Recurrent Fuzzy Network Research Articles

A Proposal to Analyze Muscle Dynamics Under Fatiguing Contractions Using Surface Electromyography Signals and Fuzzy Recurrence Network Features

The analysis of surface electromyography (sEMG) signals is significant in the detection of muscle fatigue. These signals exhibit a great degree of complexity, nonlinearity, and chaos. Also, presence of high degree of fluctuations in the signal makes its analysis a difficult task. This study aims to analyze the nonlinear dynamics of muscle fatigue conditions using Fuzzy recurrence networks (FRN). Dynamic sEMG signals are measured from biceps brachii muscle of 45 normal subjects referenced to 50% of maximal voluntary contractions (MVC) for this. Recorded signals are then pre-processed and divided into ten equal parts. FRNs are transformed from the signals. The network features, namely average weighted degree (AWD) and Closeness centrality (CC) are extracted to analyze the muscle dynamics during fatiguing conditions. The decrease in these features during fatigue indicates a reduction in signal complexity and an increase in complex network stiffness. Both AWD and CC features are statistically significant with [Formula: see text]. Further, these features are classified using Naïve Bayes (NB), k nearest neighbor (kNN) and random forest (RF) algorithms. Maximum accuracy of 96.90% is achieved using kNN classifier for combined FRN features. Thus, the proposed features provide high-quality inputs to the neural networks that may be helpful in analyzing the complexity and stiffness of neuromuscular system under various myoneural conditions.

Emotion Recognition Based on Type-2 Recurrent Wavelet Fuzzy Brain Emotion Learning Network Model

Emotion recognition plays a crucial role in human-robot emotional interaction applications, and the brain emotional learning model is one of several emotion recognition methods, but the learning rules of original brain emotional learning model play poor adaptation and do not work very well. In fact, existing facial emotion recognition methods do not have high accuracy and are not sufficiently practical in real-time applications. In order to solve this problem, this paper introduces an optimal model, which merges interval type-2 recurrent wavelet fuzzy system and brain emotional learning network for emotion recognition. The proposed model takes advantage of type-2 recurrent wavelet fuzzy theory and brain emotional neural network. There are no rules initially, and then the structure and parameters of model are tuning online simultaneously by the gradient approach and Lyapunov function. The system input data streams are directly imported into the neural network through a type-2 recurrent wavelet fuzzy inference system; then, the results are subsequently piped into sensory and emotional channels which jointly produce the final outputs of the network. The proposed model could reduce the uncertainty in terms of vagueness by using type-2 recurrent wavelet fuzzy theory and removing noise samples. Finally, the superior performance of the proposed method is demonstrated by its comparison with some emotion recognition methods on five emotion databases.

A TSK-Type Convolutional Recurrent Fuzzy Network for Predicting Driving Fatigue

Driver fatigue monitoring is very important for driving safety, and many intricate factors while driving make fatigue monitoring harder. To effectively predict driving fatigue, this article proposes a new deep learning framework called TSK-type convolution recurrent fuzzy network (TCRFN) based on the spatial and temporal characteristics of electroencephalogram (EEG) signals. In TCRFN, the convolution block is first introduced to extract spatial dependencies from EEG signals. Furthermore, since EEG noise has a strong spatial dependence, this convolutional neural networks is used to reduce the impact of noise. Additionally, a new local feedback method in fuzzy neural network is proposed to process the EEG signals, which can better capture the temporal dependencies from EEG signals. Finally, a logarithmic spatial firing layer function is used in the proposed TCRFN. The activation performance of this function is smoother, which allows more feature numbers and provides better prediction. The experimental results show that the proposed TCRFN model has better antinoise performance and prediction accuracy compared with other widely used and state-of-the-art models.

Adaptive Elman Model of Gene Regulation Network Based on Time Series Data

Background:Time series expression data of genes contain relations among different genes, which are difficult to model precisely. Slime-forming bacteria is one of the three major harmful bacteria types in industrial circulating cooling water systems.Objective:This study aimed at constructing gene regulation network(GRN) for slime-forming bacteria to understand the microbial fouling mechanism.Methods:For this purpose, an Adaptive Elman Neural Network (AENN) to reveal the relationships among genes using gene expression time series is proposed. The parameters of Elman neural network were optimized adaptively by a Genetic Algorithm (GA). And a Pearson correlation analysis is applied to discover the relationships among genes. In addition, the gene expression data of slime-forming bacteria by transcriptome gene sequencing was presented.Results:To evaluate our proposed method, we compared several alternative data-driven approaches, including a Neural Fuzzy Recurrent Network (NFRN), a basic Elman Neural Network (ENN), and an ensemble network. The experimental results of simulated and real datasets demonstrate that the proposed approach has a promising performance for modeling Gene Regulation Networks (GRNs). We also applied the proposed method for the GRN construction of slime-forming bacteria and at last a GRN for 6 genes was constructed.Conclusion:The proposed GRN construction method can effectively extract the regulations among genes. This is also the first report to construct the GRN for slime-forming bacteria.

Improve the Accuracy of Recurrent Fuzzy System Design Using an Efficient Continuous Ant Colony Optimization

This paper proposes a new population-based evolutionary optimization algorithm, elite-mixed continuous ant colony optimization with central initialization (EMCACO-C), for improving the accuracy of Takagi–Sugeno–Kang-type recurrent fuzzy network (TRFN) designs. The EMCACO-C is a stochastic search algorithm. The EMCACO-C initializes the ant solutions on concentrative region around the center of the search range followed by a new designed elite-mixed continuous ant colony optimization to generate new solutions. The EMCACO-C mixes the few best elites to generate the directional solutions for guiding and exploring possible promising regions. Then the EMCACO-C employs the Gaussian random sampling to exploit further the directional solutions for finding better solutions. The methodology similarities and differences between the EMCACO-C and genetic algorithm are analyzed. The performances of the EMCACO-C for TRFN designs are verified in the simulations of five application examples including dynamic system control, dynamic system identification, and chaotic series prediction. The EMCACO-C performance is also compared with other swarm-based evolutionary algorithms in the simulations.

Assimilation-accommodation mixed continuous ant colony optimization for fuzzy system design

Purpose The purpose of this paper is to propose a new population-based metaheuristic optimization algorithm, assimilation-accommodation mixed continuous ant colony optimization (ACACO), to improve the accuracy of Takagi-Sugeno-Kang-type fuzzy systems design. Design/methodology/approach The original N solution vectors in ACACO are sorted and categorized into three groups according to their ranks. The Research Learning scheme provides the local search capability for the best-ranked group. The Basic Learning scheme uses the ant colony optimization (ACO) technique for the worst-ranked group to approach the best solution. The operations of assimilation, accommodation, and mutation in Mutual Learning scheme are used for the middle-ranked group to exchange and accommodate the partial information between groups and, globally, search information. Only the N top-best-performance solutions are reserved after each iteration of learning. Findings The proposed algorithm outperforms some reported ACO algorithms for the fuzzy system design with the same number of rules. The performance comparison with various previously published neural fuzzy systems also shows its superiority even with a smaller number of fuzzy rules to those neural fuzzy systems. Research limitations/implications Future work will consider the application of the proposed ACACO to the recurrent fuzzy network. Originality/value The originality of this work is to mix the work of the well-known psychologist Jean Piaget and the continuous ACO to propose a new population-based optimization algorithm whose superiority is demonstrated.

CORPORATE SOCIAL RESPONSIBILITY AND FINANCIAL PERFORMANCE: Evidence from a Panel of Korea Listed Companies

A novel recurrent neural fuzzy network is proposed in this paper. The network model is composed by two structures: a fuzzy system and a neural network. The fuzzy system contains fuzzy neurons modeled with the aid of logic and and or operations processed via t-norms and s-norms. The neural network is composed by nonlinear elements placed in series with the previous logical elements. The network model implicitly encodes a set of if-then rules and its recurrent multilayered structure performs fuzzy inference. The topology induces a clear relationship between the network structure and an associated fuzzy rule-based system. In particular we explore this structure with an heuristic learning algorithm based on associative reinforcement learning and gradient search. These learning algorithms are associated to the fuzzy system and neural network, respectively. That is, output layer weights are adjusted via an error gradient method whereas a reward and punishment scheme updates the hidden layer weights. The recurrent fuzzy neural network is particularly suitable to model nonlinear dynamic systems and to learn sequences. Computational experiments with system identification problems show that the fuzzy neural models learned are simpler and that learning is faster than its counterparts.

A TS-Type Maximizing-Discriminability-Based Recurrent Fuzzy Network for Classification Problems

This work proposes a Takagi-Sugeno (TS)-type maximizing-discriminability-based recurrent fuzzy network (MDRFN) that can classify highly confusable patterns. The discriminative capability plays a significant role in determining classification performance. To increase the discriminative capability, the proposed MDRFN considers minimum classification error (MCE) and minimum training error (MTE). In MCE, the weights are updated by maximizing the discrimination among different classes. In MTE, the parameter learning adopts the gradient-descent method to reduce the cost function. Therefore, the novelty of MDRFN is that it not only minimizes the cost function but maximizes the discriminative capability as well. The effectiveness of the proposed MDRFN is demonstrated by three temporal classification problems. In the experiments, other RFNs, including the singleton-type recurrent neural fuzzy network (SRNFN), TS-type RFN (TRFN), and simple RFN (SRFN), are compared. Analysis results indicate that the proposed MDRFN exhibits excellent classification performance.

Genetic Algorithm for Fuzzy Neural Networks using Locally Crossover

Fuzzy feed-forward (FFNR) and fuzzy recurrent networks (FRNN) proved to be solutions for "real world problems". In the most cases, the learning algorithms are based on gradient techniques adapted for fuzzy logic with heuristic rules in the case of fuzzy numbers. In this paper we propose a learning mechanism based on genetic algorithms (GA) with locally crossover that can be applied to various topologies of fuzzy neural networks with fuzzy numbers. The mechanism is applied to FFNR and FRNN with L-R fuzzy numbers as inputs, outputs and weights and fuzzy arithmetic as forward signal propagation. The α-cuts and fuzzy biases are also taken into account. The effectiveness of the proposed method is proven in two applications: the mapping a vector of triangular fuzzy numbers into another vector of triangular fuzzy numbers for FFNR and the dynamic capture of fuzzy sinusoidal oscillations for FRNN.

Recurrent fuzzy system design using elite-guided continuous ant colony optimization

This paper proposes recurrent fuzzy system design using elite-guided continuous ant colony optimization (ECACO). The designed recurrent fuzzy system is the Takagi–Sugeno–Kang (TSK)-type recurrent fuzzy network (TRFN), in which each fuzzy rule contains feedback loops to handle dynamic system processing problems. The ECACO optimizes all of the free parameters in each recurrent fuzzy rule in a TRFN. Unlike the general ant colony optimization that finds solutions in discrete space, the ECACO finds solutions in a continuous space. The ECACO is a population-based optimization algorithm. New solutions are generated by selection, Gaussian random sampling, and elite-guided movement. To verify the performance of ECACO, three examples of dynamic plant control are simulated using ECACO-optimized TRFNs. The ECACO performance is also compared with other continuous ant colony optimization, particle swarm optimization, and genetic algorithms in these simulations.

A pipelined recurrent fuzzy model for real-time analysis of lung sounds

This paper presents a recurrent fuzzy-neural filter that performs the task of separation of lung sounds, obtained from patients with pulmonary pathology. The filter is a pipelined Takagi–Sugeno–Kang recurrent fuzzy network, consisting of a number of modules interconnected in a cascaded form. The participating modules are implemented through recurrent fuzzy neural networks with internal dynamics. The structure of the modules is evolved sequentially from input–output data. Extensive experimental results, regarding the lung sound category of crackles, are given, and a performance comparison with a series of other fuzzy and neural filters is conducted, underlining the separation capabilities of the proposed filter.

Birdsong recognition using prediction-based recurrent neural fuzzy networks

Automatic birdsong recognition using prediction-based singleton-type recurrent neural fuzzy networks (SRNFNs) is proposed in this paper. The recognition task consists of two stages. The first stage segments a significant portion from a birdsong sequence and the second stage performs recognition. For birdsong segmentation, an easy but effective segmentation approach based on time domain energy is proposed. For recognition, the linear predictive coding (LPC) coefficients of each frame in a segmented birdsong are extracted and used as features. These features are fed as inputs to SRNFN recognizers. The SRNFN is constructed by recurrent fuzzy if–then rules with fuzzy singletons in the consequences, and its recurrent aspect makes it suitable for processing patterns with temporal characteristics. In birdsong recognition, the sample prediction technique is used, where one SRNFN is responsible for learning the temporal birdsong relationships of only one species. The prediction error of each SRNFN is then used as a criterion for recognition. Experiments with 10 species of birds and their songs are performed, and a high recognition rate is achieved. Comparisons with a Takagi–Sugeno–Kang (TSK)-type recurrent fuzzy network (TRFN) and backpropagation neural network are also made in the experiments.

A Recurrent Fuzzy-Network-Based Inverse Modeling Method for a Temperature System Control

Temperature control by a Takagi-Sugeno-Kang (TSK)-type recurrent fuzzy network (TRFN) designed by modeling plant inverse is proposed in this paper. TRFN is a recurrent fuzzy network developed from a series of TSK-type fuzzy if--then rules, and is characterized by structure and parameter learning. In parameter learning, two types of learning algorithms, the Kalman filter and the gradient descent learning algorithms, are applied to consequent parameters depending on the learning situation. The TRFN has the following advantages when applied to temperature control problems: 1) high learning ability, which considerably reduces the controller training time; 2) no a priori knowledge of the plant order is required, which eases the design process; 3) good and robust control performance; 4) online learning ability, i.e., the TRFN can adapt itself to unpredictable plant changes. The TRFN-based direct inverse control configuration is applied to a real water bath temperature control plant, where various control conditions are experimented. The same experiments are also performed by proportional-integral (PI), fuzzy, and neural network controllers. From comparisons, the aforementioned advantages of a TRFN have been verified

Gene networks reconstruction and time-series prediction from microarray data using recurrent neural fuzzy networks

Reverse engineering problems concerning the reconstruction and identification of gene regulatory networks through gene expression data are central issues in computational molecular biology and have become the focus of much research in the last few years. An approach has been proposed for inferring the complex causal relationships among genes from microarray experimental data, which is based on a novel neural fuzzy recurrent network. The method derives information on the gene interactions in a highly interpretable form (fuzzy rules) and takes into account the dynamical aspects of gene regulation through its recurrent structure. To determine the efficiency of the proposed approach, microarray data from two experiments relating to Saccharomyces cerevisiae and Escherichia coli have been used and experiments concerning gene expression time course prediction have been conducted. The interactions that have been retrieved among a set of genes known to be highly regulated during the yeast cell-cycle are validated by previous biological studies. The method surpasses other computational techniques, which have attempted genetic network reconstruction, by being able to recover significantly more biologically valid relationships among genes.

Recurrent fuzzy network design using hybrid evolutionary learning algorithms

This paper proposes a recurrent fuzzy network design using the hybridization of a multigroup genetic algorithm and particle swarm optimization (R-MGAPSO). The recurrent fuzzy network designed here is the Takagi–Sugeno–Kang (TSK)-type recurrent fuzzy network (TRFN), in which each fuzzy rule comprises spatial and temporal sub-rules. Both the number of fuzzy rules and the parameters in a TRFN are designed simultaneously by R-MGAPSO. In R-MGAPSO, the techniques of variable-length individuals and the local version of particle swarm optimization are incorporated into a genetic algorithm, where individuals with the same length constitute the same group, and there are multigroups in a population. Population evolution consists of three major operations: elite enhancement by particle swarm optimization, sub-rule alignment-based crossover, and mutation. To verify the performance of R-MGAPSO, dynamic plant and a continuous-stirred tank reactor controls are simulated. R-MGAPSO performance is also compared with genetic algorithms in these simulations.

Water bath temperature control by a recurrent fuzzy controller and its FPGA implementation

A hardware implementation of the Takagi-Sugeno-Kan (TSK)-type recurrent fuzzy network (TRFN-H) for water bath temperature control is proposed in this paper. The TRFN-H is constructed by a series of recurrent fuzzy if-then rules built on-line through concurrent structure and parameter learning. To design TRFN-H for temperature control, the direct inverse control configuration is adopted, and owing to the structure of TRFN-H, no a priori knowledge of the plant order is required, which eases the design process. Due to the powerful learning ability of TRFN-H, a small network is generated, which significantly reduces the hardware implementation cost. After the network is designed, it is realized on a field-programmable gate array (FPGA) chip. Because both the rule and input variable numbers in TRFN-H are small, it is implemented by combinational circuits directly without using any memory. The good performance of the TRFN-H chip is verified from comparisons with computer-based proportional-integral fuzzy (PI) and neural network controllers for different sets of experiments on water bath temperature control.

Mold temperature control of a rubber injection-molding machine by TSK-type recurrent neural fuzzy network

Practical mold temperature control of a rubber injection-molding machine is studied in this paper. The controller used is a recurrent fuzzy network called Takagi–Sugeno–Kang (TSK)-type recurrent fuzzy network (TRFN), which is characterized by its recurrent structure, on-line structure and parameter learning. Due to the powerful learning ability of TRFN, a simple controller design scheme using direct inverse configuration is proposed. With recurrent structure in TRFN, no a priori knowledge of the molding machine order is required. The designed TRFN controller performs well even if the sampling interval is different from the original one used for training. The design of TRFN consists of off-line and on-line training. For off-line learning, structure and parameter of TRFN are learned, and the consequent part parameters are tuned by Kalman filter algorithm. On-line learning is performed to fine tune the consequent parameters of TRFN and achieve a better control performance with the use a simple gradient descent algorithm. Practical experiments and comparisons with other types of controllers demonstrate the performance of the proposed TRFN controller.

TSK-type recurrent fuzzy network for DSP-based permanent-magnet linear synchronous motor servo drive

A TSK-type recurrent fuzzy network (TSKRFN) control system is proposed to control the position of the mover of a field-oriented control permanent-magnet linear synchronous motor (PMLSM) servo drive system to track periodic reference trajectories in this study. The proposed TSKRFN combines the merits of self-constructing fuzzy neural network (SCFNN), TSK-type fuzzy inference mechanism, and recurrent neural network (RNN). Moreover, the structure and the parameter learning phases are preformed concurrently and online in the TSKRFN. The structure learning is based on the partition of input space, and the parameter learning is based on the supervised gradient-descent method using a delta adaptation law. Furthermore, all the control algorithms are implemented in a TMS320C32 DSP-based control computer. The simulated and experimental results due to periodic reference trajectories show that the dynamic behaviour of the proposed TSKRFN control system is robust with regard to uncertainties.

Temperature control by chip-implemented adaptive recurrent fuzzy controller designed by evolutionary algorithm

Online adaptive temperature control by field-programmable gate array (FPGA) - implemented adaptive recurrent fuzzy controller (ARFC) chip is proposed in this paper. The RFC is realized according to the structure of Takagi-Sugeno-Kang (TSK)-type recurrent fuzzy network. Direct inverse control configuration is used. To design RFC offline, evolutionary fuzzy controller using the hybrid of the Simplex method and particle swarm optimization (SPSO) is proposed. In SPSO, each RFC corresponds to a particle, and all the free parameters in RFC are optimally searched. We use the PSO to find a good solution globally, and the incorporation of the Simplex method helps find a better solution around the local region of the best solution found by PSO so far. Then, online adaptive temperature control with ARFC chip implemented by FPGA is proposed. In the ARFC chip, the consequent parameters of all rules are all tuned online using gradient descent. To verify the performance of the ARFC chip, experiments on a water bath temperature system are performed.

A Recurrent Fuzzy Network for Fuzzy Temporal Sequence Processing and Gesture Recognition

A fuzzified Takagi-Sugeno-Kang (TSK)-type recurrent fuzzy network (FTRFN) for handling fuzzy temporal information is proposed in this paper. The FTRFN extends our previously proposed network, TRFN, to deal with fuzzy temporal signals represented by Gaussian or triangular fuzzy numbers. In the precondition part of FTRFN, matching degrees between input fuzzy variables and fuzzy antecedent sets is performed by similarity measure. In the TSK-type consequence, a linear combination of fuzzy variables is computed, where two sets of combination coefficients, one for the center and the other for the width of each fuzzy number, are used. Derivation of the linear combination results and final network output is based on left-right fuzzy number operation. There are no rules in FTRFN initially; they are constructed online by concurrent structure and parameter learning, where all free parameters in the precondition/consequence of FTRFN are all tunable. FTRFN can be applied on a variety of domains related to fuzzy temporal information processing. In this paper, it has been applied on one-dimensional and two-dimensional fuzzy temporal sequence prediction and CCD-based temporal gesture recognition. The performance of FTRFN is verified from these examples.