Self-organizing Fuzzy Neural Network Research Articles

Brain-Computer Interface for Persons with Motor Disabilities - A Review

Aim /Objective: A Brain-Computer Interface (BCI) is a communication medium, which restructures brain signals into respective commands for an external device. Methodology: A BCI allows its target users like persons with motor disabilities to act on their environment using brain signals without using peripheral nerves or muscles. In this review article, we have presented a view on different BCIs for humans with motor disabilities. Results & Conclusion: From the study, it is clear that the P300 based Electroencephalography (EEG)BCIs with Steady-State Visually Evoked Potential (SSVEP) non-parametric feature extraction techniques work with high efficiency in the major parameters like Information Bit Transfer Rate (ITR), Mutual Information (MI) rate and Low Signal to Noise Ratio (SNR) and achieve a maximum classification accuracy using Self Organized Fuzzy Neural Network (SOFNN).

A Robust Predictive Model for Stock Price Prediction Using Deep Learning and Natural Language Processing

Prediction of future movement of stock prices has been a subject matter of many research work. There is a gamut of literature of technical analysis of stock prices where the objective is to identify patterns in stock price movements and derive profit from it. Improving the prediction accuracy remains the single most challenge in this area of research. We propose a hybrid approach for stock price movement prediction using machine learning, deep learning, and natural language processing. We select the NIFTY 50 index values of the National Stock Exchange (NSE) of India, and collect its daily price movement over a period of three years (2015 – 2017). Based on the data of 2015 – 2017, we build various predictive models using machine learning, and then use those models to predict the closing value of NIFTY 50 for the period January 2018 till June 2019 with a prediction horizon of one week. For predicting the price movement patterns, we use a number of classification techniques, while for predicting the actual closing price of the stock, various regression models have been used. We also build a Long and Short-Term Memory (LSTM)-based deep learning network for predicting the closing price of the stocks and compare the prediction accuracies of the machine learning models with the LSTM model. We further augment the predictive model by integrating a sentiment analysis module on Twitter data to correlate the public sentiment of stock prices with the market sentiment. This has been done using Twitter sentiment and previous week closing values to predict stock price movement for the next week. We tested our proposed scheme using a cross validation method based on Self Organizing Fuzzy Neural Networks (SOFNN) and found extremely interesting results.

The Trajectory Tracking Control of fixed-wing UAV with Self-organizing Fuzzy Neural Network to Identify and Compensate the Modelling Uncertainties

The Trajectory Tracking Control of fixed-wing UAV with Self-organizing Fuzzy Neural Network to Identify and Compensate the Modelling Uncertainties

Multiobjective optimal control for wastewater treatment process using adaptive MOEA/D

Through the analysis of the biological wastewater treatment process (WWTP), a multiobjective optimal control strategy is developed with the usage of energy consumption (EC) and effluent quality (EQ) as objectives to be optimized. To effectively handle the multiobjective optimization problem (MOP) with complex Pareto-optimal front (POF), an adaptive multiobjective evolutionary algorithm based on decomposition (AMOEA/D) is proposed in this paper. Since the efficiency of the multiple reference points and two-phase optimization strategies in solving MOPs with complex POFs has been proved. In the proposed AMOEA/D, an auto-switching strategy based on the aggregation function enhancement is designed to automatically make the algorithm switch from the first phase to the second phase. Besides, an adaptive differential evolution strategy is introduced into AMOEA/D to balance exploration and exploitation during the evolutionary process. Finally, the dynamic optimization, intelligent decision and bottom tracking control of the set-points of the dissolved oxygen and nitrate nitrogen in the WWTP are achieved via the combination of AMOEA/D with the self-organizing fuzzy neural network approximator and the self-organizing fuzzy neural network controller. The international benchmark simulation model No. 1 (BSM1) is utilized for experimental verification. Simulation results demonstrate that the proposed AMOEA/D can effectively reduce the EC of the WWTP under the premise of ensuring effluent parameters to meet the effluent discharge standards.

Design of Self-Organizing Intelligent Controller Using Fuzzy Neural Network

In this paper, a self-organizing intelligent controller (SOIC) is proposed for a class of nonlinear systems. The basic idea of this study is to use a self-organizing fuzzy neural network to imitate control law directly, and then, appeal to obtain a compact structure of controller to further reduce the computational burden and enhance the control performance. First, an effective criterion, using the tracking performance and structure risk of controller, is developed to self-organize the control rules online for SOIC to improve the tracking performance. Second, the structure and parameters of SOIC are updated by an adaptive projection-type algorithm to reduce the heavy computational burden to speed up the control response. Third, the stability of SOIC is proved in the sense of Lyapunov and the guidelines for selecting the control parameters are given. Finally, the effectiveness of SOIC is illustrated with three nonlinear systems. It is shown that the proposed SOIC can achieve better control performance in comparison with some other control schemes.

Data-Based Predictive Control for Wastewater Treatment Process

Wastewater treatment process (WWTP) has long been a challenging industrial issue due to its built-in uncertainties and discontinuous measurement of system states. To solve this problem, in this paper, a data-based predictive control (DPC) strategy, based on the available sensing measurements, is proposed to control the dissolved oxygen (DO) concentration in WWTP. First, a self-organizing fuzzy neural network, which can adjust both the structure and parameters simultaneously, is developed to identify the real-time states of WWTP. Second, an improved nonlinear predictive control method is designed to reduce the online computation complexity by transforming the constrained conditions into an unconstrained nonlinear programming problem. Then, an adaptive second-order Levenberg-Marquardt algorithm is developed to derive the control law of DPC. Third, the theoretical analysis on the stability is also given to confirm the prerequisite of any successful application of DPC. Finally, the proposed DPC strategy is applied to the Benchmark Simulation Model No. 1. Experimental results demonstrate that the control performance of the proposed DPC is better than some existing methods.

An Efficient Second-Order Algorithm for Self-Organizing Fuzzy Neural Networks.

Intelligent computing technologies are useful and important for online data modeling, where system dynamics may be nonstationary with some uncertainties. In this paper, an efficient learning mechanism is developed for building self-organizing fuzzy neural networks (SOFNNs), where a second-order algorithm (SOA) with adaptive learning rate is employed, the network size and the parameters can be determined simultaneously in the learning process. First, all parameters of SOFNN are adjusted by using the SOA strategy to achieve fast convergence through a powerful search scheme. Second, the structure of SOFNN can be self-organized using the relative importance index of each rule. The fuzzy rules used in SOFNN with SOA (SOA-SOFNN) are generated or pruned automatically to reduce the computational complexity and potentially improve the generalization power. Finally, a theoretical analysis on the learning convergence of the proposed SOA-SOFNN is given to show the computational efficiency. To demonstrate the merits of our proposed approach for data modeling, several benchmark datasets, and a real world application associated with nonlinear systems modeling problems are examined with comparisons against other existing methods. The results indicate that our proposed SOA-SOFNN performs favorably in terms of both learning speed and prediction accuracy for online data modeling.

Introducing validity into self-organizing fuzzy neural network applied to impedance force control

In this paper, a novel self-organizing fuzzy neural network is proposed that constructed by an input–output mapping and monitored by a hierarchy of validity degrees. We define new operators called validification and devalidification to propagate validity into the six layers of proposed architecture. Self-organizing in structure learning is accomplished through a new measure that depends on error, the number of rules, and validity degrees. Additionally, a parameter learning condition is derived through studying the stability of proposed approach. To evaluate the proposed approach, an impedance controller is designed facing three challenges: different kinds of uncertainty, partial truth, and real-time realization. In the proposed controller, considering the challenge of partial truth, we assume that the manipulator's inertia is known according to first-principle knowledge while other parts are uncertain. Simulation results show the effectiveness of the proposed approach in the presence of disturbance. The proposed approach emerges as a promising approach by involving self-organizing property and possibility (fuzzy) and validity aspects of information.

Intelligent control of an MR prosthesis knee using of a hybrid self-organizing fuzzy controller and multidimensional wavelet NN

A Magneto rheological (MR) rotary brake as a prosthesis knee is addressed here. To the gait of the amputee, the brake, automatically adapts knee damping coefficient using only local sensing of the knee torque and position. It is difficult to design a model-based controller, since the MR knee system has nonlinear and very complicated governing mathematical equations. Hence, a Hybrid self-organizing fuzzy controller and multidimensional wavelet neural network (HSFCMWNN) is proposed here to control the knee damping coefficient using of the inverse dynamics of the MR rotary damper. A Self-organizing fuzzy controller (SOFC) is also proposed and during the control process, the SOFC continually updates fuzzy rules, while at the beginning contains blank fuzzy rules. Therefore the problem of finding appropriate fuzzy rules and consequently membership functions for the design of a fuzzy logic controller is ignored by using of the SOFC. It is, however, difficult to select appropriate parameters (learning rate and weighting distribution) in the SOFC which are crucial for control of MR prosthesis knee. To deal with this drawback, a hybrid self-organizing fuzzy and multidimensional wavelet neural network is employed appropriately. The proposed strategy uses a Multidimensional wavelet neural network (MWNN) to adjust these parameters in real time, to achieve to optimal values. First, the MWNN is trained by Stochastic gradient algorithm (SGA) and then to reduce the learning cycle to be needed and the appropriate error, a learning procedure based on the Levenberg-Marquardt (LM) algorithm is adopted intentionally. Simulation results demonstrate that the HSFCMWNN performs better in control performance than that of the SOFC in improving gait of the amputee.

Modeling of nonlinear systems using the self-organizing fuzzy neural network with adaptive gradient algorithm

In this paper, a self-organizing fuzzy neural network with adaptive gradient algorithm (SOFNN-AGA) is proposed for nonlinear systems modeling. First, a potentiality of fuzzy rules (PFR) method is introduced by using the output of normalized layer and the error reduction ratio (ERR) in the training process. And a structure learning approach is developed to determine the network size based on PFR. Second, a novel adaptive gradient algorithm (AGA) with adaptive learning rate is designed to adjust the parameters of SOFNN-AGA. Moreover, a theoretical analysis on the convergence of SOFNN-AGA is given to show the efficiency in both fixed structure and self-organizing structure cases. Finally, to demonstrate the merits of SOFNN-AGA, simulation and experimental results of several benchmark problems and a real world application are examined for nonlinear systems modeling with comparisons against other existing methods. Some promising results are reported in this study, indicating that the proposed SOFNN-AGA performs better favorably in terms of both convergence speed and modeling accuracy.

Research on the Virtual Machine Migration Model and QoS Guarantee Mechanism based on Fuzzy Self-Organizing Neural Network

Research on the Virtual Machine Migration Model and QoS Guarantee Mechanism based on Fuzzy Self-Organizing Neural Network

Predicting PM2.5 Concentrations at a Regional Background Station Using Second Order Self-Organizing Fuzzy Neural Network

This study aims to develop a second order self-organizing fuzzy neural network (SOFNN) to predict the hourly concentrations of fine particulate matter (PM2.5) for the next 24 h at a regional background station called Shangdianzi (SDZ) in China from 14 to 23 January 2010. The structure of the SOFNN was automatically adjusted according to the sensitivity analysis (SA) of model output and the parameter-learning phase was performed applying a second order gradient (SOG) algorithm. Principal component analysis (PCA) was employed to select the dominating factors for PM2.5 concentrations as the input variables for the SOFNN. It was found that the dominating variables (relative humidity (RH), pressure (Pre), aerosol optical depth (AOD), wind speed (WS) and wind direction (WD)) extracted by PCA agreed well with the characteristics of PM2.5 at SDZ where the PM2.5 concentrations were heavily affected by meteorological parameters and were closely related to AOD. The forecasting results showed that the proposed SOG-SASOFNN performed better than other models with higher coefficient of determination (R2) during both training phase and test phase (0.89 and 0.84, respectively) in predicting PM2.5 concentrations at SDZ. In conclusion, the developed SOG-SASOFNN provided satisfying results for modeling the hourly distribution of PM2.5 at SDZ during the studied period.

Self-organizing fuzzy control for dissolved oxygen concentration using fuzzy neural network1

In order to improve the accuracy and adaptive ability of dissolved oxygen concentration control in the wastewater treatment process (WWTP), a self-organizing fuzzy control (SOFC) method is developed in this paper. The main feature of this control system is that the fuzzy controller can extract fuzzy rules automatically using a self-organizing fuzzy neural network (FNN), which can adjust the network structure during the process based on the growing-pruning-combining algorithm. Furthermore, to ensure the convergence of the system, a compensation controller is designed to dispel the FNN approximation error, and the parameter compensation is also considered while adjusting the network structure. Finally, simulation results, based on the international benchmark simulation model No.1 (BSM1), demonstrate that the proposed method can achieve better control performance and superior adaptive ability compared with PID, model predictive control and conventional fuzzy logic controller.

Research on optimisation and application of improved fuzzy neural network control algorithm

Conventional neural fuzzy design techniques address only the parameter identification, and the structure of network is established according to the knowledge of experience. Therefore, a kind of self-organising fuzzy neural network FNN is proposed based on neural network and the advantages of FNN. First, the architecture of this proposed network is investigated, then the parameters of this new scheme are optimised by intelligent computing. At last, two experiments are done to test the performance of this new scheme. Through the analysis of experiment result, it can be seen that the proposed scheme is better than commonly used network.

Optimization and Implementation of Self-Organization Fuzzy Neutral Network Control Algorithm

Traditional fuzzy neural network tends to be used for parameters identification and the network structure is separated by grids, so there are obvious defects in this mode of control design. This paper introduces a flexibly model of self-organizing fuzzy neural network according to specific network structure. We analyze its structure and containing pa- rameters and propose an improved nearest neighbor clustering algorithm first for the predicting model of online identifica- tion. For parameter optimization, the parameter value acquired at self-organizing learning phase is adopted as the initial value of supervised learning. Then it adopts BP algorithm to adjust the parameter to optimal value based on the same training set, so as to acquire the final model of FNN. The experiments demonstrate that our algorithm can solve the pre- dicting problems of nonlinear system with constraints, and the range and changing rate of control signal. It shows rapid computing speed, better stability and strong anti-disturbance capacity. It is also verified to be suitable for actual engineer- ing control environments.

Rule generation of fuzzy logic systems using a self-organized fuzzy neural network

This paper proposes an algorithm for creating rules of a fuzzy logic system using a neuro-fuzzy approach. The proposal is based on the results of Juang and Tsao who use a Fuzzy Neural Network (FNN) to generate rules and fuzzy sets from input data. A time series example is solved using our proposal, which is tested using statistical analysis of the residuals of the model.

A Novel Self-Organized Fuzzy Neural Network Surface Reconstruction Algorithm for Point Clouds Without Normal

A Novel Self-Organized Fuzzy Neural Network Surface Reconstruction Algorithm for Point Clouds Without Normal

Development of a self sustaining cognitive architecture

A context-aware cognitive system is a prime requirement for a sensor rich smart home environment. In this paper, we discuss the development and evaluation of a self-sustaining cognitive architecture for the RUBICON (Robotic UBIquitous COgnitive Network) system which builds its knowledge as per the environmental situations. The proposed cognitive architecture consists of a reasoning module, a decision module, and a supporting memory module. An online sliding-window based self-organising fuzzy neural network (SOFNN), which explores relationships between the event inputs and desired reasoning outputs, is developed for the reasoning module. We also propose a prediction model based on event information to support the reasoning module for continuous training in the absence of external training data. The decision module generates control goals for the robots according to the status outputs from the reasoning module. We develop a MySQL based database for the memory module which supports the overall system by storing processed information about the states of the environment and providing historical information for enhanced understanding. The architecture is trained and tested with environmentally realistic synthesized data to show its adaptation capabilities. The results demonstrate that the proposed system can learn activities and track them within a smart home environment. This initial implementation also highlights the potential of the architecture and will serve as a very important test-bed for future work. We envisage that the proposed combination of the prediction model and the reasoning module will eventually result in a general purpose, self-sustaining, self-organising cognitive architecture for different applications and thus the proposed architecture enters into the sphere of the biologically inspired cognitive architecture (BICA) challenge.

A fast learnt fuzzy neural network for huge scale discrete data function approximation and prediction

In real world dataset, there are often large amount of discrete data that the concern is the interpolation and/or extrapolation by an approximation tool. Therefore, a training process will be actually used for definition and construction of the approximator parameters. Huge amount of data may lead to high computation time and a time consuming training process. To this concern a fast learnt fuzzy neural network as a robust function approximator and predictor is proposed in this paper. The learning procedure and the structure of the network is described in detail. Simplicity and fast learning process are the main features of the proposing Self-Organizing Fuzzy Neural Network SOFNN, which automates structure and parameter identification simultaneously based on input-target samples. First, without need of clustering, the initial structure of the network with the specified number of rules is established, and then a training process based on the error of other training samples is applied to obtain a more precision model. After the network structure is identified, an optimization process based on the known error criteria is performed to optimize the obtained parameter set of the premise parts and the consequent parts. At the end, comprehensive comparisons are made with other approaches to demonstrate that the proposed algorithm is superior in term of compact structure, convergence speed, memory usage and learning efficiency.

Fuzzy Kohonen clustering networks for interval data

The Fuzzy Kohonen Clustering Network combines the idea of fuzzy membership values for learning rates. It is a kind of self-organizing fuzzy neural network that can show great superiority in processing the ambiguity and the uncertainty of data sets or images. Symbolic data analysis provides suitable tools for managing aggregated data described by intervals. This paper introduces Fuzzy Kohonen Clustering Networks for partitioning interval data. The first network is based on a fixed Euclidean distance for interval and the second one considers weighted distances that change at each iteration, but are different from one cluster to another. Experiments with real and synthetic interval data sets demonstrate the usefulness of these networks.