Learning Adaptive Neuro-fuzzy Inference System Research Articles

A Novel Hybrid IWD Algorithm with Extreme Learning Adaptive Neuro-fuzzy Inference System based Follicle Identification for Polycystic Ovary Syndrome in Ultrasound Images

The ovary's production of many follicles produces PCOS (Polycystic Ovary Syndrome) is a condition that affects women. This article developed an automated diagnostic approach for detecting follicles in the ovary utilizing ultrasound (US) images during infertility treatment. This approach includes procedures including pre-processing, segmentation, feature extraction, and classification. Weiner filter is utilized for eliminating salt and pepper noise, expectation and maximization technique is applied for segmenting follicles, texture-based and statistical features are extracted, and at last, the ovary is classified as normal and abnormal utilizing Hybrid Intelligent Water Drop (IWD) with Extreme learning adaptive neuro-fuzzy inference system (HIWD-ELANFIS) approach. Then, the severity of the disorder is identified as severe, moderate or normal by applying this new method on US images of ovaries. To determine the efficiency of this strategy, the findings are contrasted with those of other conventional methods.

Failure prediction by regularized fuzzy learning with intelligent parameters selection

Software failure time prediction, which is critical in software dependable evaluation, is among one of the most critical issues in software quality assurance research. Conventional software reliability predictions often use single models to illustrate the overall characteristic of the process of software failure. However, those models often fail to produce good prediction performance owing to the constant changes in software failure patterns during different time periods. Fuzzy systems like Takagi–Sugeno–Kang are multimodel approaches that combine simple submodels to represent the overall characteristic of dynamic nonlinear complex systems. This paper presents a novel Fuzzy system based software reliability prediction model, called regularized extreme learning adaptive neuro-fuzzy inference system, and employs the quantum-inspired binary gravitational search algorithm to determine its suitable regularization parameters. The new model can effectively reduce randomness, computational complexity as well as avoid local optimization when searching for optimal parameters. An experimentation using four real-world software failure data sets was carried out to compare the performance of the proposed model with that of certain representative software reliability prediction models. The results showed that the proposed model with the optimized parameters exhibits superior performance.

Knowledge workers mental workload prediction using optimised ELANFIS

The competitive society in the new era calls for more research to improve the well-being of workers as well as to improve their productivity. Knowledge workers face a high mental workload in terms of planning and coordination. One solution is to predict the mental workload of knowledge workers. Some machine learning models have been implemented for mental workload prediction, but deep learning models are yet to be introduced for this purpose. Deep learning models are superior to machine learning models because of their ability to correct inaccurate predictions if they ever occur. Therefore, this study aims to optimize the extreme learning adaptive neuro-fuzzy inference system (ELANFIS) by integrating particle swarm optimization into a micro-genetic algorithm to predict the mental workload of knowledge workers. Although the adaptive neuro-fuzzy inference system (ANFIS) shows reasonable prediction performance, it also suffers from the curse of dimensionality and has a poor computation time. Thus, ELANFIS is introduced because its curse of dimensionality is less severe when solving problems with a high number of input dimensions. The integration of the advantages of a micro-genetic algorithm and particle swarm optimization is suggested to optimize the premise parameters of ELANFIS, as this can allow better solutions to be located at a faster rate. The proposed model yields promising prediction results, with improvements of 6.0665 in the Mean Squared Error(MSE) and 1.279 in the Root Mean Squared Error (RMSE) for regression; the proposed model even surpasses the prediction results of ELANFIS optimized with PSO alone, with improvements of 1.5369 in MSE and 0.4094 in RMSE for regression. The findings are expected to assist employers in determining an appropriate working lifestyle for their employees.

Extreme learning adaptive neuro-fuzzy inference system model for classifying the epilepsy using Q-Tuned wavelet transform

Extreme learning adaptive neuro-fuzzy inference system model for classifying the epilepsy using Q-Tuned wavelet transform

Neuro-Fuzzy Control of DFIG Wind Energy System with Distribution Network

For highly efficient and powerful operation of modern grid connected wind energy generation system, reliable operation and smooth control strategy is sufficient. Control strategies incorporated in double fed induction generator (DFIG) based wind energy conversion system should capable for handling the uncertainties in wind speed and grid disturbances. This paper investigates a neuro-fuzzy based adaptive control strategy for controlling rotor side converter of DFIG based wind energy distribution system. Recently proposed extreme learning adaptive neuro-fuzzy inference system (ELANFIS) is utilized for efficient control. ELANFIS is a hybrid neuro-fuzzy system which combines reasoning capability of fuzzy logic systems and approximation capability of extreme learning machine (ELM). The membership function parameters of ELANFIS are calculated randomly and output parameters are found using Moore Penrose pseudo inverse method. The vector control with proposed ELANFIS control strategy on DFIG connected IEEE-34 bus system is tested under various contingencies and is able to handle the uncertainties in the wind speed and grid disturbance. The performance of the proposed in technique is verified thought real time digital simulator (RTDS) along with hardware in loop (HIL) configuration.

Research on air pollutant concentration prediction method based on self-adaptive neuro-fuzzy weighted extreme learning machine

In order to improve the prediction accuracy and real-time of the air pollutant concentration prediction, this paper proposes self-adaptive neuro-fuzzy weighted extreme learning machine (ANFIS-WELM) based on the weighted extreme learning machine (WELM) and the adaptive neuro-fuzzy inference system (ANFIS) combined air pollutant concentration prediction method. Firstly, Gaussian membership function parameters are selected to fuzzify the input values and calculate the membership degree of each input variable. Secondly, corresponding fuzzy rules are activated, and the firing strength is normalized to calculate the output matrix of hidden nodes. Then, the optimal parameters (C, M), weights are assigned to weighted ELM by using locally weighted linear regression, and the regularized WELM target formula with equality constraint is optimized by the Karush–Kuhn–Tucker (KKT) conditions, the output weight matrix is calculated, and finally the prediction output matrix is calculated. Based on the air pollutant concentration data collected in Datong, Taiwan, the data on the pollutants containing carbon monoxide (CO), nitric oxide (NO), PM2.5 (particulate matter) and PM10, are selected by different historical time series lengths, using genetic algorithm-backpropagation neural network (GA-BPNN), support vector regression (SVR), extreme learning machine (ELM), WELM, ANFIS, regularized extreme learning adaptive neuro-fuzzy inference system (R-ELANFIS) and ANFIS-WELM are built for predict the concentration of each pollutant collected by single monitoring point in single-step time series. The experimental results show that the ANFIS-WELM presented in this paper has better prediction accuracy and real-time performance, realizes the prediction of multi-step time series on the basis of the ANFIS-WELM, and realizes the engineering application of the ANFIS-WELM algorithm package on the self-developed mobile source emissions online monitoring data center software system.

Landslide displacement prediction technique using improved neuro-fuzzy system

Landslides are one of the most destructive forms of natural hazards, which cause serious threat to life and properties. Landslide monitoring and perdition of future landslide behavior is an important aspect of disaster mitigation, as it helps to issue early warnings and adopt suitable control measures in time. This paper proposes a technique, landslide displacement prediction using recently proposed extreme learning adaptive neuro-fuzzy inference system (ELANFIS) with empirical mode decomposition (EMD) technique. ELANFIS reduces the computational complexity of conventional ANFIS by incorporating the theoretical idea of extreme learning machines (ELM). The nonlinear original landslide displacement series first converted into a limited number of intrinsic mode functions (IMFs) and one residue. Then, the decomposed data are predicted using ELANFIS algorithm. Final prediction is obtained by summation of outputs of all ELANFIS submodels. The performances of the proposed technique are tested in Baishuihe and Liangshuijing landslides. The results show that ELANFIS with EMD model outperforms state of art methods in terms of prediction accuracy and generalization performance.

Particle swarm optimization based extreme learning neuro-fuzzy system for regression and classification

This paper improves the performance of adaptive neuro-fuzzy inference system (ANFIS) using extreme learning machines (ELM) concept and particle swarm optimization (PSO). The proposed learning machine, particle swarm optimization (PSO) based regularized extreme learning adaptive neuro-fuzzy inference system (PSO-RELANFIS), has the advantages of reduced randomness, reduced computational complexity and better generalization. The fuzzy membership function parameters of the proposed system are randomly selected with in constraint ranges. A regularized loss function is developed using constrained optimization and the optimized regularization parameter is obtained using PSO technique. Performance analysis on regression and classification problems shows that proposed algorithm achieves similar or better generalization performance compared to well-known kernel based methods and ELM based neuro-fuzzy systems.

Prediction of landslide displacement with controlling factors using extreme learning adaptive neuro-fuzzy inference system (ELANFIS)

Landslide is a major geo-environmental hazard which imparts serious threat to lives and properties. The slope failures are due to adverse inherent geological conditions triggered by an external factor. This paper proposes a new method for the prediction of displacement of step-like landslides, by accounting the controlling factors, using recently proposed extreme learning adaptive neuro-fuzzy inference system (ELANFIS) with empirical mode decomposition (EMD) technique. ELANFIS reduces the computational complexity of conventional ANFIS by incorporating the theoretical idea of extreme learning machines (ELM). The rainfall data and reservoir level elevation data are also integrated into the study. The nonlinear original landslide displacement series, rainfall data, and reservoir level elevation data are first converted into a limited number of intrinsic mode functions (IMF) and one residue. Then decomposed displacement data are predicted by using appropriate ELANFIS model. Final prediction is obtained by the summation of outputs of all ELANFIS sub models. The performance of proposed the technique is tested for the prediction Baishuihe and Shiliushubao landslides. The results show that ELANFIS with EMD model outperforms other methods in terms of generalization performance.

Regularized extreme learning adaptive neuro-fuzzy algorithm for regression and classification

This paper incorporates the regularization strategy of kernel based extreme learning machines (ELM) to improve the performance of a neuro-fuzzy learning machine. The proposed learning machine, regularized extreme learning adaptive neuro-fuzzy inference system (R-ELANFIS), has the advantages of reduced randomness, reduced computational complexity and better generalization. The parameters of the fuzzy layer of R-ELANFIS are randomly selected by incorporating the explicit knowledge representation using fuzzy membership functions. The parameters of the linear neural layer are determined by solving a constrained optimization problem in a regularized framework. Simulations on regression problems show that R-ELANFIS achieves similar or better generalization performance compared to well known kernel based regression methods and ELM based neuro-fuzzy systems. The proposed method can also be applied to multi-class classification problems.