Fuzzy Neural Network Architecture Research Articles

Fuzzy-neural networks for medical diagnosis

In this paper, a novel fuzzy-neural network architecture is proposed and the algorithm is developed. Using this new architecture, fuzzy-CSFNN, fuzzy-MLP and fuzzy-RBF configurations were constituted, and their performances have been compared on medical diagnosis problems. Here, conic section function neural network (CSFNN) is also a hybrid neural network structure that unifies the propagation rules of multilayer perceptron (MLP) and radial basis function (RBF) neural networks at a unique network by its distinctive propagation rules. That means CSFNNs accommodate MLPs and RBFs in its own self-network structure. The proposed hybrid fuzzy-neural networks were implemented in a well-known benchmark medical problems with real clinical data for thyroid disorders, breast cancer and diabetes disease diagnosis. Simulation results show that proposed hybrid structures outperform both MATLAB-ANFIS and non-hybrid structures.

FUZZY GRAPHS IN FUZZY NEURAL NETWORKS

In this paper we observe that, the fuzzy neural network architecture is isomorphic to the fuzzy graph model and the output of a fuzzy neural network with OR fuzzy neuron is equal to the strength of strongest path between the input layer (particular input neuron/neurons) and the out put layer(particular output neuron). We explain this result through an example, which describes the marketability of text books of kindergarten classes.

Features extraction for speech emotion

In this paper the speech emotion verification using two most popular methods in speech processing and analysis based on the Mel-Frequency Cepstral Coefficient (MFCC) and the Gaussian Mixture Model (GMM) were proposed and analyzed. In both cases, features for the speech emotion were extracted using the Short Time Fourier Transform (STFT) and Short Time Histogram (STH) for MFCC and GMM respectively. The performance of the speech emotion verification is measured based on three neural network (NN) and fuzzy neural network (FNN) architectures; namely: Multi Layer Perceptron (MLP), Adaptive Neuro Fuzzy Inference System (ANFIS) and Generic Self-organizing Fuzzy Neural Network (GenSoFNN). Results obtained from the experiments using real audio clips from movies and television sitcoms show the potential of using the proposed features extraction methods for real time application due to its reasonable accuracy and fast training time. This may lead us to the practical usage if the emotion verifier can be embedded in real time applications especially for personal digital assistance (PDA) or smart-phones.

A hybrid learning algorithm for a class of interval type-2 fuzzy neural networks

In real life, information about the world is uncertain and imprecise. The cause of this uncertainty is due to: deficiencies on given information, the fuzzy nature of our perception of events and objects, and on the limitations of the models we use to explain the world. The development of new methods for dealing with information with uncertainty is crucial for solving real life problems. In this paper three interval type-2 fuzzy neural network (IT2FNN) architectures are proposed, with hybrid learning algorithm techniques (gradient descent backpropagation and gradient descent with adaptive learning rate backpropagation). At the antecedents layer, a interval type-2 fuzzy neuron (IT2FN) model is used, and in case of the consequents layer an interval type-1 fuzzy neuron model (IT1FN), in order to fuzzify the rule’s antecedents and consequents of an interval type-2 Takagi–Sugeno–Kang fuzzy inference system (IT2-TSK-FIS). IT2-TSK-FIS is integrated in an adaptive neural network, in order to take advantage the best of both models. This provides a high order intuitive mechanism for representing imperfect information by means of use of fuzzy If–Then rules, in addition to handling uncertainty and imprecision. On the other hand, neural networks are highly adaptable, with learning and generalization capabilities. Experimental results are divided in two kinds: in the first one a non-linear identification problem for control systems is simulated, here a comparative analysis of learning architectures IT2FNN and ANFIS is done. For the second kind, a non-linear Mackey–Glass chaotic time series prediction problem with uncertainty sources is studied. Finally, IT2FNN proved to be more efficient mechanism for modeling real-world problems.

A novel neuro-cognitive approach to modeling traffic control and flow based on fuzzy neural techniques

In many developed and developing countries, efficient monitoring and controlling of the city’s traffic have become major challenges. Conventional traffic light control methods, Preset Cycle Timing and Preset Cycle Timing with proximity sensors used today are neither sufficiently efficient nor effective to manage different traffic conditions. One solution is to employ a human operator. Unfortunately this method is expensive and error-prone due to lapse in concentration and other factors. Another alternative is to introduce an intelligent controller using fuzzy neural learning memory techniques, which have the capability to mimic human intelligence in controlling the frequency of traffic light changes at a junction. The performances of four suitable soft-computing architectures are investigated in this study as a possible platform to model and develop an intelligent traffic light control regime. These neural fuzzy learning structures construct memories that possess the intelligence and capabilities of a human operator in monitoring and managing the traffic at road intersections under different traffic scenarios. An open source traffic light simulator, Green Light District, is used to create and simulate different traffic conditions at (i) a simple traffic light intersection and (ii) a complex traffic light intersection. Traffic data generated by the simulator under the control of a human operator is then used as inputs for the training and testing of four fuzzy neural network architectures. The four architectures are Generic Self-organizing Fuzzy Neural Network (GenSoFNN), Pseudo Outer Product based Fuzzy Neural Network (POPFNN), Fuzzy Adaptive Learning Control Network (Falcon) and Multilayer Perceptrons (MLP). The performance of each of the neural network architectures was found to be promising from the simulation results derived for both simple and complex traffic light intersections. Performance was based on the mean classified rate, mean training time, mean number of rules, and standard deviation of the classified rate across the traffic conditions simulated. A technique from each of the architectures with the best results is subsequently selected for more in-depth study on its performance in a complex traffic light intersection. Although all the selected techniques from the four architectures suffered a decline in performance in the complex traffic light intersection; architectures such as GenSoFNN and Falcon continue to produce good results. The POPFNN architecture generated a large number of rules and the MLP architecture produced poor classified rates. This work has demonstrated that it is highly feasible to develop neuro-cognitive traffic control regime that can mimic the behaviors of a human operator.

Numerical solution of a system of fuzzy polynomials by fuzzy neural network

In this paper, a new approach for solving systems of fuzzy polynomials based on fuzzy neural network (FNN) is presented. This method can also lead to improve numerical methods. In this work, an architecture of fuzzy neural networks is also proposed to find a real root of a system of fuzzy polynomials (if exists) by introducing a learning algorithm. Finally, we illustrate our approach by numerical examples.

Numerical solution of fuzzy polynomials by fuzzy neural network

In this paper, an architecture of fuzzy neural networks is proposed to find a real root of fuzzy polynomials (if exists) by introducing a learning algorithm. We proposed a learning algorithm from the cost function for adjusting of crisp weights. Finally, we illustrated our approach by numerical examples.

Genetic optimization-driven multi-layer hybrid fuzzy neural networks

In this study, we introduce a new architecture of hybrid fuzzy neural networks (gHFNNs) and offer a comprehensive design methodology that supports their development. The gHFNN rule-based architecture results from a synergistic usage of Fuzzy Neural Networks (FNNs) with Polynomial Neural Networks (PNNs). The FNN contributes to the formation of the premise part of the overall network of the gHFNN. The consequence part of the gHFNN is designed taking advantage of PNNs. The optimization of the FNN is realized with the aid of a standard back-propagation learning combined with genetic optimization. The development of the PNN dwells on the extended Group Method of Data Handling (GMDH) and Genetic Algorithms (GAs). Through the consecutive process of such structural and parametric optimization, an optimized topology of the PNN becomes generated in a dynamic fashion. The performance of the gHFNN is evaluated through a series of numeric experiments. A comparative analysis shows that the proposed gHFNN is characterized by higher accuracy as well as significant predictive capabilities when contrasted with other neurofuzzy models presented in the literature.

A fuzzy clustering neural network architecture for classification of ECG arrhythmias

Accurate and computationally efficient means of classifying electrocardiography (ECG) arrhythmias has been the subject of considerable research effort in recent years. This study presents a comparative study of the classification accuracy of ECG signals using a well-known neural network architecture named multi-layered perceptron (MLP) with backpropagation training algorithm, and a new fuzzy clustering NN architecture (FCNN) for early diagnosis. The ECG signals are taken from MIT-BIH ECG database, which are used to classify 10 different arrhythmias for training. These are normal sinus rhythm, sinus bradycardia, ventricular tachycardia, sinus arrhythmia, atrial premature contraction, paced beat, right bundle branch block, left bundle branch block, atrial fibrillation and atrial flutter. For testing, the proposed structures were trained by backpropagation algorithm. Both of them tested using experimental ECG records of 92 patients (40 male and 52 female, average age is 39.75 ± 19.06 ). The test results suggest that a new proposed FCNN architecture can generalize better than ordinary MLP architecture and also learn better and faster. The advantage of proposed structure is a result of decreasing the number of segments by grouping similar segments in training data with fuzzy c-means clustering.

Cascade Architectures of Fuzzy Neural Networks

This study is concerned with cascade architectures of fuzzy neural networks. These networks exhibit three interesting and practically appealing features: (i) come with sound and transparent logic characteristics by being developed with the aid of AND and OR fuzzy neurons and subsequently logic processors (LPs), (ii) possess significant learning abilities and in this way fall in the realm of neuro-fuzzy architectures, and (iii) exhibit an evident hierarchical structure owing to the cascade of the LPs. We discuss main functional properties of the model and relate them to its form of cascade-type of systems formed as a stack of LPs. The construction of the systems of this form calls for some structural optimization that is realized in the realm of genetic optimization. The structure of the network that deals with a selection of a subset of input variables and their distribution across the individual LPs is optimized with the use of genetic algorithms (GAs). The chromosomes encode the order of the variables as well as include the parameters (connections) of the neurons. We discuss various schemes of genetic optimization (both a two-level and single-level GA) and gradient-based learning aimed at further refinement of the connections of the neurons. We elaborate on the interpretation aspects of the network and show how this leads to a Boolean or multivalued logic description of the experimental data. A number of numeric data sets are discussed with respect to the performance of the constructed networks and their interpretability.

퍼지뉴럴 네트워크와 자기구성 네트워크에 기초한 적응 퍼지 다항식 뉴럴네트워크 구조의 설계

The study is concerned with an approach to the design of new architectures of fuzzy neural networks and the discussion of comprehensive design methodology supporting their development. We propose an Adaptive Fuzzy Polynomial Neural Networks(APFNN) based on Fuzzy Neural Networks(FNN) and Self-organizing Networks(SON) for model identification of complex and nonlinear systems. The proposed AFPNN is generated from the mutually combined structure of both FNN and SON. The one and the other are considered as the premise and the consequence part of AFPNN, respectively. As the premise structure of AFPNN, FNN uses both the simplified fuzzy inference and error back-propagation teaming rule. The parameters of FNN are refined(optimized) using genetic algorithms(GAs). As the consequence structure of AFPNN, SON is realized by a polynomial type of mapping(linear, quadratic and modified quadratic) between input and output variables. In this study, we introduce two kinds of AFPNN architectures, namely the basic and the modified one. The basic and the modified architectures depend on the number of input variables and the order of polynomial in each layer of consequence structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the AFPNN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed AFPNN can produce the model with higher accuracy and predictive ability than any other method presented previously.

A NOVEL TECHNIQUE FOR CLASSIFICATION OF MYOELECTRIC SIGNALS FOR PROSTHESIS

This paper presents an investigation into classifying myoelectric signals using a new fuzzy clustering neural network architecture for control of multifunction prostheses. Moreover, a comparative study of the classification accuracy of myoelectric signals using multi-layer perceptron with back-propagation algorithm, and the new fuzzy clustering neural network (FCNN) is presented. The myoelectric signals considered are used to classify four upper-limb movements, which are elbow flexion, elbow extension, wrist pronation and wrist supination, grasp, and resting. The results suggest that FCNN can generalise better than the multi-layer perceptron without requiring extra computational effort. The proposed neural network algorithm allows the user to learn better and faster.

Sequential learning artificial fuzzy neural networks (SLAFNN) with single hidden layer

In this paper, a sequential orthogonal approach to the building and training of a single hidden layer fuzzy neural network is presented. Sequential learning artificial neural network model proposed by Zhang and Morris (Neural Networks 11 (1) (1998) 65) is modified to tackle fuzzy inputs and crisp outputs and a sequential learning artificial fuzzy neural network model is developed and used in this paper. This model can tackle the common problem encountered by conventional fuzzy back propagation neural network in the determination of the network structure in the number of hidden layers and the number of hidden neurons in each layer. Non-linear mapping between fuzzy input vectors and crisp output is performed. Left and right (LR) type representation is used to reduce the network complexity. A simple defuzzification process is proposed. The procedure starts with a single hidden neuron and sequentially increases in the number of hidden neurons until the model error is sufficiently small. The classical Gram–Schmidt orthogonalization method is used at each step to form a set of orthogonal bases for the space spanned by output vectors of the hidden neurons. In this approach it is possible to determine the necessary number of hidden neurons required. The fuzzy neural network architecture has been trained and tested to civil engineering problems such as determination of allowable stress limits for a beam subjected to lateral loads, earthquake damage and the evaluation of wind pressure predictions.

Cross-validation in Fuzzy ARTMAP for large databases

In this paper we are examining the issue of overtraining in Fuzzy ARTMAP. Over-training in Fuzzy ARTMAP manifests itself in two different ways: (a) it degrades the generalization performance of Fuzzy ARTMAP as training progresses; and (b) it creates unnecessarily large Fuzzy ARTMAP neural network architectures. In this work, we are demonstrating that overtraining happens in Fuzzy ARTMAP and we propose an old remedy for its cure: cross-validation. In our experiments, we compare the performance of Fuzzy ARTMAP that is trained (i) until the completion of training, (ii) for one epoch, and (iii) until its performance on a validation set is maximized. The experiments were performed on artificial and real databases. The conclusion derived from those experiments is that cross-validation is a useful procedure in Fuzzy ARTMAP, because it produces smaller Fuzzy ARTMAP architectures with improved generalization performance. The trade-off is that cross-validation introduces additional computational complexity in the training phase of Fuzzy ARTMAP.

An Efficient Method for Selecting the Optimal Structure of a Fuzzy Neural Network Architecture

The fusion of artificial neural networks with soft computing enables to construct learning machines that are superior compared to classical artificial neural networks, because knowledge can be extracted and explained in the form of simple rules. An efficient method for selecting the optimal structure of a fuzzy neural network architecture is developed. The Vapnik Chervonenkis (VC) dimension is introduced as a measure of the capacity of the learning machine. A prediction of the expected error on the yet unseen examples is estimated with the help of the VC dimension. The structural risk minimization principle is introduced for constructing the optimal architecture with the lowest expected error for the small data sets. A comparison between fuzzy neural network and the neural network ARX model is presented.

A polynomial fuzzy neural network for modeling and control

This paper introduces a novel neurofuzzy system based on polynomial fuzzy neural network (PFNN) architecture. A PFNN consists of a set of if-then rules with appropriate membership functions (MFs) whose parameters are optimized via a hybrid genetic algorithm. A polynomial neural network is employed in the defuzzification scheme to improve output performance and to select appropriate rules. A performance criterion for model selection is defined to overcome the overfitting problem in the modeling procedure. For a performance assessment of the PFNN inference system, two well-known problems are employed for a comparison with other methods. The results of these comparisons show that the PFNN inference system out-performs the other methods and exhibits robustness characteristics.

Dynamic fuzzy neural networks-a novel approach to function approximation

In this paper, an architecture of dynamic fuzzy neural networks (D-FNN) implementing Takagi-Sugeno-Kang (TSK) fuzzy systems based on extended radial basis function (RBF) neural networks is proposed. A novel learning algorithm based on D-FNN is also presented. The salient characteristics of the algorithm are: 1) hierarchical on-line self-organizing learning is used; 2) neurons can be recruited or deleted dynamically according to their significance to the system's performance; and 3) fast learning speed can be achieved. Simulation studies and comprehensive comparisons with some other learning algorithms demonstrate that a more compact structure with higher performance can be achieved by the proposed approach.

An architecture of fuzzy neural networks for linguistic processing

Fuzzy sets have been used successfully in order to deal with imprecise data, linguistic terms or not well-defined concepts. Recently, considerable effort has been made in the direction of combining the neural network approach with fuzzy sets. In this paper a fuzzy feed-forward neural network, able to process trapezoidal fuzzy sets, has been investigated. Normalized trapezoidal fuzzy sets have been considered. The fuzzy generalized delta rule with different back-propagation algorithms is discussed. The more interesting and characteristic property of the proposed architecture is the ability of each node to process fuzzy sets or linguistic terms, preserving the simplicity of the back-propagation algorithm. Consequently, the resulting architecture is able to cope with problems in which the input parameters and the desired targets are described by linguistic terms. This methodology has the further interesting characteristic of being able to operate at the linguistic level rather than at the numerical level, that is it can work at a higher data abstraction level. An example in computerized electrocardiography will be illustrated in order to test the proposed approach.

Fuzzy lattice neural network (FLNN): a hybrid model for learning

This paper proposes two hierarchical schemes for learning, one for clustering and the other for classification problems. Both schemes can be implemented on a fuzzy lattice neural network (FLNN) architecture, to be introduced herein. The corresponding two learning models draw on adaptive resonance theory (ART) and min-max neurocomputing principles but their application domain is a mathematical lattice. Therefore they can handle more general types of data in addition to N-dimensional vectors. The FLNN neural model stems from a cross-fertilization of lattice theory and fuzzy set theory. Hence a novel theoretical foundation is introduced in this paper, that is the framework of fuzzy lattices or FL-framework, based on the concepts fuzzy lattice and inclusion measure. Sufficient conditions for the existence of an inclusion measure in a mathematical lattice are shown. The performance of the two FLNN schemes, that is for clustering and for classification, compares quite well with other methods and it is demonstrated by examples on various data sets including several benchmark data sets.

FuNN/2—A fuzzy neural network architecture for adaptive learning and knowledge acquisition

Fuzzy neural networks have several features that make them well suited to a wide range of knowledge engineering applications. These strengths include fast and accurate learning, good generalization capabilities, excellent explanation facilities in the form of semantically meaningful fuzzy rules, and the ability to accommodate both data and existing expert knowledge about the problem under consideration. This paper investigates adaptive learning, rule extraction and insertion, and neural/fuzzy reasoning for a particular model of a fuzzy neural network called FuNN. As well as providing for representing a fuzzy system with an adaptable neural architecture, FuNN also incorporates a genetic algorithm in one of its adaptation modes. A version of FuNN—FuNN/2, which employs triangular membership functions and correspondingly modified learning and adaptation algorithms, is also presented in the paper.