Background: Abortion is an important and controversial issue and one of the important reasons for the mortality of pregnant women worldwide. This study aimed to predict the risk factors of abortion in pregnant women using artificial neural NETWORK, WAVELET neural NETWORK, and adaptive neural FUZZY inference system. Materials and Methods: The study is an analytical-comparative modeling and data of 4437 pregnant women from the Ravansar Non-Communicable Disease (RaNCD) cohort study from 2014 to 2016 was used. First, six variables were chosen through the genetic algorithm approach, then artificial neural NETWORK (ANN), WAVELET neural NETWORK (WNN), and adaptive neural FUZZY inference system (ANFIS) were run. Finally, the performance of the models was compared based on the evaluation criteria. All analyses were done in MATLAB R2019b software. Results: ANN with RMSE of 0. 019 showed better performance than ANFIS and WNN with 0. 42 and 1. 445, respectively. Further, the accuracy, sensitivity, and specificity in ANN were 100%, 99%, and 100%, while in WNN, they were 76. 2%, 76. 4%, and 66. 7%. However, when the researchers used three selected variables, the accuracy, sensitivity, and specificity as well as RMSE in ANFIS were 100%, 100% 100%, and 0,100%, 99%, 100%, and 0. 021 in ANN,and finally 76. 2%, 76. 4%, 38. 5%, and 1. 553 in WNN. Conclusion: The models with six input variables indicated that the artificial neural NETWORK has a better performance than the other two models, but based on the three variables, the FUZZY neural inference system performed better than the other two models.

The purpose of this study was to compare the predictive power of FUZZY neural NETWORK with FUZZY WAVELET neural NETWORK in predicting stock prices of banks in Tehran Stock Exchange. The period of this research was from 2011 to 2016. In this research, the FUZZY logic system with the use of a multi-layer neural NETWORK system with an error-optimized back-propagation optimization structure and a Maximum Overlapping Discrete WAVELET Transform for exchange rate variables, opec oil, each ounce of gold, the total stock index as well as the volume of trades were used in order to predict stock prices. The results of the model were done by using the updated cost function. The results of the research in comparison of FUZZY WAVELET NETWORK and FUZZY neural NETWORK showed that the reliability of banks with FUZZY WAVELET neural NETWORK is over 90% and with FUZZY neural NETWORK above is 80%. As a result, FUZZY WAVELET neural NETWORK is more reliable than FUZZY neural NETWORK.

In recent years FUZZY WAVELET Neural NETWORKs (FWNNs) have been used in many areas. Function approximation is an important application of FWNNs. One of the main problems in effective usage of FWNN is tuning of its parameters. In this paper several different evolutionary algorithms including Genetic Algorithm (GA), Gravitational Search Algorithm (GSA), Evolutionary Strategy (ES), Fast Evolutionary Strategy (FES) and variants of Differential Evolutionary algorithms (DE) are used for adjusting these parameters on five test functions. The obtained results are compared based on some measures by using multiple non-parametric statistical tests. The comparison reveals the superiority of some variants of DE in terms of convergence behavior and the ability of function approximation.

The training algorithm of WAVELET Neural NETWORKs (WNN) is a bottleneck which impacts on the accuracy of the final WNN model. Several methods have been proposed for training the WNNs. From the perspective of our research, most of these algorithms are iterative and need to adjust all the parameters of WNN. This paper proposes a one-step learning method which changes the weights between hidden layer and output layer of the NETWORK; meanwhile, the WAVELET function parameters are randomly assigned and kept fixed during the training process. Besides the simplicity and speed of the proposed one-step algorithm, the experimental results verify the performance of the proposed method in terms of final model accuracy and computational time.

This paper presents a new damping controller design based on FUZZY WAVELET neural NETWORK (FWNN) to damp the multi-machine power system low frequency oscillations. The error between the desired system output and the output of control object is directly utilized to tune the NETWORK parameters. The orthogonal least square (OLS) algorithm is used to purify the WAVELETs for each rule and determine the number of FUZZY rules and NETWORK dimension. In this paper, Shuffled Frog Leaping Algorithm (SFLA) is proposed for learning of FWNN and to find the optimal values of the parameters of the FWNN damping controller. To illustrate the capability of the proposed approach, some numerical results are presented on a 2- area 4-machine and a 5-area-16-machine power system. To show the effectiveness and robustness of the designed controller, the case studies are tested under two conditions: applying a line-to-ground fault at a bus and applying a three phase fault at a bus. Furthermore, to make a comparison, the proposed approach is compared with a classical based method and a FWNN based genetic algorithm approach, which is adopted from literature, through eigenvalue analysis, time- domain simulation and some performance indices. The simulation results show the superiority and capability of the proposed FWNN damping controller.

This paper will purpose a beat recognition algorithm using discrete WAVELET coefficients and FUZZY hybrid neural NETWORK. Cardiac beats have been detected from differential of compressed WAVELET coefficients by Linear Approximation Data Transfer (LADT) algorithm and adaptive thresholds. The variance and sum of the squared WAVELET coefficients and the R-R ratio of successive beats have been applied to the self organizing subNETWORK connected in cascade with a multi layer perceptron as final classifier.The c-means and Gustafson-Kessel algorithms have been applied for the self-organizing layer. Potential of the method was examined using MIT_BIH arrhythmia database. Results show high detection (99.43%) and high sensitivity (99.65%) on 59864 detected beats and 100% sensitivity and specificity on premature beat recognition.

This paper presents a new online Power System Stabilizer (PSS) design based on FUZZY WAVELET NETWORK (FWN) to damp the multi-machine power system low frequency oscillations. The FWN, inspired by the WAVELET theory and FUZZY concepts, is used to simultaneous design of two PSSs, in which error between system desired output and output of control object is directly utilized to tune the NETWORK parameters. The orthogonal least square (OLS) algorithm is used to determine NETWORK dimension, purify the WAVELETs for selecting efficient WAVELETs, and determine the number of sub- WAVELET neural NETWORKs and FUZZY rules. In this paper, Shuffled Frog Leaping Algorithm (SFLA) is employed for learning of FWN parameters and to find the optimal values of the controller parameters. To illustrate the capability of the proposed approach, some numerical results are presented on a 2-area 4-machine system. To show the effectiveness and robustness of the designed supplementary controllers, a line-to-ground fault and also a three phase fault are applied at a bus. Furthermore, to make a comparison, two conventional PSSs are designed in which a lead-lag structure is considered for each PSS and its parameters are tuned using SFLA. The simulation results show the superiority and capability of the FWN based PSSs.