Training ANFIS as an identifier with intelligent hybrid stable learning algorithm based on particle swarm optimization and extended Kalman filter

Teshnehlab

et al. 2015

JAIDM

The stability of learning rate in neural network identifiers and controllers is one of the challenging issues, which attract many researchers' interest in neural networks. This paper suggests adaptive gradient descent algorithm with stable learning laws for modified dynamic neural network (MDNN) and studies the stability of this algorithm. Also, stable learning algorithm for parameters of MDNN is proposed. By the proposed method, some constraints are obtained for learning rate. Lyapunov stability theory is applied to study the stability of the proposed algorithm. The Lyapunov stability theory guaranteed the stability of the learning algorithm. In the proposed method, the learning rate can be calculated online and will provide an adaptive learning rate for the MDNN structure. Simulation results are given to validate the results.

“…In this neural network, it has been assumed that 2 f is a linear function, and 1 f is a symmetric sigmoid function defined as below:…”

Section: Simulation and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Designing stable neural identifier based on Lyapunov method

Teshnehlab

et al. 2015

JAIDM

Seasonal Short‐Term Prediction of Dissolved Oxygen in Rivers via Nature‐Inspired Algorithms

Fadaee

Mahdavi‐Meymand

Zounemat‐Kermani

2020

CLEAN Soil Air Water

This study challenges the use of three nature-inspired algorithms as learning frameworks of the adaptive-neuro-fuzzy inference system (ANFIS) machine learning model for short-term modeling of dissolved oxygen (DO) concentrations. Particle swarm optimization (PSO), butterfly optimization algorithm (BOA), and biogeography-based optimization (BBO) are employed for developing predictive ANFIS models using seasonal 15 min data collected from the Rock Creek River in Washington, DC. Four independent variables are used as model inputs including water temperature (T), river discharge (Q), specific conductance (SC), and pH. The Mallow's Cp and R 2 parameters are used for choosing the best input parameters for the models. The models are assessed by several statistics such as the coefficient of determination (R 2 ), root-mean-square error (RMSE), Nash-Sutcliffe efficiency, mean absolute error, and the percent bias. The results indicate that the performance of all-nature-inspired algorithms is close to each other. However, based on the calculated RMSE, they enhance the accuracy of standard ANFIS in the spring, summer, fall, and winter around 13.79%, 15.94%, 6.25%, and 12.74%, respectively. Overall, the ANFIS-PSO and ANFIS-BOA provide slightly better results than the other ANFIS models.

Neuro‐Fuzzy Prediction of Fe‐V₂O₅‐Promoted γ‐Alumina Catalyst Behavior in the Reverse Water–Gas–Shift Reaction

et al. 2013

The application of an Fe‐V2O5‐promoted γ‐alumina catalyst was studied for the reverse water–gas–shift reaction. The reaction was performed under a wide range of synthesis conditions, temperatures, and CO2/H2 ratios in a batch reactor. The experimental results were compared with neuro‐fuzzy simulation results. The Mamdani algorithm (a gradient descent algorithm) was applied to train the fuzzy system, and a test set was used to evaluate the performance of the system by applying the efficiency coefficient (E), root‐mean‐square error (RMSE) and mean absolute error (MAE). The predicted values from the model are in good agreement with the experimental data. The outcome of this study demonstrates how the neuro‐fuzzy method, as a promising prediction technique, can be effectively applied to the reverse water–gas–shift reaction. This study applies neuro‐fuzzy modelling to predict the product composition of CO, CO2 and CH4 in the reverse water–gas–shift reaction, for which the input vector was three‐dimensional (including the variables of operating temperature, time, and CO2/H2 ratio) for 34 different experiments, and the output vectors consisted of CO, CO2 and CH4 conversions.