Showing papers on "Neuro-fuzzy published in 2020"

Fuzzy Broad Learning System: A Novel Neuro-Fuzzy Model for Regression and Classification

Abstract: A novel neuro-fuzzy model named fuzzy broad learning system (BLS) is proposed by merging the Takagi–Sugeno (TS) fuzzy system into BLS. The fuzzy BLS replaces the feature nodes of BLS with a group of TS fuzzy subsystems, and the input data are processed by each of them. Instead of aggregating the outputs of fuzzy rules produced by every fuzzy subsystem into one value immediately, all of them are sent to the enhancement layer for further nonlinear transformation to preserve the characteristic of inputs. The defuzzification outputs of all fuzzy subsystem and the outputs of enhancement layer are combined together to obtain the model output. The ${k}$ -means method is employed to determine the centers of Gaussian membership functions in antecedent part and the number of fuzzy rules. The parameters that need to be calculated in a fuzzy BLS are the weights connecting the outputs of enhancement layer to model output and the randomly initialized coefficients of polynomials in consequent part in fuzzy subsystems, which can be calculated analytically. Therefore, fuzzy BLS retains the fast computational nature of BLS. The proposed fuzzy BLS is evaluated by some popular benchmarks for regression and classification, and compared with some state-of-the-art nonfuzzy and neuro-fuzzy approaches. The results indicate that fuzzy BLS outperforms other models involved. Moreover, fuzzy BLS shows advantages over neuro-fuzzy models regarding to the number of fuzzy rules and training time, which can ease the problem of rule explosion to some extent.

Development of neuro-fuzzy and neuro-bee predictive models for prediction of the safety factor of eco-protection slopes

Abstract: This study is aimed to investigate the surface eco-protection techniques for cohesive soil slopes along the selected Guthrie Corridor Expressway (GCE) stretch by way of analyzing a new set of intelligence techniques namely neuro-bee, artificial neural network (ANN) and neuro-fuzzy. Soil erosion and mass movement which induce landslides have become one of the disasters faced in Selangor, Malaysia causing enormous loss affecting human lives, destruction of property and the environment. Establishing and maintaining slope stability using mechanical structures are costly. Hence, biotechnical slope protection offers an alternative which is not only cost effective but also aesthetically pleasing. To reach the aim of the current study, a field investigations and numerical studies were conducted and a suitable database was prepared and established. By preparing factor of safety (FOS) as a single output parameter and a combination of the most important parameters on that, the desired models have been designed based on training and test patterns. In order to evaluate and compare the prediction precision of the developed models, a series of statistical indices, such as root mean squared error (RMSE), determination coefficient (R-square) and variance account for (VAF) are calculated. Many intelligence models with the most effective parameters on the mentioned models were developed to predict FOS. Based on the simulation results and the measured indices, it was found that the proposed neuro-fuzzy model with the lowest system error and highest R-square performs better as compared to other proposed ANN and neuro-bee models. Therefore, the neuro-fuzzy can provide a new applicable model to effectively predict the FOS of the slopes due to the fact that it is able to combine the advantages of the ANN and fuzzy inference system to indicate a high prediction capacity in solving problem of slope stability.

Comparison of adaptive neuro-fuzzy inference systems (ANFIS) and support vector regression (SVR) for data-driven modelling of aerobic granular sludge reactors

Abstract: Maintaining stable operation of aerobic granular sludge (AGS) reactors is a challenge due to the high sensitivity of the biomass to a wide array of parameters, and the frequent changes in influent characteristics. The application of artificial intelligence in AGS modelling has shown promising results but is still at its early stages. This work investigated, for the first time, the capabilities of two artificial intelligence algorithms for the development of predictive models for AGS reactors based on influent characteristics and operational conditions: adaptive neuro-fuzzy inference system (ANFIS), and support vector regression (SVR). The model structure adopted a two-stage modular approach. The models predicted the performance of the reactors for the unseen data with an average R2, nRMSE, sMAPE, and MASE of 91 %, 0.21, 0.06, and 0.22 for ANFIS, and 99 %, 0.07, 0.006, and 0.01 for SVR. The results showed that SVR provides more accurate predictions than ANFIS, in terms of prediction errors, and correctly predicting different types of failures. However, ANFIS provided better generalization ability than SVR. The results of this study showed the potential of artificial intelligence for the development of predictive models for the AGS process and provided insight into the selection of the appropriate algorithms for these models.

Neuro-fuzzy modeling and prediction of summer precipitation with application to different meteorological stations

Abstract: Research community has a growing interest in neural networks because of their practical applications in many fields for accurate modeling and prediction of the complex behavior of systems arising from engineering, economics, business, financial and metrological fields. Artificial neural networks (ANN) are very flexible function approximations tool used as universal modeling based on the separating of the past dynamics into clusters, in which we construct local models to capture the potential growth of the series depends on the previously known values. In this study, rain data of five major cities of Sindh province of Pakistan is considered, and summer rainfall of these five synoptic stations are statistically evaluated for prediction. The nonlinear autoregressive network with exogenous inputs (NARX) model for a time series is analyzed to evaluate the pattern of precipitation. We train a highly nonlinear NARX network model from randomly generated initial weights that converged to the best solution with the help of the Levenberg-Marquardt algorithm. A multi-step ahead NARX response time predictor is developed for rain forecasting. The performance of the NARX model is viable to capture nonlinear behavior with a high value of correlation coefficient R ranging from 0.70 to 0.99 for different synoptic stations. The results calculated using the proposed NARX neural network time series approach are accurate and reliable based on the coefficient of correlation and mean square error indices for rainfall forecasting.

Drought index prediction using advanced fuzzy logic model: Regional case study over Kumaon in India.

Abstract: A new version of the fuzzy logic model, called the co-active neuro fuzzy inference system (CANFIS), is introduced for predicting standardized precipitation index (SPI). Multiple scales of drought information at six meteorological stations located in Uttarakhand State, India, are used. Different lead times of SPI were computed for prediction, including 1, 3, 6, 9, 12, and 24 months, with inputs abstracted by autocorrelation function (ACF) and partial-ACF (PACF) analysis at 5% significance level. The proposed CANFIS model was validated against two models: classical artificial intelligence model (e.g., multilayer perceptron neural network (MLPNN)) and regression model (e.g., multiple linear regression (MLR)). Several performance evaluation metrices (root mean square error, Nash-Sutcliffe efficiency, coefficient of correlation, and Willmott index), and graphical visualizations (scatter plot and Taylor diagram) were computed for the evaluation of model performance. Results indicated that the CANFIS model predicted the SPI better than the other models and prediction results were different for different meteorological stations. The proposed model can build a reliable expert intelligent system for predicting meteorological drought at multi-time scales and decision making for remedial schemes to cope with meteorological drought at the study stations and can help to maintain sustainable water resources management.

Electrical Insulator Fault Forecasting Based on a Wavelet Neuro-Fuzzy System

Abstract: The surface contamination of electrical insulators can increase the electrical conductivity of these components, which may lead to faults in the electrical power system. During inspections, ultrasound equipment is employed to detect defective insulators or those that may cause failures within a certain period. Assuming that the signal collected by the ultrasound device can be processed and used for both the detection of defective insulators and prediction of failures, this study starts by presenting an experimental procedure considering a contaminated insulator removed from the distribution line for data acquisition. Based on the obtained data set, an offline time series forecasting approach with an Adaptive Neuro-Fuzzy Inference System (ANFIS) was conducted. To improve the time series forecasting performance and to reduce the noise, Wavelet Packets Transform (WPT) was associated to the ANFIS model. Once the ANFIS model associated with WPT has distinct parameters to be adjusted, a complete evaluation concerning different model configurations was conducted. In this case, three inference system structures were evaluated: grid partition, fuzzy c-means clustering, and subtractive clustering. A performance analysis focusing on computational effort and the coefficient of determination provided additional parameter configurations for the model. Taking into account both parametrical and statistical analysis, the Wavelet Neuro-Fuzzy System with fuzzy c-means showed that it is possible to achieve impressive accuracy, even when compared to classical approaches, in the prediction of electrical insulators conditions.

Neuro-Fuzzy Based Intrusion Detection System for Wireless Sensor Network

Abstract: Malicious attacks like denial-of-service massively affect the network activities of wireless sensor network. These attacks exploit network layer vulnerabilities and affect all the layers of the network. Anomaly based intrusion detection system (AIDS) are designed for monitoring such unpredictable attacks but it generates high false positive. In the proposed study we design robust and efficient AIDS which use fuzzy and neural network (NN) based tools. The proposed system can be implemented in each node as it is lightweight and does not consume much overhead. Also it can independently monitor the local nodes behaviour and identify whether a node is trust, distrust or enemy. The use of a trained NN filters the false alarms generated due to fuzzy logic applied in the first step thus enhancing the system accuracy. We evaluate the system’s performance in NS2.35 and result shows a 100% true positive with 0% false positive.

Artificial Neural Network and Adaptive Neuro-Fuzzy Interface System Modelling to Predict Thermal Performances of Thermoelectric Generator for Waste Heat Recovery

Abstract: The present study elaborates the suitability of the artificial neural network (ANN) and adaptive neuro-fuzzy interface system (ANFIS) to predict the thermal performances of the thermoelectric generator system for waste heat recovery. Six ANN models and seven ANFIS models are formulated by considering hot gas temperatures and voltage load conditions as the inputs to predict current, power, and thermal efficiency of the thermoelectric generator system for waste heat recovery. The ANN model with the back-propagation algorithm, the Levenberg–Marquardt variant, Tan-Sigmoidal transfer function and 25 number of hidden neurons is found to be an optimum model to accurately predict current, power and thermal efficiency. For current, power and thermal efficiency, the ANFIS model with pi-5 or gauss-5-membership function is recommended as the optimum model when the prediction accuracy is important while the ANFIS model with gbell-3-membership function is suggested as the optimum model when the prediction cost plays a crucial role along with the prediction accuracy. The proposed optimal ANN and ANFIS models present higher prediction accuracy than the coupled numerical approach.

Development of AN Advanced Method of Finding Solutions for Neuro-Fuzzy Expert Systems of Analysis of the Radioelectronic Situation

Abstract: Nowadays, artificial intelligence has entered into all spheres of our life. The system of analysis of the electronic environment is not an exception. However, there are a number of problems in the analysis of the electronic environment, namely the signals. They are analyzed in a complex electronic environment against the background of intentional and natural interference. Also, the input signals do not match the standards due to the influence of different types of interference. Interpretation of signals depends on the experience of the operator, the completeness of additional information on a specific condition of uncertainty. The best solution in this situation is to integrate with the data of the information system analysis of the electronic environment and artificial neural networks. Their advantage is also the ability to work in real time and quick adaptation to specific situations. These circumstances cause uncertainty in the conditions of the task of signal recognition and fuzzy statements in their interpretation, when the additional involved information may be incomplete and the operator makes decisions based on their experience. That is why, in this article, an improved method for finding solutions for neuro-fuzzy expert systems of analysis of the electronic environment is developed. Improving the efficiency of information processing (reducing the error) of evaluation is achieved through the use of neuro-fuzzy artificial neural networks that are evolving and learning not only the synaptic weights of the artificial neural network, but also the type and parameters of the membership function. High efficiency of information processing is also achieved through training in the architecture of artificial neural networks by taking into account the type of uncertainty of the information that has to be assessed and work with clear and fuzzy products. This reduces the computational complexity of decision-making and absence of accumulation of an error of training of artificial neural networks as a result of processing of the arriving information on an input of artificial neural networks. The use of the proposed method was tested on the example of assessing the state of the electronic environment. This example showed an increase in the efficiency of assessment at the level of 20–25 % on the efficiency of the processing information

Optimizing a Neuro-Fuzzy System Based on Nature-Inspired Emperor Penguins Colony Optimization Algorithm

Abstract: A neuro-fuzzy system is a learning machine that finds the parameters of a fuzzy system using approximate techniques of neural networks. Both neural network and fuzzy system have common features. These can solve problems that have no mathematical models. Adaptive neuro-fuzzy inference system (ANFIS) is an adaptive network that uses supervised learning on learning algorithm. To achieve effective results with ANFIS, selecting the optimization method in training is very important. Heuristics and metaheuristics algorithms attempt to find the best solution out of all possible solutions to an optimization problem. ANFIS training can be based on nonderivative algorithms. Heuristics and metaheuristics are nonderivative algorithms that can lead to better performance in ANFIS training. Most heuristic and metaheuristic algorithms are taken from the behavior of biological systems or physical systems in nature. The newly released emperor penguins colony (EPC) algorithm is a population-based and nature-inspired metaheuristic algorithm. This algorithm has much potential for solving various problems. In this article, an optimized ANFIS based on the new EPC algorithm is proposed. The optimized ANFIS is compared with other nonderivative algorithms on benchmark data sets. Eventually, the proposed algorithm is used to solve the classical inverted pendulum problem. The results show that the proposed ANFIS based on the EPC algorithm has less error and better performance than other state-of-the-art algorithms in both training and testing phase.

Human Action Performance Using Deep Neuro-Fuzzy Recurrent Attention Model

Abstract: A great number of computer vision publications have focused on distinguishing between human action recognition and classification rather than the intensity of actions performed. Indexing the intensity which determines the performance of human actions is a challenging task due to the uncertainty and information deficiency that exists in the video inputs. To remedy this uncertainty, in this paper we coupled fuzzy logic rules with the neural-based action recognition model to rate the intensity of a human action as intense or mild . In our approach, we used a Spatio-Temporal LSTM to generate the weights of the fuzzy-logic model, and then demonstrate through experiments that indexing of the action intensity is possible. We analyzed the integrated model by applying it to videos of human actions with different action intensities and were able to achieve an accuracy of 89.16% on our intensity indexing generated dataset. The integrated model demonstrates the ability of a neuro-fuzzy inference module to effectively estimate the intensity index of human actions.

Comparison of Power Output Forecasting on the Photovoltaic System Using Adaptive Neuro-Fuzzy Inference Systems and Particle Swarm Optimization-Artificial Neural Network Model

Abstract: The power output forecasting of the photovoltaic (PV) system is essential before deciding to install a photovoltaic system in Nakhon Ratchasima, Thailand, due to the uneven power production and unstable data. This research simulates the power output forecasting of PV systems by using adaptive neuro-fuzzy inference systems (ANFIS), comparing accuracy with particle swarm optimization combined with artificial neural network methods (PSO-ANN). The simulation results show that the forecasting with the ANFIS method is more accurate than the PSO-ANN method. The performance of the ANFIS and PSO-ANN models were verified with mean square error (MSE), root mean square error (RMSE), mean absolute error (MAP) and mean absolute percent error (MAPE). The accuracy of the ANFIS model is 99.8532%, and the PSO-ANN method is 98.9157%. The power output forecast results of the model were evaluated and show that the proposed ANFIS forecasting method is more beneficial compared to the existing method for the computation of power output and investment decision making. Therefore, the analysis of the production of power output from PV systems is essential to be used for the most benefit and analysis of the investment cost.

Topology Learning-based Fuzzy Random Neural Network for Streaming Data Regression

Abstract: As a type of evolving-fuzzy system, the evolving-fuzzy-neuro (EFN) system uses the structure inspired by neural networks to determine its parameters (fuzzy sets and fuzzy rules), so EFN system can inherit the advantages of neural networks. However, for streaming data regression, EFN systems still have several drawbacks: 1) determining fuzzy sets is not robust to data sequence; 2) determining fuzzy rules is complex due to subspaces that can approximate to a Takagi-Sugeno-Kang (TSK) rule need to be obtained, and many parameters need to be optimized; 3) it is difficult to detect and adapt to changes in the data distribution, i.e., concept drift, if the output is a continuous variable. Hence, in this paper, a novel evolving-fuzzy-neuro system, called the topology learning-based fuzzy random neural network (TLFRNN), is proposed. In TLFRNN, an online topology learning algorithm is designed to self-organize each layer of TLFRNN. Different from current EFN systems, TLFRNN learns multiple fuzzy sets to reduce the impact of noises on each fuzzy set, and a randomness layer is designed, which assigning the probability of each fuzzy set. Also, TLFRNN does not utilize TSK rules instead uses a simple inference which considering fuzzy and random information of data simultaneously. More importantly, in TLFRNN, concept drift can be detected and adapted easily and rapidly. The experiments demonstrate that TLFRNN achieves superior performance compared to other EFSs.

Evolving neuro-fuzzy network for real-time high impedance fault detection and classification

Abstract: This paper concerns the application of a neuro-fuzzy learning method based on data streams for high impedance fault (HIF) detection in medium-voltage power lines. A wavelet-packet-transform-based feature extraction method combined with a variation of evolving neuro-fuzzy network with fluctuating thresholds is considered for recognition of spatial–temporal patterns in the data. Wavelet families such as Haar, Symlet, Daubechie, Coiflet and Biorthogonal were investigated as a way to provide the most discriminative features for fault detection. The proposed evolving neuro-fuzzy classification model has shown to be particularly suitable for the problem because the HIF environment is subject to concept changes. Different from other statistical and intelligent approaches to the problem, the developed neuro-fuzzy model for HIF classification is not only parametrically, but also structurally adaptive to cope with nonstationarities and novelties. New neurons and connections are incrementally added to the neuro-fuzzy network when necessary for the identification of new patterns, such as faults and usual transients including sag, swell and spikes due to the switching of 3-phase capacitors and energization of transformers. Experimental evaluations compare the proposed classifier with other well-established computational intelligence methods, viz. multilayer perceptron neural network, learning vector quantization neural network and a support vector machine model. Results have shown that the evolving neuro-fuzzy system is effective and robust to changes. The system is able to maintain its detection and classification accuracy even in situations in which other classifiers exhibit a significant drop in accuracy due to gradual and abrupt changes of the fault patterns. Fuzzy rules are useful for interpretability purposes and help to enhance model credibility for decision making.

Experimental Kinematic Modeling of 6-DOF Serial Manipulator Using Hybrid Deep Learning

Abstract: According to its significance, robotics is always an area of interest for research and further development. While robots have varying types, design and sizes, the six degrees of freedom (DOF) serial manipulator is a famous robotic arm that has a vast areas of applications, not only in industrial application, but also in other fields such as medical and exploration applications. Accordingly, control and optimization of such robotic arm is crucial and needed. In this paper, different analyses are done on the chosen design of robotic arm. Forward kinematics are calculated and validated, then simulation using MSC ADAMS is done, followed by experimentation and tracking using Microsoft Kinect. Two approaches are used in this study: adaprive neuro fuzzy (ANF) system optimized by simulated annealing (SA) algorithm and convolutional neural networks (CNNs) optimized by adaptive moment estimation (Adam). The same inputs are given to both models and their results are compared in order to determine the best fit algorithm for higher precision in the given robotic model. The findings have shown that the accuracy of CNNs is higher. Furthermore, this advantage has a higher cost for the time of computation than for NFs with SA.

An Incremental Construction of Deep Neuro Fuzzy System for Continual Learning of Nonstationary Data Streams

Abstract: Existing fuzzy neural networks (FNNs) are mostly developed under a shallow network configuration having lower generalization power than those of deep structures. This article proposes a novel self-organizing deep FNN, namely deep evolving fuzzy neural network (DEVFNN). Fuzzy rules can be automatically extracted from data streams or removed if they play limited role during their lifespan. The structure of the network can be deepened on demand by stacking additional layers using a drift detection method, which not only detects the covariate drift, variations of input space, but also accurately identifies the real drift, dynamic changes of both feature space and target space. The DEVFNN is developed under the stacked generalization principle via the feature augmentation concept, where a recently developed algorithm, namely generic classifier, drives the hidden layer. It is equipped by an automatic feature selection method, which controls activation and deactivation of input attributes to induce varying subsets of input features. A deep network simplification procedure is put forward using the concept of hidden layer merging to prevent the uncontrollable growth of dimensionality of input space due to the nature of the feature augmentation approach in building a deep network structure. The DEVFNN works in the samplewise fashion and is compatible for data stream applications. The efficacy of the DEVFNN has been thoroughly evaluated using seven datasets with nonstationary properties under the prequential test-then-train protocol. It has been compared with four popular continual learning algorithms and its shallow counterpart, where the DEVFNN demonstrates improvement of classification accuracy. Moreover, it is also shown that the concept of the drift detection method is an effective tool to control the depth of the network structure, while the hidden layer merging scenario is capable of simplifying the network complexity of a deep network with negligible compromise of generalization performance.

Controlling wheeled mobile robot considering the effects of uncertainty with neuro-fuzzy cognitive map.

Abstract: In this paper, we present neuro-fuzzy cognitive map (NFCM) to control a non-holonomic wheeled mobile robot, for both the kinematic control and the dynamic control. For this purpose, the rules for updating the parameters of NFCM used in online training have been extracted. Also, the convergence of the presented approach has been confirmed by means of Lyapunov method. To evaluate the strength and robustness of the proposed model, it has been tested in tracking different circular and square paths. Experimental results indicate that despite the presence of disturbances, the changes of system parameters, and the existence of non-holonomic constraints, our robot has been able to follow challenging paths (e.g. square-shape trajectories) successfully.

Developing a hybrid adoptive neuro-fuzzy inference system in predicting safety of factors of slopes subjected to surface eco-protection techniques

Abstract: This study predicts the investigation of surface eco-protection techniques for cohesive soil slopes along the selected Guthrie Corridor Expressway stretch by way of analyzing a new set of probabilistic models using a hybrid technique of artificial neural network and fuzzy inference system namely adaptive neuro-fuzzy inference system (ANFIS). Soil erosion and mass movement which induce landslides have become one of the disasters faced in Selangor, Malaysia causing enormous loss affecting human lives, destruction of property and the environment. Establishing and maintaining slope stability using mechanical structures are costly. Hence, biotechnical slope protection offers an alternative which is not only cost effective but also aesthetically pleasing. A parametric study was carried out to discover the relationship between various eco-protection techniques, i.e., application of grasses, shrubs and trees with different soil properties as well as slope angles. Then the data have been used to develop a new hybrid ANFIS technique for prediction of factor of safety (FOS) of slopes. Four inputs were considered in relation to the different vegetation types, i.e., slope angle (θ), unit weight (γ), effective cohesion (c′), effective friction angle (o′). Then, many hybrid ANFIS models were constructed, trained and tested using various parametric studies. Eventually, a hybrid ANFIS model with a high performance prediction and a low system error was developed and introduced for solving problem of slope stability.