rules. The results obtained have been validated by the use of non-parametric statistical tests, showing a good performance in terms of accuracy and interpretability.

Data Mining of Gene Expression Data by Fuzzy and Hybrid Fuzzy Methods

Microarray studies and gene expression analysis have received tremendous attention over the last few years and provide many promising avenues toward the understanding of fundamental questions in biology and medicine. Data mining of these vasts amount of data is crucial in gaining this understanding. In this paper, we present a fuzzy rule-based classification system that allows for effective analysis of gene expression data. The applied classifier consists of a set of fuzzy if-then rules that enable accurate nonlinear classification of input patterns. We further present a hybrid fuzzy classification scheme in which a small number of fuzzy if-then rules are selected through means of a genetic algorithm, leading to a compact classifier for gene expression analysis. Extensive experimental results on various well-known gene expression datasets confirm the efficacy of our approaches.

MINING SIMPLIFIED FUZZY IF-THEN RULES FOR PATTERN CLASSIFICATION

A fuzzy if-then rule whose consequent part is a real number is referred to as a simplified fuzzy rule. Simplified fuzzy if-then rules have been widely used in function approximation problems due to no complicated defuzzification is required. The proposed simplified fuzzy rule-based classification system, whose number of output is equal to the number of different classes, approximates an unknown mapping from input to desired output for each discriminant function. Not only a fuzzy data mining method is proposed to find simplified fuzzy if-then rules from training data, but also the genetic algorithm is employed to determine some user-specified parameters. To evaluate the classification performance of the proposed method, computer simulations are performed on some well-known datasets, showing that the generalization ability of the proposed method is comparable to the other fuzzy or nonfuzzy methods.

An interpretable fuzzy rule-based classification methodology for medical diagnosis

The aim of this paper is to present a novel fuzzy classification framework for the automatic extraction of fuzzy rules from labeled numerical data, for the development of efficient medical diagnosis systems. The proposed methodology focuses on the accuracy and interpretability of the generated knowledge that is produced by an iterative, flexible and meaningful input partitioning mechanism. The generated hierarchical fuzzy rule structure is composed by linguistic; multiple consequent fuzzy rules that considerably affect the model comprehensibility. The performance of the proposed method is tested on three medical pattern classification problems and the obtained results are compared against other existing methods. It is shown that the proposed variable input partitioning leads to a flexible decision making framework and fairly accurate results with a small number of rules and a simple, fast and robust training process.

Multi-objective genetic fuzzy classifiers for imbalanced and cost-sensitive datasets

We exploit an evolutionary three-objective optimization algorithm to produce a Pareto front approximation composed of fuzzy rule-based classifiers (FRBCs) with different trade-offs between accuracy (expressed in terms of sensitivity and specificity) and complexity (computed as sum of the conditions in the antecedents of the classifier rules). Then, we use the ROC convex hull method to select the potentially optimal classifiers in the projection of the Pareto front approximation onto the ROC plane. Our method was tested on 13 highly imbalanced datasets and compared with 2 two-objective evolutionary approaches and one heuristic approach to FRBC generation, and with three well-known classifiers. We show by the Wilcoxon signed-rank test that our three-objective optimization approach outperforms all the other techniques, except for one classifier, in terms of the area under the ROC convex hull, an accuracy measure used to globally compare different classification approaches. Further, all the FRBCs in the ROC convex hull are characterized by a low value of complexity. Finally, we discuss how, the misclassification costs and the class distributions are fixed, we can select the most suitable classifier for the specific application. We show that the FRBC selected from the convex hull produced by our three-objective optimization approach achieves the lowest classification cost among the techniques used as comparison in two specific medical applications.

FURIA: an algorithm for unordered fuzzy rule induction

This paper introduces a novel fuzzy rule-based classification method called FURIA, which is short for Fuzzy Unordered Rule Induction Algorithm. FURIA extends the well-known RIPPER algorithm, a state-of-the-art rule learner, while preserving its advantages, such as simple and comprehensible rule sets. In addition, it includes a number of modifications and extensions. In particular, FURIA learns fuzzy rules instead of conventional rules and unordered rule sets instead of rule lists. Moreover, to deal with uncovered examples, it makes use of an efficient rule stretching method. Experimental results show that FURIA significantly outperforms the original RIPPER, as well as other classifiers such as C4.5, in terms of classification accuracy.

Protein Superfamily Classification Using Fuzzy Rule-Based Classifier

In this paper, we have proposed a fuzzy rule-based classifier for assigning amino acid sequences into different superfamilies of proteins. While the most popular methods for protein classification rely on sequence alignment, our approach is alignment-free and so more human readable. It accounts for the distribution of contiguous patterns of n amino acids ( n-grams) in the sequences as features, alike other alignment-independent methods. Our approach, first extracts a plenty of features from a set of training sequences, then selects only some best of them, using a proposed feature ranking method. Thereafter, using these features, a novel steady-state genetic algorithm for extracting fuzzy classification rules from data is used to generate a compact set of interpretable fuzzy rules. The generated rules are simple and human understandable. So, the biologists can utilize them, for classification purposes, or incorporate their expertise to interpret or even modify them. To evaluate the performance of our fuzzy rule-based classifier, we have compared it with the conventional nonfuzzy C4.5 algorithm, beside some other fuzzy classifiers. This comparative study is conducted through classifying the protein sequences of five superfamily classes, downloaded from a public domain database. The obtained results show that the generated fuzzy rules are more interpretable, with acceptable improvement in the classification accuracy.

Development of Rule-Based Classifiers for Rapid Stability Assessment of Wide-Area Post-Disturbance Records

The paper proposes a systematic scheme for building compact and transparent fuzzy rule-based classifiers for rapid stability assessment; the classifiers are initialized by large accurate decision trees (DTs). The approach starts by selecting strategic monitoring buses where phasor measurement units (PMUs) are placed to capture wide-area response signals in real-time operation. These measurements are processed in the time and frequency domains for extracting selected decision features such as the peak spectral density of the angle, frequency and their dot product evaluated over the grid areas. These so-called wide-area severity indices (WASI) are reliable time-varying stability indicators that form the basis of an effective classification system. Large-size DTs are used to generate initial accurate classification boundaries for decision making as early as 1 s or 2 s after fault clearing. From the DT classification boundaries, fuzzy membership functions (MFs) are developed and the corresponding fuzzy rule base is formulated parsimoniously by eliminating redundant MFs and rules using a similarity measure. The resulting fuzzy-rule classifiers are successfully tested for system-wise and area-wise contingencies based on a large database of detailed simulations of the Hydro-Quebec grid and are further confirmed on actual measurements recorded with existing wide-area measurements (WAMS).

Feature selection and fuzzy rule-based classifier applied to bankruptcy prediction in banks

We propose a fuzzy 'if-then' rule-based expert system preceded by feature selection for predicting bankruptcy in Turkish, Spanish and the UK banks. The system comprises three phases: feature selection, rule generation and optimisation. Feature selection reduces the number of rule antecedents, thereby enhancing human comprehensibility without sacrificing accuracy. Top five features are selected using wavelet neural network-based algorithm, t-statistic and f-statistic. Then, the reduced set of features is fed to a fuzzy rule-based classifier (FRBC) that generates rules and the third phase optimises the rule base. Tenfold cross-validation is performed throughout. The frequency of the presence of a rule in each fold decides the common rule base. The experiments are conducted for 2-4 partitions and area under receiver operating characteristic curve criterion selects the optimal partition and the best feature selection algorithm. Results indicate the effectiveness of FRBC with feature selection in predicting bank bankruptcy.