Fuzzy Neural Network Model Research Articles

Estimating High-Resolution PM2.5 Concentrations by Fusing Satellite AOD and Smartphone Photographs Using a Convolutional Neural Network and Ensemble Learning

Aerosol optical depth (AOD) data derived from satellite products have been widely used to estimate fine particulate matter (PM2.5) concentrations. However, existing approaches to estimate PM2.5 concentrations are invariably limited by the availability of AOD data, which can be missing over large areas due to satellite measurements being obstructed by, for example, clouds, snow cover or high concentrations of air pollution. In this study, we addressed this shortcoming by developing a novel method for determining PM2.5 concentrations with high spatial coverage by integrating AOD-based estimations and smartphone photograph-based estimations. We first developed a multiple-input fuzzy neural network (MIFNN) model to measure PM2.5 concentrations from smartphone photographs. We then designed an ensemble learning model (AutoELM) to determine PM2.5 concentrations based on the Collection-6 Multi-Angle Implementation of Atmospheric Correction AOD product. The R2 values of the MIFNN model and AutoELM model are 0.85 and 0.80, respectively, which are superior to those of other state-of-the-art models. Subsequently, we used crowdsourced smartphone photographs obtained from social media to validate the transferability of the MIFNN model, which we then applied to generate smartphone photograph-based estimates of PM2.5 concentrations. These estimates were fused with AOD-based estimates to generate a new PM2.5 distribution product with broader coverage than existing products, equating to an average increase of 12% in map coverage of PM2.5 concentrations, which grows to an impressive 25% increase in map coverage in densely populated areas. Our findings indicate that the robust estimation accuracy of the ensemble learning model is due to its detection of nonlinear correlations and high-order interactions. Furthermore, our findings demonstrate that the synergy of smartphone photograph-based estimations and AOD-based estimations generates significantly greater spatial coverage of PM2.5 distribution than AOD-based estimations alone, especially in densely populated areas where more smartphone photographs are available.

Early Risk Warning of Highway Soft Rock Slope Group Using Fuzzy-Based Machine Learning

Maintaining the stability of highway soft rock slopes is of critical importance for ensuring the safety of road networks. Although much research has been carried out to assess the stability of individual soft rock slope, the goal of efficient and effective risk management focusing on multiple highway soft rock slopes has not been fully achieved due to the many complex factors involved and the interactions among these factors. In the present study, a machine learning algorithm based on a fuzzy neural network (FNN) and a comprehensive evaluation method based on the FNN is developed, in order to identify and issue early warnings regarding the risks induced by soft rock slopes along highways, in an efficient and effective way. Using a large amount of collected soft rock slope information as training and validation data, an FNN-based risk identification model is first developed to identify the risk level of individual soft rock slope based on the meteorological conditions, topographical and geomorphological factors, geotechnical properties, and the measured horizontal displacement. An FNN-based comprehensive evaluation method is then developed, in order to quantify the risk level of a soft rock slope group according to the slope, road and external factors. The results show that the risk level identification accuracy obtained based on validation of the FNN model was higher than 90%, and the model showed a good training effect. On this basis, we further made early warnings of the risks of soft rock slope groups. The proposed early-warning model can quickly and accurately evaluate the risk posed by multiple soft rock slopes to a highway, thereby ensuring the safety of the highway.

Forecasting of short-term photovoltaic power generation using combined interval type-2 Takagi-Sugeno-Kang fuzzy systems

For the purpose of environmental protection and economic development, photovoltaic (PV) power generation is becoming increasingly popular, but the intermittence and uncertainty in PV power generation make grid-connected PV systems face severe challenges, accurate forecast is an effective way to solve this problem. Motived by the expectancy to process uncertainty and improve the prediction accuracy, in this study, a new prediction model combines interval type-2 Takagi-Sugeno-Kang (TSK) fuzzy neural network (type-2 TSKFNN) model optimized by extended Kalman filter (EKF) and SOM is proposed. A possible clustering interval is first determined according to the distribution of PV power generation, then the meteorological data are clustered using SOM, and the optimal size of categories is determined by Davies-Bouldin index (DBI). In each data partition, the decoupled extended Kalman filter (DKEF) is used to optimize the parameters of type-2 TSKFNN, including two Gaussian models with uncertain mean and uncertain standard deviation, and the independent fuzzy prediction models are established. The actual prediction analysis verifies the performance of proposed SOM-EKTSK model by using the data collected from Yulara Solar System in Australia, and the comparisons with other fuzzy logic system (FLS) models are also completed. The results show that the proposed SOM-EKTSK model has the highest prediction accuracy. Compared with other contrast models, the root mean square error (RMSE) of forecasts is reduced by 16.47% in spring, 4.75% in summer, 23.15% in autumn and 44.36% in winter, on average.© 2017 Elsevier Inc. All rights reserved.

Observer-based self-organizing adaptive fuzzy neural network control for non-linear, non-affine systems with unknown sign of control gain and dead zone: A case study of pneumatic actuators

In this paper, an observer-based self-organizing adaptive fuzzy neural network (OSOAFNN) control for non-linear, non-affine systems with the unknown sign of control gain and dead zone is presented. First, a reverse dead-zone compensator scheme to cope with the impact of dead-zone phenomenon existing in control input is investigated. Then, an observed-based control approach to address immeasurable states of the system is proposed, utilizing this approach all states of the system are not needed to be available. A self-organizing fuzzy neural network (SOFNN) technique is presented to approximate the non-linear and unknown function of the observer error dynamics. The proposed fuzzy neural network (FNN) model benefits from two main advantages: (1) the number of rules is automatically generated or pruned and (2) the parameters of antecedent and consequent part of SOFNN are updated through the hybrid tuning, simultaneously. Furthermore, the control law contains a Nussbaum function which deals with the unknown sign of control gain. As the system states are immeasurable, the strictly positive real (SPR) Lyapunov function to guarantee the closed-loop system stability, and tracking error convergence to zero is employed, as well as the boundedness of control parameters are assured through a projection law merged with adaptive law. Finally, the controller is practically implemented on a non-linear, non-affine pneumatic system with unknown dead zone which exploits just a sensor for output measuring. Experimental results show that the proposed controller has satisfactory performance in tracking different trajectories, and tracking error for desired signal case I and case II is limited to [−1.5, 1.5] and [−1,1]mm, respectively.

Trilateral Filterative Hermitian feature transformed deep perceptive fuzzy neural network for finger vein verification

Automated person recognition is an essential field to preserve individual privacy in biometrics. A conventional system performs the recognition, but inaccurate detection of finger-vein lines causes lesser verification accuracy. To address this problem, a novel Trilateral Filterative Hermitian Feature Transformation based Deep Perceptive Fuzzy Neural Network (TFHFT-DPFNN) model is introduced for the capability of learning biometric features that offers robust and accurate vein image verification with minimum time. The proposed TFHFT-DPFNN model performs four different processing stages in the network layers. In the first stage, multiple finger vein images are captured from the database. Then the input images are taken to perform the denoising in the second stage by applying a guided trilateral filter to smooth the input image for accurate matching with minimum time consumption. Followed by, Hermitian Hat wavelet transformation is applied to perform decomposition and feature extraction from the input image. Then, the extracted features are transferred to the next hidden layer where the feature matching process is carried by applying the Jaccard similarity index. Based on the similarity value, the finger vein verification is performed through the fuzzy triangular membership function at the output layer. Finally, the verified results are obtained at the output layer with minimum error. Experimental evaluation is carried out with training images and testing images on different factors such as peak signal-to-noise ratio, finger vein verification accuracy, false-positive rate, and computation time with the number of finger vein images. The proposed TFHFT-DPFNN model offers promising outcomes in terms of higher verification accuracy and lesser false-positive rate with minimum time consumption than the conventional methods.

SIMULATION OF FUZZY NEURAL NETWORK ALGORITHM IN DYNAMIC NONLINEAR SYSTEM

The identification of nonlinear system is studied to establish an accurate model of coordination system. The original dynamic fuzzy neural network (DFNN) is first used to identify the nonlinear system for finding the existing problems. Aiming at the problems found, two improvements are made. For the problem of too many pre-set parameters in the original algorithm, the fuzzy completeness [Formula: see text] is introduced to allocate the parameters, and the width of the membership function is modified. The simulation results reveal that the fuzzy neural network (FNN) model not improved produces seven fuzzy rules, and the root mean square error (RMSE) of training is 0.0261, while the improved FNN model produces six fuzzy rules, and the RMSE of training is 0.0161. The improved network has more advantages in performance. The model proposed provides some references for the application of FNN in dynamic nonlinear systems.

The establishment of prediction model for soil liquefaction based on the seismic energy using the neural network

In the development of the prediction model for soil liquefaction, compared to the stress-based method, the energy-based methods proposed and developed in recent years are closer to the essence of soil liquefaction which is about the energy dissipation. Therefore, considering the weak nonlinear relationship found by the previous research, the fuzzy neural network (FNN) and BP neural network (BPNN) were adopted to try to obtain a prediction model which is the most proper to this nonlinear relationship. Firstly, the database including 284 cases obtained from laboratory test was divided into 3 separate groups denoted as training, validation set and testing sets by the ratio of 5:1:1; then, the FNN model and BPNN model were iterated to determine the model parameter by referring to the variation of fitness value and relative error of validation set; at the same time, the optimization algorithm of genetic algorithm (GA) was adopted to BPNN to find the best coefficients; besides, the parameter of \({C}_{c}\) and \({D}_{50}\) was respectively excluded from the database to test their influence degree according to the prediction error; finally, six prediction results of FNN and genetic algorithm BP neural network (GABP) were compared with the previously proposed models. The results showed that the relationship of capacity energy to the influencing parameters could not be fitted as a fully linear relationship; the FNN model can learn the role of \({C}_{c}\) in affecting the capacity energy while the GABP model needs not to take it into account; the FNN and GABP model all fitted a good weakly nonlinear relationship for the capacity energy, and the GABP model is a better prediction model for capacity energy so far.

Detection of sludge bulking using adaptive fuzzy neural network and mechanism model

The frequent occurrence of sludge bulking can influence the effluent qualities and destroy the stable operation of activated sludge process (ASP). In order to accurately detect the sludge bulking, a detection method, based on adaptive fuzzy neural network and mechanism model, is proposed in this paper. First, a novel detection scheme is designed, where hybrid detection model and intelligent identification algorithm, are designed to describe the dynamics of sludge bulking. Second, an error compensation model, by using adaptive fuzzy neural network, is established to make up for the errors caused by the assumptions set in hybrid detection model. Finally, an error-assisted detection strategy is designed to evaluate sludge bulking. To verify the effectiveness of the proposed detection method, operating data from ASP are applied. The results show that this proposed method can efficiently detect sludge bulking.

PREDICTION OF HIGH-PERFORMANCE FIBERREINFORCED POLYMER CONCRETE USING FUZZY NEURAL NETWORK PROTOTYPES

RC building elements of Reinforcing and upgrading is essential to extend its maintenance time, to overcome first structural limitations, and to control the consequence of building construction or design flaws. The RC constructions are reinforced by using the FRP-fiber reinforced polymer. This study utilizes the FRP in concrete structures for instance a Jute, coir, and Sisal is explored for its reliability in improving ductility and strength related structural performance. FRP structural response of the model parameters is studied by measuring the numerical and experimental terms, for instance, Ductility, Deflection, Tensile-Strength, and Compression-Strength. The quality of the sample specimens is tested by using the Fuzzy Neural Network (FNN) system. At this time, compared with existing jobs, the propounded Fuzzy Neural Network model accomplishes the best presentation regarding all boundaries for the fiberreinforced specimen over different stacked conditions

Modelling of the Slope Solute Loss Based on Fuzzy Neural Network Model

In regards to soil macropores, the solute loss carried by overland flow is a very complex process. In this study, a fuzzy neural network (FNN) model was used to analyze the solute loss on slopes, taking into account the soil macropores. An artificial rainfall simulation experiment was conducted in indoor experimental tanks, and the verification of the model was based on the results. The characteristic scale of the macropores, the rainfall intensity and duration, the slope and the adsorption coefficient of ions, were chosen as the input variables to the Sugeno FNN model. The cumulative solute loss quantity on the slope was adopted as the output variable of the Sugeno FNN model. There were three membership functions, and the type of membership function was gbellmf (generalized bell membership function). The hybrid learning algorithm, which combines the back propagation algorithm with a least square method, was applied to train and optimize the network parameters, and the optimal network parameters were determined. The simulation results showed that the simulated values were consistent with the measured values.

Design of Automated Opinion Mining Model Using Optimized Fuzzy Neural Network

Sentiment analysis or Opinion Mining (OM) has gained significant interest among research communities and entrepreneurs in the recent years. Likewise, Machine Learning (ML) approaches is one of the interesting research domains that are highly helpful and are increasingly applied in several business domains. In this background, the current research paper focuses on the design of automated opinion mining model using Deer Hunting Optimization Algorithm (DHOA) with Fuzzy Neural Network (FNN) abbreviated as DHOA-FNN model. The proposed DHOA-FNN technique involves four different stages namely, preprocessing, feature extraction, classification, and parameter tuning. In addition to the above, the proposed DHOA-FNN model has two stages of feature extraction namely, Glove and N-gram approach. Moreover, FNN model is utilized as a classification model whereas GTOA is used for the optimization of parameters. The novelty of current work is that the GTOA is designed to tune the parameters of FNN model. An extensive range of simulations was carried out on the benchmark dataset and the results were examined under diverse measures. The experimental results highlighted the promising performance of DHOA-FNN model over recent state-of-the-art techniques with a maximum accuracy of 0.9928.

Bird Swarm Algorithm with Fuzzy Min-Max Neural Network for Financial Crisis Prediction

Financial crisis prediction (FCP) models are used for predicting or forecasting the financial status of a company or financial firm. It is considered a challenging issue in the financial sector. Statistical and machine learning (ML) models can be employed for the design of accurate FCP models. Though numerous works have existed in the literature, it is needed to design effective FCP models adaptable to different datasets. This study designs a new bird swarm algorithm (BSA) with fuzzy min-max neural network (FMM-NN) model, named BSA-FMMNN for FCP. The major intention of the BSA-FMMNN model is to determine the financial status of a firm or company. The presented BSA-FMMNN model primarily undergoes min-max normalization to transform the data into uniformity range. Besides, k-medoid clustering approach is employed for the outlier removal process. Finally, the classification process is carried out using the FMMNN model, and the parameters involved in it are tuned by the use of BSA. The utilization of proficient parameter selection process using BSA demonstrate the novelty of the study. The experimental result analysis of the BSA-FMMNN model is validated using benchmark dataset and the comparative outcomes highlighted the supremacy of the BSA-FMMNN model over the recent approaches.

Research and Embedded Implementation of Let-Off and Take-Up Dynamic Control Based on Fuzzy Neural Network and Vector Control Optimization

This paper investigates the warp let-off and take-up mechanism of rapier looms to solve the problem that the warp tension of rapier looms fluctuates greatly and the warp let-off is difficult to maintain constant. The design and hardware implementation of a let-off and take-up control system based on fuzzy neural network (FNN) and vector control (VC) are presented to improve the control level of warp tension and drive performance of the let-off and take-up system. Firstly, the spring-damper dynamic model of the warp is established according to the mechanical properties. The parametric expression of warp tension and the control strategy of fixed angle interval based on let-off and take-up motions are constructed according to the generation mechanism and fluctuation law of warp tension. Then, based on fuzzy reasoning mechanism and neural network model, the fusion theory of fuzzy neural network is introduced, and a tension controller based on T-S fuzzy neural network (FNN) is designed. FNN is trained by introducing genetic optimization and the backpropagation fusion algorithm (GA-BP). In addition, a specialized let-off and take-up hardware circuit is constructed through embedded technology, and the SVPWM algorithm is used as the driving scheme of the hardware circuit. Finally, simulation and actual weaving experiments test the proposed let-off and take-up control system and hardware circuit. The results show that, compared to PID and fuzzy PID, the proposed fuzzy neural network algorithm has higher tension control accuracy and can effectively restrain the rapier loom’s warp tension undulation. The designed hardware circuit and SVPWM algorithm have a fast and stable driving ability, which ensures the constant let-off amount.

A fuzzy DRBFNN-based information security risk assessment method in improving the efficiency of urban development.

The rapid development of urban informatization is an important way for cities to achieve a higher pattern, but the accompanying information security problem become a major challenge restricting the efficiency of urban development. Therefore, effective identification and assessment of information security risks has become a key factor to improve the efficiency of urban development. In this paper, an information security risk assessment method based on fuzzy theory and neural network technology is proposed to help identify and solve the information security problem in the development of urban informatization. Combined with the theory of information ecology, this method establishes an improved fuzzy neural network model from four aspects by using fuzzy theory, neural network model and DEMATEL method, and then constructs the information security risk assessment system of smart city. According to this method, this paper analyzed 25 smart cities in China, and provided suggestions and guidance for information security control in the process of urban informatization construction.

Scenario construction and deduction for railway emergency response decision-making based on network models

Railway emergencies have the characteristics of unobvious precursors and complex secondary derivatives, which is difficult for decision-makers to make effective emergency response solutions. This paper develops a scenario-response method to construct and deduce the state and severity of railway emergencies. Firstly, the scenario framework is constructed and the key scenario elements are extracted. Secondly, three scenario deduction models based on dynamic Bayesian network, fuzzy neural network, and convolutional neural network are proposed to deduce the process of an emergency. Finally, the “7.23” Yongwen train collision accident as a case study is presented and discussed. The results show that convolutional neural network model with multi time-sequence inputs has an advantage of high accuracy in comparisons with the dynamic Bayesian network model and fuzzy neural network model.

A FUZZY NEURAL NETWORK MODEL FOR ANALYZING BALTIC DRY INDEX IN THE BULK MARITIME INDUSTRY

Baltic Dry Index (BDI) is one of the important indexes in the dry bulk shipping market. BDI analysis and forecasting is one of important activities of shipowners, charterers, shipping carriers, importers and exporters, and banks in the dry bulk shipping market. Based on the accurate BDI analysis and forecasting , the shipowners, charterers, shipping carriers, importers and exporters, and banks in the bulk shipping market could make many important decisions of shipping operation, management and financial invest such as building a new bulk carrier, chartering-in or chartering-out a second-hand bulk carrier, demolishing an old bulk carrier, and providing funding for shipowners. Thus, this paper adopts a fuzzy neural network model to analyze the relationship between the BDI in the international bulk shipping market and the major economic indexes in the global financial market. Finally, the proposed fuzzy neural network model is tested by empirical data during the period of 2000-2015. The results show that the fuzzy neural network model has high accuracy of forecasting. The fuzzy neural network model in this study seems to be promising and the model could help the shipowners, charterers, shipping carriers, importers and exporters, and banks forecast future BDI points in the bulk shipping market, and then make important decisions and operation strategies of shipping operation, management and financial invest.

Credit and Financial Risk Measurement of Financial Enterprises Based on PSM Model

With the rapid development of social economy and information technology, the credit risk and financial risk of my country’s financial enterprises are also facing severe challenges. In financial enterprises, credit is related to the survival of the enterprise. As the business volume and scale of financial enterprises continue to expand, financial risks are correspondingly increased. Therefore, the research on financial enterprise credit and financial risks is of great significance. The research on the credit and financial risks of financial enterprises is helpful to help financial enterprises handle financial risks well and perform evasive operations on them. In addition, it can also enhance the credit awareness of enterprises and reduce the default rate in the financial industry. This paper studies and analyzes the financial enterprise credit and financial risk measurement based on the PSM model. First, it uses the literature method to study the PSM model, corporate credit, financial risk and other theoretical knowledge, and then establish a fuzzy neural network model for risk assessment. And the establishment of a PSM model to conduct a questionnaire survey experiment design, analyze the price sensitivity changes and acceptable price ranges under the PSM model, and get the optimal pricing of new financial products issued by financial companies. Finally, it analyzes the relationship between the default rate of corporate credit and internal finance. The conclusion is that when this financial product is priced at 45 yuan, the proportion of reserved recipients is the largest, reaching 66%; when the price is 75 yuan, the acceptable proportion is 23%, which is the acceptable number of people in the three price ranges. The proportion is the largest; if the price is 100 yuan, the unacceptable proportion is the largest, reaching 45%. This shows that the pricing of a new financial product is directly related to its sales. The reasonableness of the product pricing directly determines whether people are willing to pay for it and accept it.

Application of improved and optimized fuzzy neural network in classification evaluation of top coal cavability

Longwall top coal caving technology is one of the main methods of thick coal seam mining in China, and the classification evaluation of top coal cavability in longwall top coal caving working face is of great significance for improving coal recovery. However, the empirical or numerical simulation method currently used to evaluate the top coal cavability has high cost and low-efficiency problems. Therefore, in order to improve the evaluation efficiency and reduce evaluation the cost of top coal cavability, according to the characteristics of classification evaluation of top coal cavability, this paper improved and optimized the fuzzy neural network developed by Nauck and Kruse and establishes the fuzzy neural network prediction model for classification evaluation of top coal cavability. At the same time, in order to ensure that the optimized and improved fuzzy neural network has the ability of global approximation that a neural network should have, its global approximation is verified. Then use the data in the database of published papers from CNKI as sample data to train, verify and test the established fuzzy neural network model. After that, the tested model is applied to the classification evaluation of the top coal cavability in 61,107 longwall top coal caving working face in Liuwan Coal Mine. The final evaluation result is that the top coal cavability grade of the 61,107 longwall top coal caving working face in Liuwan Coal Mine is grade II, consistent with the engineering practice.

Medical Image Interpolation Using Recurrent Type-2 Fuzzy Neural Network.

Image interpolation is an essential process for image processing and computer graphics in wide applications to medical imaging. For image interpolation used in medical diagnosis, the two-dimensional (2D) to three-dimensional (3D) transformation can significantly reduce human error, leading to better decisions. This research proposes the type-2 fuzzy neural networks method which is a hybrid of the fuzzy logic and neural networks as well as recurrent type-2 fuzzy neural networks (RT2FNNs) for advancing a novel 2D to 3D strategy. The ability of the proposed methods in the approximation of the function for image interpolation is investigated. The results report that both proposed methods are reliable for medical diagnosis. However, the RT2FNN model outperforms the type-2 fuzzy neural networks model. The average squares error for the recurrent network and the typical network reported 0.016 and 0.025, respectively. On the other hand, the number of fuzzy rules for the recurrent network and the typical network reported 16 and 22, respectively.

Construction of fuzzy radial basis function neural network model for diagnosing prostate cancer

In this paper, we propose a construction of fuzzy radial basis function neural network model for diagnosing prostate cancer. A fuzzy radial basis function neural network (fuzzy RBFNN) is a hybrid model of logical fuzzy and neural network. The fuzzy membership function of the fuzzy RBFNN model input is developed using the triangle function. The fuzzy C-means method is applied to estimate the center and the width parameters of the radial basis function. The weight estimation is performed by various ways to gain the most accurate model. A singular value decomposition (SVD) is exploited to address this process. As a comparison, we perform other ways including back propagation and global ridge regression. The study also promotes image preprocessing using high frequency emphasis filter (HFEF) and histogram equalization (HE) to enhance the quality of the prostate radiograph. The features of the textural image are extracted using the gray level co-occurrence matrix (GLCM) and gray level run length matrix (GLRLM). The experiment results of fuzzy RBFNN are compared to those of RBFNN model. Generally, the performances of fuzzy RBFNN surpass the RBFNN in all accuracy calculation. In addition, the fuzzy RBFNN-SVD demonstrates the most accurate model for prostate cancer diagnosis.