Autonomous learning for fuzzy systems: a review

As one of the three pillars in computational intelligence, fuzzy systems are a powerful mathematical tool widely used for modelling nonlinear problems with uncertainties. Fuzzy systems take the form of linguistic IF-THEN fuzzy rules that are easy to understand for human. In this sense, fuzzy inference mechanisms have been developed to mimic human reasoning and decision-making. From a data analytic perspective, fuzzy systems provide an effective solution to build precise predictive models from imprecise data with great transparency and interpretability, thus facilitating a wide range of real-world applications. This paper presents a systematic review of modern methods for autonomously learning fuzzy systems from data, with an emphasis on the structure and parameter learning schemes of mainstream evolving, evolutionary, reinforcement learning-based fuzzy systems. The main purpose of this paper is to introduce the underlying concepts, underpinning methodologies, as well as outstanding performances of the state-of-the-art methods. It serves as a one-stop guide for readers learning the representative methodologies and foundations of fuzzy systems or who desire to apply fuzzy-based autonomous learning in other scientific disciplines and applied fields.

Fuzzy Algorithms for Diagnosis of Furnace Transformer Insulation Condition

Implementation of the smart transformer concept is critical for the deployment of IIoT-based smart grids. Top manufacturers of power electrics develop and adopt online monitoring systems. Such systems become part of high-voltage grid and unit transformers. However, furnace transformers are a broad category that this change does not affect yet. At the same time, adoption of diagnostic systems for furnace transformers is relevant because they are a heavy-duty application with no redundancy. Creating any such system requires a well-founded mathematical analysis of the facility’s condition, carefully selected diagnostic parameters, and setpoints thereof, which serve as the condition categories. The goal hereof was to create an expert system to detect insulation breach and its expansion as well as to evaluate the risk it poses to the system; the core mechanism is mathematical processing of trends in partial discharge (PD). We ran tests on a 26-MVA transformer installed on a ladle furnace at a steelworks facility. The transformer is equipped with a versatile condition monitoring system that continually measures apparent charge and PD intensity. The objective is to identify the condition of the transformer and label it with one of the generally recognized categories: Normal, Poor, Critical. The contribution of this paper consists of the first ever validation of a single generalized metric that describes the condition of transformer insulation based on the online monitoring of the PD parameters. Fuzzy logic algorithms are used in mathematical processing. The proposal is to generalize the set of diagnostic variables to a single deterministic parameter: insulation state indicator. The paper provides an example of calculating it from the apparent charge and PD power readings. To measure the indicativeness of individual parameters for predicting further development of a defect, the authors developed a method for testing the diagnostic sensitivity of these parameters to changes in the condition. The method was tested using trends in readings sampled whilst the status was degrading from Normal to Critical. The paper also shows a practical example of defect localization. The recommendation is to broadly use the method in expert systems for high-voltage equipment monitoring.

A novel ensemble fuzzy classification model in SARS-CoV-2 B-cell epitope identification for development of protein-based vaccine

B-cell epitope prediction research has received growing interest since the development of the first method. B-cell epitope identification with the aid of an accurate prediction method is one of the most important steps in epitope-based vaccine development, immunodiagnostic testing, antibody production, disease diagnosis, and treatment. Nevertheless, using experimental methods in epitope mapping is very time-consuming, costly, and labor-intensive. Therefore, although successful predictions with in silico methods are very important in epitope prediction, there are limited studies in this area. The aim of this study is to propose a new approach for successfully predicting B-cell epitopes for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). In this study, the SARS-CoV B-cell epitope prediction performances of different fuzzy learning classification models genetic cooperative competitive learning (GCCL), fuzzy genetics-based machine learning (GBML), Chi's method (CHI), Ishibuchi's method with weight factor (W), structural learning algorithm on vague environment (SLAVE) and the state-of-the-art ensemble fuzzy classification model were compared. The obtained results showed that the proposed ensemble approach has the lowest error in SARS-CoV B-cell epitope estimation compared to the base fuzzy learners (average error rates; ensemble fuzzy=8.33, GCCL=30.42, GBML=23.82, CHI=29.17, W=46.25, and SLAVE=20.42). SARS-CoV and SARS-CoV-2 have high genome similarities. Therefore, the most successful method determined for SARS-CoV B-cell epitope prediction was used in SARS-CoV-2 cell epitope prediction. Finally, the eventual B-cell epitope prediction results obtained for SARS-CoV-2 with the ensemble fuzzy classification model were compared with the epitope sequences predicted by the BepiPred server and immunoinformatics studies in the literature for the same protein sequences according to VaxiJen 2.0 scores. We hope that the developed epitope prediction method will help design effective vaccines and drugs against future outbreaks of the coronavirus family, especially SARS-CoV-2 and its possible mutations.

White striping degree assessment using computer vision system and consumer acceptance test

OBJECTIVE

The objective of this study was to evaluate three different degrees of white striping (WS) addressing their automatic assessment and customer acceptance. The WS classification was performed based on a computer vision system (CVS), exploring different machine learning (ML) algorithms and the most important image features. Moreover, it was verified by consumer acceptance and purchase intent.

METHODS

The samples for image analysis were classified by trained specialists, according to severity degrees regarding visual and firmness aspects. Samples were obtained with a digital camera, and 25 features were extracted from these images. ML algorithms were applied aiming to induce a model capable of classifying the samples into three severity degrees. In addition, two sensory analyses were performed: 75 samples properly grilled were used for the first sensory test, and 9 photos for the second. All tests were performed using a 10-cm hybrid hedonic scale (acceptance test) and a 5-point scale (purchase intention).

RESULTS

The information gain metric ranked 13 attributes. However, just one type of image feature was not enough to describe the phenomenon. The classification models support vector machine, fuzzy-W, and random forest showed the best results with similar general accuracy (86.4%). The worst performance was obtained by multilayer perceptron (70.9%) with the high error rate in normal (NORM) sample predictions. The sensory analysis of acceptance verified that WS myopathy negatively affects the texture of the broiler breast fillets when grilled and the appearance attribute of the raw samples, which influenced the purchase intention scores of raw samples.

CONCLUSION

The proposed system has proved to be adequate (fast and accurate) for the classification of WS samples. The sensory analysis of acceptance showed that WS myopathy negatively affects the tenderness of the broiler breast fillets when grilled, while the appearance attribute of the raw samples eventually influenced purchase intentions.

Intelligent methodology for project conceptual cost prediction

Developing a reliable parametric cost model at the conceptual stage of the project is crucial for projects managers and decision makers. Several methodologies exist to develop a conceptual cost model. However, many gaps exist in the current methodologies such as depending only on experts 'opinions and questionnaire survey to identify the project features, key cost drivers and developing deterministic predictive models without taking uncertainty nature into consideration. The main contribution of this study is developing an intelligent methodology for predicting the project cost at the conceptual stage. The proposed methodology can automatically identify key cost drivers and maintain uncertainty to predicted cost. Field canals improvement projects (FCIPs) are used as a case study to validate the proposed methodology. The selected methodology has applied quantitative approaches to identify the key cost drivers. In addition, the methodology has applied a genetic fuzzy model that automatically generates fuzzy rules to automatically predict the conceptual cost. Moreover, the results show a superior performance of the genetic fuzzy model than the traditional fuzzy model. In addition, this study presents a publicly open dataset for FCIPs to be used for future models validation and analysis.

Prediction of infarction volume and infarction growth rate in acute ischemic stroke

The prediction of infarction volume after stroke onset depends on the shape of the growth dynamics of the infarction. To understand growth patterns that predict lesion volume changes, we studied currently available models described in literature and compared the models with Adaptive Neuro-Fuzzy Inference System [ANFIS], a method previously unused in the prediction of infarction growth and infarction volume (IV). We included 67 patients with malignant middle cerebral artery [MMCA] stroke who underwent decompressive hemicraniectomy. All patients had at least three cranial CT scans prior to the surgery. The rate of growth and volume of infarction measured on the third CT was predicted with ANFIS without statistically significant difference compared to the ground truth [P = 0.489]. This was not possible with linear, logarithmic or exponential methods. ANFIS was able to predict infarction volume [IV3] over a wide range of volume [163.7–600 cm³] and time [22–110 hours]. The cross correlation [CRR] indicated similarity between the ANFIS-predicted IV3 and original data of 82% for ANFIS, followed by logarithmic 70%, exponential 63% and linear 48% respectively. Our study shows that ANFIS is superior to previously defined methods in the prediction of infarction growth rate (IGR) with reasonable accuracy, over wide time and volume range.

Evolutionary approach to violating group anonymity using third-party data

In the era of Big Data, it is almost impossible to completely restrict access to primary non-aggregated statistical data. However, risk of violating privacy of individual respondents and groups of respondents by analyzing primary data has not been reduced. There is a need in developing subtler methods of data protection to come to grips with these challenges. In some cases, individual and group privacy can be easily violated, because the primary data contain attributes that uniquely identify individuals and groups thereof. Removing such attributes from the dataset is a crude solution and does not guarantee complete privacy. In the field of providing individual data anonymity, this problem has been widely recognized, and various methods have been proposed to solve it. In the current work, we demonstrate that it is possible to violate group anonymity as well, even if those attributes that uniquely identify the group are removed. As it turns out, it is possible to use third-party data to build a fuzzy model of a group. Typically, such a model comes in a form of a set of fuzzy rules, which can be used to determine membership grades of respondents in the group with a level of certainty sufficient to violate group anonymity. In the work, we introduce an evolutionary computing based method to build such a model. We also discuss a memetic approach to protecting the data from group anonymity violation in this case.

An Interval Type-2 Neural Fuzzy System for Online System Identification and Feature Elimination

We propose an integrated mechanism for discarding derogatory features and extraction of fuzzy rules based on an interval type-2 neural fuzzy system (NFS)-in fact, it is a more general scheme that can discard bad features, irrelevant antecedent clauses, and even irrelevant rules. High-dimensional input variable and a large number of rules not only enhance the computational complexity of NFSs but also reduce their interpretability. Therefore, a mechanism for simultaneous extraction of fuzzy rules and reducing the impact of (or eliminating) the inferior features is necessary. The proposed approach, namely an interval type-2 Neural Fuzzy System for online System Identification and Feature Elimination (IT2NFS-SIFE), uses type-2 fuzzy sets to model uncertainties associated with information and data in designing the knowledge base. The consequent part of the IT2NFS-SIFE is of Takagi-Sugeno-Kang type with interval weights. The IT2NFS-SIFE possesses a self-evolving property that can automatically generate fuzzy rules. The poor features can be discarded through the concept of a membership modulator. The antecedent and modulator weights are learned using a gradient descent algorithm. The consequent part weights are tuned via the rule-ordered Kalman filter algorithm to enhance learning effectiveness. Simulation results show that IT2NFS-SIFE not only simplifies the system architecture by eliminating derogatory/irrelevant antecedent clauses, rules, and features but also maintains excellent performance.

A Fuzzy Kernel Motion Classifier for Autonomous Stroke Rehabilitation

Autonomous poststroke rehabilitation systems which can be deployed outside hospital with no or reduced supervision have attracted increasing amount of research attentions due to the high expenditure associated with the current inpatient stroke rehabilitation systems. To realize an autonomous systems, a reliable patient monitoring technique which can automatically record and classify patient's motion during training sessions is essential. In order to minimize the cost and operational complexity, the combination of nonvisual-based inertia sensing devices and pattern recognition algorithms are often considered more suitable in such applications. However, the high motion irregularity due to stroke patients' body function impairment has significantly increased the classification difficulty. A novel fuzzy kernel motion classifier specifically designed for stroke patient's rehabilitation training motion classification is presented in this paper. The proposed classifier utilizes geometrically unconstrained fuzzy membership functions to address the motion class overlapping issue, and thus, it can achieve highly accurate motion classification even with poorly performed motion samples. In order to validate the performance of the classifier, experiments have been conducted using real motion data sampled from stroke patients with a wide range of impairment level and the results have demonstrated that the proposed classifier is superior in terms of error rate compared to other popular algorithms.

Modeling hourly dissolved oxygen concentration (DO) using two different adaptive neuro-fuzzy inference systems (ANFIS): a comparative study

This article presents a comparison of two adaptive neuro-fuzzy inference systems (ANFIS)-based neuro-fuzzy models applied for modeling dissolved oxygen (DO) concentration. The two models are developed using experimental data collected from the bottom (USGS station no: 420615121533601) and top (USGS station no: 420615121533600) stations at Klamath River at site KRS12a nr Rock Quarry, Oregon, USA. The input variables used for the ANFIS models are water pH, temperature, specific conductance, and sensor depth. Two ANFIS-based neuro-fuzzy systems are presented. The two neuro-fuzzy systems are: (1) grid partition-based fuzzy inference system, named ANFIS_GRID, and (2) subtractive-clustering-based fuzzy inference system, named ANFIS_SUB. In both models, 60 % of the data set was randomly assigned to the training set, 20 % to the validation set, and 20 % to the test set. The ANFIS results are compared with multiple linear regression models. The system proposed in this paper shows a novelty approach with regard to the usage of ANFIS models for DO concentration modeling.

Analysis of a multilevel diagnosis decision support system and its implications: a case study

Medical diagnosis can be performed in an automatic way with the use of computer-based systems or algorithms. Such systems are usually called diagnostic decision support systems (DDSSs) or medical diagnosis systems (MDSs). An evaluation of the performance of a DDSS called ML-DDSS has been performed in this paper. The methodology is based on clinical case resolution performed by physicians which is then used to evaluate the behavior of ML-DDSS. This methodology allows the calculation of values for several well-known metrics such as precision, recall, accuracy, specificity, and Matthews correlation coefficient (MCC). Analysis of the behavior of ML-DDSS reveals interesting results about the behavior of the system and of the physicians who took part in the evaluation process. Global results show how the ML-DDSS system would have significant utility if used in medical practice. The MCC metric reveals an improvement of about 30% in comparison with the experts, and with respect to sensitivity the system returns better results than the experts.

An approach for solving multi-level diagnosis in high sensitivity medical diagnosis systems through the application of semantic technologies

The capability of medical diagnosis systems to provide results in different situations depends on the modeling of the knowledge base. In the case of high sensitivity systems, the capability of having an adequate model allows to increase the accuracy of the system even in situations where the number of input elements is low. In this context the concept of multi-level diagnosis emerges, where a pathology can be assumed as a diagnostic element of another pathology (acting as a finding). In this paper this concept is studied in depth from the modeling point of view, providing a solution based on rule inference techniques modeled with semantic technologies, and allowing solving the problem generated by multi-level diagnosis.

Some novel classifiers designed using prototypes extracted by a new scheme based on self-organizing feature map

We propose two new comprehensive schemes for designing prototype-based classifiers. The scheme addresses all major issues (number of prototypes, generation of prototypes, and utilization of the prototypes) involved in the design of a prototype-based classifier. First we use Kohonen's self-organizing feature map (SOFM) algorithm to produce a minimum number (equal to the number of classes) of initial prototypes. Then we use a dynamic prototype generation and tuning algorithm (DYNAGEN) involving merging, splitting, deleting, and retraining of the prototypes to generate an adequate number of useful prototypes. These prototypes are used to design a "1 nearest multiple prototype (1-NMP)" classifier. Though the classifier performs quite well, it cannot reasonably deal with large variation of variance among the data from different classes. To overcome this deficiency we design a "1 most similar prototype (1-MSP)" classifier. We use the prototypes generated by the SOFM-based DYNAGEN algorithm and associate with each of them a zone of influence. A norm (Euclidean)-induced similarity measure is used for this. The prototypes and their zones of influence are fine-tuned by minimizing an error function. Both classifiers are trained and tested using several data sets, and a consistent improvement in performance of the latter over the former has been observed. We also compared our classifiers with some benchmark results available in the literature.

HANDLING HIGHLY-DIMENSIONAL CLASSIFICATION TASKS WITH HIERARCHICAL GENETIC FUZZY RULE-BASED CLASSIFIERS

Many modern classification tasks are defined in highly-dimensional feature spaces. The derivation of high-performing genetic fuzzy rule-based classification systems (GFRBCSs) in such scenarios is a non-trivial task. This paper presents a framework for increasing the performance of GFRBCSs by creating a hierarchical fuzzy rule-based classifier. The proposed system is constructed through repeated invocations to a base GFRBCS procedure, considering at each step an input space fuzzy partition of a certain granularity. The best performing rules are inserted in the hierarchical rule base and the process is repeated again, considering a thicker granularity. The employed boosting scheme guides the algorithm in creating new rules to treat uncovered or misclassified patterns, thus monotonically increasing the performance of the classifier. Extensive experimental analysis in a number of real-world high-dimensional classification tasks proves the effectiveness of the proposed approach in increasing the performance of the base classifier, maintaining its interpretability to a considerable degree.

A FILTER PROPOSAL FOR INCLUDING FEATURE CONSTRUCTION IN A GENETIC LEARNING ALGORITHM

In system identification process often a predetermined set of features is used. However, in many cases it is difficult to know a priori whether the selected features were really the more appropriate ones. This is the reason why the feature construction techniques have been very interesting in many applications. Thus, the current proposal introduces the use of these techniques in order to improve the description of fuzzy rule-based systems. In particular, the idea is to include feature construction in a genetic learning algorithm. The construction of attributes in this study will be restricted to the inclusion of functions defined on the initial attributes of the system. Since the number of functions and the number of attributes can be very large, a filter model, based on the use of information measures, is introduced. In this way, the genetic algorithm only needs to explore the particular new features that may be of greater interest to the final identification of the system. In order to manage the knowledge provided by the new attributes based on the use of functions we propose a new model of rule by extending a basic learning fuzzy rule-based model. Finally, we show the experimental study associated with this work.

Opposition-Based Discrete PSO Using Natural Encoding for Classification Rule Discovery

In this paper we present a new Discrete Particle Swarm Optimization approach to induce rules from discrete data. The proposed algorithm, called Opposition-based Natural Discrete PSO (ONDPSO), initializes its population by taking into account the discrete nature of the data. Particles are encoded using a Natural Encoding scheme. Each member of the population updates its position iteratively on the basis of a newly designed position update rule. Opposition-based learning is implemented in the optimization process. The encoding scheme and position update rule used by the algorithm allows individual terms corresponding to different attributes within the rule's antecedent to be a disjunction of the values of those attributes. The performance of the proposed algorithm is evaluated against seven different datasets using a tenfold testing scheme. The achieved median accuracy is compared against various evolutionary and non-evolutionary classification techniques. The algorithm produces promising results by creating highly accurate and precise rules for each dataset.

FUSING FUZZY ASSOCIATION RULE-BASED CLASSIFIERS USING SUGENO INTEGRAL WITH ORDERED WEIGHTED AVERAGING OPERATORS

The time or space complexity may considerably increase for a single classifier if all features are taken into account. Thus, it is reasonable to train a single classifier by partial features. Then, a set of multiple classifiers can be generated, and an aggregation of outputs from different classifiers is subsequently performed. The aim of this paper is to propose a classification system with a heuristic fusion scheme in which multiple fuzzy association rule-based classifiers with partial features are combined, and show the feasibility and effectiveness of fusing multiple classifiers through the Sugeno integral extended by ordered weighted averaging operators. In comparison with the Sugeno integral by computer simulations on the iris data and the appendicitis data show that the overall classification accuracy rate could be improved by the Sugeno integral with ordered weighted averaging operators. The experimental results further demonstrate that the proposed method performs well in comparison with other fuzzy or non-fuzzy classification methods.

MIXED GENETIC ALGORITHM APPROACH FOR FUZZY CLASSIFIER DESIGN

An important issue in the design of FRBS is the formation of fuzzy if-then rules and the membership functions. This paper presents a Mixed Genetic Algorithm (MGA) approach to obtain the optimal rule set and the membership function of the fuzzy classifier. While applying genetic algorithm for fuzzy classifier design, the membership functions are represented as real numbers and the fuzzy rules are represented as binary string. Modified forms of crossover and mutation operators are proposed to deal with the mixed string. The proposed genetic operators help to improve the convergence of GA and accuracy of the classifier. The performance of the proposed approach is evaluated through development of fuzzy classifier for seven standard data sets. From the simulation study it is found that the proposed algorithm produces a fuzzy classifier with minimum number of rules and high classification accuracy. Statistical analysis of the test results shows the superiority of the proposed algorithm over the existing methods.

An Intelligent Operator for Genetic Fuzzy Rule Based System

This paper proposes a modified form of operator based on Particle Swarm Optimization (PSO) for designing Genetic Fuzzy Rule Based System (GFRBS). The usual procedure of velocity updating in PSO is modified by calculating the velocity using chromosome’s individual best value and global best value based on an updating probability without considering the inertia weight, old velocity and constriction factors. This kind of calculation brings intelligent information sharing mechanism and memory capability to Genetic Algorithm (GA) and can be easily implemented along with other genetic operators. The performance of the proposed operator is evaluated using ten publicly available bench mark data sets. Simulation results show that the proposed operator introduces new material into the population, thereby allows faster and more accurate convergence without struck into a local optima. Statistical analysis of the experimental results shows that the proposed operator produces a classifier model with minimum number of rules and higher classification accuracy.

Hybrid cost-sensitive fuzzy classification for breast cancer diagnosis

Breast cancer is the most commonly diagnosed form of cancer in women accounting for about 30% of all cases. From a computational point of view, breast cancer diagnosis can be viewed as a pattern classification problem. In this paper, we present a cost-sensitive approach to classifying breast cancer data. In particular, we employ a fuzzy rule base that allows incorporation of a misclassification cost term in order to provide the ability to focus on certain classes and hence to boost the identification of malignant cases. Moreover, we show how genetic algorithms can be employed to optimise a compact yet effective rule base, investigating both Michigan and Pittsburgh style approaches of hybrid GA-fuzzy classifiers in the context of breast cancer diagnosis.