Fuzzy Neural Network Architecture Research Articles

Enhancing pitch angle control in variable speed doubly fed induction generator based wind energy conversion system using advanced adaptive neuro-fuzzy approach with particle swarm optimization

Pitch angle control is a common method used to smooth out output power fluctuations in the wind turbines. This paper focuses on Particle Swarm Optimization (PSO) based Adaptive Neuro-Fuzzy Inference System (ANFIS) pitch angle control scheme for a variable speed Doubly Fed Induction Generator (DFIG) based wind energy conversion system designed for operation in high wind speed regions. The proposed enhanced adaptive controller comprises both Sugeno type fuzzy inference system (FIS) and neural network architecture. In the Sugeno type FIS, the membership functions are optimized using a revisited PSO method. The primary objective is to control the pitch angle to ensure that generator power and speed operate within desired references, reducing fluctuations and minimizing mechanical blade stress. A MATLAB/SIMULINK model of wind energy conversion system setup is prepared and simulations are conducted using different control methods. The effectiveness of the proposed approach is confirmed based on the simulation results.

A self-organizing deep network architecture designed based on LSTM network via elitism-driven roulette-wheel selection for time-series forecasting

In this study, we propose a new self-organizing deep network architecture of fuzzy polynomial neural networks (FPNN) based on Fuzzy rule-based Polynomial Neurons (FPNs) and a long short-term memory (LSTM) network to solve the task of time-series forecasting. In the existing regression model based on polynomial neural networks (PNN), it is difficult to achieve high quality performance when predicting time series data, because this model lacks the ability to extract temporal and spatial information. Therefore, we propose a new architecture consisting of one LSTM (temporal) layer and several fuzzy polynomial (spatial) layers to overcome the above-mentioned shortcomings of PNN and enhance its predictive ability to approximate the data. The temporal layer consists of LSTM neurons that have inherently strong modeling capabilities to learn sequential information. The spatial layers are composed of Rule-based Polynomial Neurons (FPNs) that can effectively reflect the complex nonlinear structure found in the input space and granulate it using of the Fuzzy C-Means (FCM) clustering method. An elitism-driven roulette-wheel selection (E_RWS) is used to select appropriate neurons. E_RWS not only ensures that the neuron with the strongest fitting ability is selected but also increases the diversity of candidate neurons. According to the experimental results, the proposed model has a high prediction performance and outperforms many state-of-the-art prediction methods when applied to the real-world time-series.

Application of Fuzzy Neural Networks in Combustion Process Diagnostics

Coal remains one of the key raw materials used in the energy industry to generate electricity and heat. As a result, diagnostics of the combustion process is still an important topic of scientific research. Correct implementation of the process allows the emission of pollutants into the atmosphere to be kept at a compliant level. Therefore, it is important to conduct the process in a manner that will not exceed these standards. A preliminary analysis of the measurement signals was carried out, and signal predictions of flame intensity changes were determined using the autoregressive moving average (ARMA) model. Different fuzzy neural network architectures have been investigated. Binary and multi-class classifications of flame states were conducted. The best results were obtained from the ANFIS_grid partition model, producing an accuracy of 95.46% for binary classification and 79.08% for multi-class classification. The accuracy of the recognition of flame states and the high convergence of the determined predictions with measurement signals validate the application of the proposed approach in diagnosing or controlling the combustion process of pulverized coal and its mixtures with biomass. Expert decisions determine the range of acceptable states.

Sensor-based human activity recognition using fuzzified deep CNN architecture with λmax method

PurposeThis work aims to develop a novel fuzzy associator rule-based fuzzified deep convolutional neural network (FDCNN) architecture for the classification of smartphone sensor-based human activity recognition. This work mainly focuses on fusing the λmax method for weight initialization, as a data normalization technique, to achieve high accuracy of classification.Design/methodology/approachThe major contributions of this work are modeled as FDCNN architecture, which is initially fused with a fuzzy logic based data aggregator. This work significantly focuses on normalizing the University of California, Irvine data set’s statistical parameters before feeding that to convolutional neural network layers. This FDCNN model with λmax method is instrumental in ensuring the faster convergence with improved performance accuracy in sensor based human activity recognition. Impact analysis is carried out to validate the appropriateness of the results with hyper-parameter tuning on the proposed FDCNN model with λmax method.FindingsThe effectiveness of the proposed FDCNN model with λmax method was outperformed than state-of-the-art models and attained with overall accuracy of 97.89% with overall F1 score as 0.9795.Practical implicationsThe proposed fuzzy associate rule layer (FAL) layer is responsible for feature association based on fuzzy rules and regulates the uncertainty in the sensor data because of signal inferences and noises. Also, the normalized data is subjectively grouped based on the FAL kernel structure weights assigned with the λmax method.Social implicationsContributed a novel FDCNN architecture that can support those who are keen in advancing human activity recognition (HAR) recognition.Originality/valueA novel FDCNN architecture is implemented with appropriate FAL kernel structures.

Методология построения нейронной нечеткой сети в области информационной безопасности

This paper proposes the use of hybrid models based on neural networks and fuzzy systems to build intelligent intrusion detection systems based on the theory of fuzzy rules. The presented system will be able to generate rules based on the results using fuzzy logic neurons. To avoid oversaturation and assist in determining the necessary network topology, training models based on extreme learning machine and regularization theory will be used to find the most significant neurons. In this paper, a type of SQL injection cyberattack is considered, which actively exploits errors in systems that communicate with the database via SQL commands, and for this reason is considered a kind of straightforward attack. The fuzzy neural network architecture used in detecting SQL injection attacks is a multi-component structure. The first two layers of the model are considered as a fuzzy inference system capable of extracting knowledge from data and transforming it into fuzzy rules. These rules help build automated systems for detecting SQL injection attacks. The third layer consists of a simple neuron that has an activation function called a leaky ReLU. The first layer consists of fuzzy neurons, the activation functions of which are Gaussian membership functions of fuzzy sets, defined in accordance with the partitioning of the input variables. The technique uses the concept of a simple linear regression model to solve the problem of choosing the best subsets of neurons. To perform model selection, the paper used the widely used least angular regression (LARS) algorithm.

Fuzzy U-Net Neural Network Architecture Optimization for Image Segmentation

In this article, the optimization of the modified U-Net neural network model extended with fuzzy layers has been studied with the usage of Grid search and Keras tuner. The article is a continuation of previous work where the model is suggested and explored. From one point of view, the research is focused on the optimization of Fuzzy Layers embedded in the U-Net model in order to find the better neural network architecture for nuclei segmentation in the research work in BioMed Varna R&D ecosystem for the segmentation of cellular nuclei. At the same time from a global perspective, this experiment is a part of the bigger one for the searching of new neural network architecture design techniques.

A Convolutional Fuzzy Neural Network Architecture for Object Classification with Small Training Database

In this paper, we propose a novel architecture that combines the convolutional neural network (CNN) with a fuzzy neural network (FNN). We utilize the fuzzy neural network with semi-connected layers to sum up feature information. During the training process, to map membership values, the CNN generates feature maps as outputs and feeds into fuzzifier layers, alternatively called fuzzy maps. The proposed method increases classification accuracy, because fuzzy neural networks can generate not only crisp values but also fuzzy values; this means that there is potentially more information contained in the fuzzy set. Our model is evaluated by cross-validation tests. While big data is necessary for training in general, we train our model with small data and test with big data to demonstrate its ability of object classification in cases where sufficient data are not available.

An Overview and Recent Advances in Fuzzy ARTMAP Classifier Usage for Mapping Purposes Using Remotely Sensed Data

This paper presents an overview and recent advances on the usage of Fuzzy ARTMAP artificial neural network architecture (and its variants) for mapping purposes using remotely sensed data. It aims to offer a perspective into the past and ongoing developments of this specific research field. Moreover, this paper suggests initial pathways for those who intend to perform a scientific investigation using this artificial neural network architecture. Some applications of this architecture in other research fields are highlighted for general knowledge purposes, as well as suggestions of code repositories to implement it. Possible gaps in the literature related to Fuzzy ARTMAP classifier usage for mapping are suggested, leading to paths for future developments in this field of research.

Optimising Fuzzy Neural Network Architecture for Dissolved Oxygen Prediction and Risk Analysis

A fuzzy neural network method is proposed to predict minimum daily dissolved oxygen concentration in the Bow River, in Calgary, Canada. Owing to the highly complex and uncertain physical system, a data-driven and fuzzy number based approach is preferred over traditional approaches. The inputs to the model are abiotic factors, namely water temperature and flow rate. An approach to select the optimum architecture of the neural network is proposed. The total uncertainty of the system is captured in the fuzzy numbers weights and biases of the neural network. Model predictions are compared to the traditional, non-fuzzy approach, which shows that the proposed method captures more low DO events. Model output is then used to quantify the risk of low DO for different conditions.

Structural parameters identification of uncertain multi-storey shear buildings using fuzzy neural network modelling

Present paper proposes a fuzzy neural network (FNN)-based modelling for the identification of structural parameters of uncertain multi-storey shear buildings. Here, the method is developed to identify uncertain structural mass, stiffness and damping matrices from the dynamic responses of the structure without any optimization processes that are generally used to solve inverse vibration problems. Uncertainty has been taken in term of fuzzy numbers. The governing equations of motion are first solved by the classical method to get responses of the consecutive stories. Further the governing equations of motion are modified based on relative responses of consecutive stories in such a way that the new set of equations can be implemented in a cluster of FNNs. As such the model starts solving the nth floor by FNN modelling to estimate the structural parameters. Subsequently, series of FNN models are used to estimate the parameters for (n − 1)th storey to the first storey. One may note that single layer FNNs have been used for training for each cluster of the FNN such that the converged weights give the uncertain structural parameters. The initial weights in the FNN architecture are taken as the design parameters in uncertain (fuzzy) form. In order to validate the present model, various example problems of different multi-storey shear structures have been considered. Related results are incorporated in term of tables and graphs. Comparisons between theoretical and identified results are carried out and are found to be in good agreement.

Brain Dynamics in Predicting Driving Fatigue Using a Recurrent Self-Evolving Fuzzy Neural Network.

This paper proposes a generalized prediction system called a recurrent self-evolving fuzzy neural network (RSEFNN) that employs an on-line gradient descent learning rule to address the electroencephalography (EEG) regression problem in brain dynamics for driving fatigue. The cognitive states of drivers significantly affect driving safety; in particular, fatigue driving, or drowsy driving, endangers both the individual and the public. For this reason, the development of brain-computer interfaces (BCIs) that can identify drowsy driving states is a crucial and urgent topic of study. Many EEG-based BCIs have been developed as artificial auxiliary systems for use in various practical applications because of the benefits of measuring EEG signals. In the literature, the efficacy of EEG-based BCIs in recognition tasks has been limited by low resolutions. The system proposed in this paper represents the first attempt to use the recurrent fuzzy neural network (RFNN) architecture to increase adaptability in realistic EEG applications to overcome this bottleneck. This paper further analyzes brain dynamics in a simulated car driving task in a virtual-reality environment. The proposed RSEFNN model is evaluated using the generalized cross-subject approach, and the results indicate that the RSEFNN is superior to competing models regardless of the use of recurrent or nonrecurrent structures.

Intelligent forecasting system based on integration of electromagnetism-like mechanism and fuzzy neural network

Fuzzy neural network (FNN) architectures, in which fuzzy logic and artificial neural networks are integrated, have been proposed by many researchers. In addition to developing the architecture for the FNN models, evolution of the learning algorithms for the connection weights is also a very important. Researchers have proposed gradient descent methods such as the back propagation algorithm and evolution methods such as genetic algorithms (GA) for training FNN connection weights. In this paper, we integrate a new meta-heuristic algorithm, the electromagnetism-like mechanism (EM), into the FNN training process. The EM algorithm utilizes an attraction–repulsion mechanism to move the sample points towards the optimum. However, due to the characteristics of the repulsion mechanism, the EM algorithm does not settle easily into the local optimum. We use EM to develop an EM-based FNN (the EM-initialized FNN) model with fuzzy connection weights. Further, the EM-initialized FNN model is used to train fuzzy if–then rules for learning expert knowledge. The results of comparisons done of the performance of our EM-initialized FNN model to conventional FNN models and GA-initialized FNN models proposed by other researchers indicate that the performance of our EM-initialized FNN model is better than that of the other FNN models. In addition, our use of a fuzzy ranking method to eliminate redundant fuzzy connection weights in our FNN architecture results in improved performance over other FNN models.

MODIFIED FUZZY NEURAL NETWORK FOR THE CLASSIFICATION OF MURDER CASES IN CRIMINAL LAW USING GAUSSIAN MEMBERSHIP FUNCTION

This paper presents the problem of decision making by a judge in the case of murder cases in criminal law using single hidden layered fuzzy neural network algorithm. Since the membership functions (MFs) of fuzzy sets can affect the performance of the classification models, determination of MFs is crucial. In this paper, the MF selected is Triangular and Gaussian is proposed for evaluation to improve the classification results. To evaluate the effectiveness of the proposed Fuzzy Neural Network model for the classification of murder cases, sufficient number of real-world data sets of court decisions are trained and tested. The simulation model of different membership functions for the modified fuzzy neural network architecture is implemented in C++. Experimental results show that the proposed neuro-fuzzy classifier with Gaussian MF outperforms Triangular MF with higher accuracy. The proposed classification model is proved to be a suitable tool for classification of murder cases in criminal law.

A Design of Dynamically Simultaneous Search GA-based Fuzzy Neural Networks: Comparative Analysis and Interpretation

In this paper, we introduce advanced architectures of genetically-oriented Fuzzy Neural Networks (FNNs) based on fuzzy set and fuzzy relation and discuss a comprehensive design methodology. The proposed FNNs are based on ‘if-then’ rule-based networks with the extended structure of the premise and the consequence parts of the fuzzy rules. We consider two types of the FNNs topologies, called here FSNN and FRNN, depending upon the usage of inputs in the premise of fuzzy rules. Three different type of polynomials function (namely, constant, linear, and quadratic) are used to construct the consequence of the rules. In order to improve the accuracy of FNNs, the structure and the parameters are optimized by making use of genetic algorithms (GAs). We enhance the search capabilities of the GAs by introducing the dynamic variants of genetic optimization. It fully exploits the processing capabilities of the FNNs by supporting their structural and parametric optimization. To evaluate the performance of the proposed FNNs, we exploit a suite of several representative numerical examples and its experimental results are compared with those reported in the previous studies.

SELFLEARNING FUZZY SPIKING NEURAL NETWORK BASED ON DISCRETE SECOND-ORDER CRITICALLY DUMPED RESPONSE UNITS FOR FUZZY CLUSTERING TASKS

Hybrid neural networks based on the idea of combining spiking neural networks and the principles of fuzzy logic are considered. The architecture of self-learning fuzzy spiking neural network based on discrete second-order critically damped response units is proposed. It is proposed to define a spiking neural network in terms of apparatus of classical automatic control theory based on the Laplace transform and z-transform. It is shown that a spiking neural network is a pulse-position threshold detection system based on second-order damped response units. Such kind of description allows using it as an analog-digital system in technical problems solving. The output layer takes firing times of spikes arriving from the second layer, and either performs fuzzy partitioning of the input patterns using probabilistic approach.

On-Road Sensor Configuration Design for Traffic Flow Prediction Using Fuzzy Neural Networks and Taguchi Method

On-road sensors provide proactive traffic control centers with current traffic flow conditions in order to forecast the future conditions. However, the number of on-road sensors is usually huge, and not all traffic flow conditions captured by these sensors are useful for predicting future traffic flow conditions. The inclusion of all captured traffic flow conditions is an ineffective means of predicting future traffic flow. Therefore, the selection of appropriate on-road sensors, which are significantly correlated to future traffic flow, is essential, although the trial and error method is generally used for the selection. In this paper, the Taguchi method, which is a robust and systematic optimization approach for designing reliable and high-quality models, is proposed for determinations of appropriate on-road sensors, in order to capture useful traffic flow conditions for forecasting. The effectiveness of the Taguchi method is demonstrated by developing a traffic flow predictor based on the architecture of fuzzy neural networks which can perform well on traffic flow forecasting. The case study was conducted based on traffic flow data captured by on-road sensors located on a Western Australia freeway. The advantages of using the Taguchi method can be indicated: 1) Traffic flow predictors with high accuracy can be designed, and 2) development time of traffic flow predictors is reasonable.

System of fully fuzzy nonlinear equations with fuzzy neural network

In this paper, a new approach for solving system of fully fuzzy nonlinear equations based on fuzzy neural network 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 fuzzy root of a system of fuzzy nonlinear equations (if exists) by introducing a learning algorithm. We propose a learning algorithm from the cost function for adjusting of fuzzy weights. Finally, we illustrate our approach by numerical examples.

A Production Planning Model using Fuzzy Neural Network: A Case Study of an Automobile Industry

production forecast based on order received is adversely affected by deterrent factors in supply chain management (SCM). Although several mathematical models have been attempted by researchers, the accuracy of such forecast still need to be improved. In the present paper the various deterrent factors influencing the supply chain have been considered adequately to forecast the production plan on the order received. The model is based on the machine learning using fuzzy neural network architecture and validated with real data on automobile production. The result is compared with that obtained by conventional multiple regression model and the former is found to be quite satisfactory, the error being as low as 2.9847 e-006

Speech emotion recognition using FCBF feature selection method and GA-optimized fuzzy ARTMAP neural network

Emotion recognition from speech has noticeable applications in the speech-processing systems. In this paper, the effect of using a rich set of features including formant frequency related, pitch frequency related, energy, and the two first mel-frequency cepstral coefficients (MFCCs) on improving the performance of speech emotion recognition systems is investigated. To do this, the different sets of features are employed, and by using the fast correlation-based filter (FCBF) feature selection method, some efficient feature subsets are determined. Finally, to recognize the emotion from speech, fuzzy ARTMAP neural network (FAMNN) architecture is used. Also, the genetic algorithm (GA) is employed to determine optimum values of the choice parameter (α), the vigilance parameters (ρa, ρb, and ρab), and the learning rate (β) of FAMNN. Experimental results show the improvement in emotion recognition rate of angry, happiness, and neutral states by using a subset of 25 selected features and the GA-optimized FAMNN-based emotion recognizer.

ANALOG-DIGITAL SELF-LEARNING FUZZY SPIKING NEURAL NETWORK AND ITS LEARNING ALGORITHM BASED ON ‘WINNER-TAKES-MORE’ RULE

Analog-digital architecture of self-learning fuzzy spiking neural network is proposed in this paper.Spiking neuron synapse and some are treated in terms of classical automatic control theory.Conventional unsupervised learning algorithm of spiking neural network is improved by applying‘Winner-Takes-More’ rule.