Proposed Wavelet Neural Network Research Articles

Forecasting Wind Speed Using the Proposed Wavelet Neural Network

Wind energy is one of the speedy processing technologies in the energy generation industry and the most economical methods of electrical power generation. For the reliability of system, it is wanted to improve highly appropriate wind speed forecasting methods. The wavelet transform is a powerful mathematical technique that converts an analyzed signal into a time-frequency representation. This technique has proven useful in a nonstationary time series forecasting. The aims of this study are to propose a wavelet function by derivation of a quotient from two different Lucas polynomials, as well as a comparison between an artificial neural network (ANN) and wavelet-artificial neural network (WNN). We used the proposed wavelet, Mexican hat, Morlet, Gaussian, Haar, Daubechies, and Coiflet to transform the wind speed data using the continuous wavelet transform (CWT). MATLAB software was used to implement the CWT and ANN. The proposed models were applied in the meteorological field to forecast the daily wind speed data that were collected from the meteorological directorate of Sulaymaniyah which is a city located in the Kurdistan region of Iraq for the period (Jan. 2011–Dec. 2020). Five different performance criteria during calibration and validation, the root mean square error ( R M S E ), mean square error ( M S E ), mean absolute percentage error M A P E , mean absolute error M A E , and coefficient of determination ( R 2 ), were evaluated. When studying, analyzing, and comparing these models, the results of the study concluded that the proposed wavelet-ANN is the best result ( M S E = 0.00072 , R M S E = 0.02683 , M A P E = 2.32400 , and R 2 = 0.99983 .

A water cycle optimized wavelet neural network algorithm for demand prediction in cloud computing

Nowadays, using cloud computing services is becoming very popular among corporations and dependent users because of its flexibility and diverse facilities. So, demand for its infrastructures is increasing exponentially and with this huge growth of demands, it is getting more challenging for cloud providers to serve all the user requests in a way that quality of service is high enough and service level agreement is also met. Along years, researchers found out that for an optimized resource allocation which provides required user quality of service it is needed to know the amount of future workload in advance so resources can be prepared. There are many methods introduced for cloud workload prediction but excessive changes in the number of requests in cloud workloads cause a reduction in their prediction accuracy. To solve this problem, we have proposed a novel hybrid wavelet neural network method which can efficiently model excessive changes in workload and predict the upcoming requests. For training the proposed method accurately, we have used two heuristic algorithms, Artificial Immune System and Water Cycle Algorithm. The two mentioned heuristic algorithms are used for finding optimized parameters (such as bias and weight) for the wavelet neural network algorithm. The proposed wavelet neural network trained with heuristic algorithms is tested on real and standard cloud workloads. At last, the accuracy of the proposed method is thoroughly surveyed statistically and also compared with other state-of-the-art prediction methods. Simulation results show that our method improves MAPE error at least 10% in comparison to other rival prediction methods.

A New Wind Speed Forecasting Modeling Strategy Using Two-Stage Decomposition, Feature Selection and DAWNN

Accurate wind speed prediction plays a crucial role on the routine operational management of wind farms. However, the irregular characteristics of wind speed time series makes it hard to predict accurately. This study develops a novel forecasting strategy for multi-step wind speed forecasting (WSF) and illustrates its effectiveness. During the WSF process, a two-stage signal decomposition method combining ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD) is exploited to decompose the empirical wind speed data. The EEMD algorithm is firstly employed to disassemble wind speed data into several intrinsic mode function (IMFs) and one residual (Res). The highest frequency component, IMF1, obtained by EEMD is further disassembled into different modes by the VMD algorithm. Then, feature selection is applied to eliminate the illusive components in the input-matrix predetermined by partial autocorrelation function (PACF) and the parameters in the proposed wavelet neural network (WNN) model are optimized for improving the forecasting performance, which are realized by hybrid backtracking search optimization algorithm (HBSA) integrating binary-valued BSA (BBSA) with real-valued BSA (RBSA), simultaneously. Combinations of Morlet function and Mexican hat function by weighted coefficient are constructed as activation functions for WNN, namely DAWNN, to enhance its regression performance. In the end, the final WSF values are obtained by assembling the prediction results of each decomposed components. Two sets of actual wind speed data are applied to evaluate and analyze the proposed forecasting strategy. Forecasting results, comparisons, and analysis illustrate that the proposed EEMD/VMD-HSBA-DAWNN is an effective model when employed in multi-step WSF.

A Novel Deep Learning Approach With Data Augmentation to Classify Motor Imagery Signals

Brain–computer interface provides a new communication bridge between the human mind and devices, depending largely on the accurate classification and identification of non-invasive EEG signals. Recently, the deep learning approaches have been widely used in many fields to extract features and classify various types of data successfully. However, the deep learning approach requires massive data to train its neural networks, and the amount of data impacts greatly on the quality of the classifiers. This paper proposes a novel approach that combines deep learning and data augmentation for EEG classification. We applied the empirical mode decomposition on the EEG frames and mixed their intrinsic mode functions to create new artificial EEG frames, followed by transforming all EEG data into tensors as inputs of the neural network by complex Morlet wavelets. We proposed two neural networks—convolutional neural network and wavelet neural network—to train the weights and classify two classes of motor imagery signals. The wavelet neural network is a new type of neural network using wavelets to replace the convolutional layers. The experimental results show that the artificial EEG frames substantially improve the training of neural networks, and both two networks yield relatively higher classification accuracies compared to prevailing approaches. Meanwhile, we also verified the performance of our new proposed wavelet neural network model in the classification of steady-state visual evoked potentials.

Localized genetically optimized wavelet neural network for semi-active control of buildings subjected to earthquake

Control algorithm is one of the most important aspects in successful control of buildings against earthquake. In recent years, because of their capabilities, soft computing methods, stemmed from human brain abilities, have become of particular interest to researchers. In this paper, a wavelet neural network-based semi-active control model is proposed in order to provide accurately computed input voltage to the magneto rheological dampers to generate the optimum control force of structures. This model is optimized by a localized genetic algorithm and then applied to a nine-story benchmark structure subjected to 1.5× El Centro earthquake. The results show an average of 43% reduction of maximum drift in the controlled structure versus the uncontrolled one. The capability of the controller is also validated by applying other far-field and near-field earthquakes. The capability and efficiency of the proposed model are demonstrated in terms of drift, acceleration and base shear reduction. The proposed wavelet neural network is also compared with a tangent hyperbolic-based feed forward neural network, linear quadratic Gaussian, clipped optimal controller, and genetic algorithm-based fuzzy inference systems to show the superiority of the proposed controller. Copyright © 2016 John Wiley & Sons, Ltd.

Kinematic Analysis for Hybrid 2-(6-UPU) Manipulator Using Wavelet Neural Network

This paper addresses forward and inverse kinematics of a specific class of serial-parallel manipulators, known as 2(6-UPU) manipulators. This manipulator composed of two modules which consist of elementary manipulators with the parallel structure of Stewart Platform. At first, the Kinematics Model of the hybrid manipulator is obtained. As there is a highly nonlinear relations between joint variables, and position and orientation of the end effectors, the inverse kinematic problem of these manipulators is quite complicated to solve. In this study, wavelet based neural network (WNN) with its inherent learning ability, is used to solve the inverse kinematic problem. Also, proposed wavelet neural network is applied to approximate the paths of mid and upper plates in circle and spiral trajectories. Finally, the results of simulation show high accurate performance of proposed method.

Neural Network Solutions for Forward Kinematics Analysis of 2-(6UPS) Manipulator

In this paper, we present Kinematic analysis of a specific class of series–parallel manipulators, known as 2(6-UPS) manipulator, which composed of two modules which consist of elementary manipulators with the parallel structure of the Stewart Platform. After extracting the Kinematics Model of the hybrid manipulator, because of highly nonlinear relations between joint variables and position and orientation (location) of the end effectors in this kind of hybrid mechanism, we applied wavelet neural network with its inherent learning ability, to solve the kinematics problem. Proposed wavelet neural network (WNN) is applied to approximate the paths of mid and upper plate in different paths. Comparison the results of neural network with closed form solution (CFS) show high accurate performance of proposed WNN.

Model of Information Security Risk Assessment based on Improved Wavelet Neural Network

This paper concentrates on the information security risk assessment model utilizing the improved wavelet neural network. The structure of wavelet neural network is similar to the multi-layer neural network, which is a feed-forward neural network with one or more inputs. Afterwards, we point out that the training process of wavelet neural networks is made up of four steps until the value of error function can satisfy a pre-defined error criteria. In order to enhance the quality of information security risk assessment, we proposed a modified version of wavelet neural network which can effectively combine all influencing factors in assessing information security risk by linear integrating several weights. Furthermore, the proposed wavelet neural network is trained by the BP algorithm with batch mode, and the weight coefficients of the wavelet are modified with the adopting mode. Finally, a series of experiments are conduct to make performance evaluation. From the experimental results, we can see that the proposed model can assess information security risk accurately and rapidly

Wavelet Neural Network Approach for Testing of Switched-Current Circuits

Combining the time and frequency location and multiple-scale analysis of wavelet transform with the nonlinear mapping and generalizing of neural network, an efficient defect-oriented parametric test method using Wavelet Neural Network (WNN) for switched-current integrated circuits is proposed. Contraposing to the fully compatible digital CMOS technology and current scaling calculation of SI circuits, parameter cohort of switched current elements is used to compute the sensitivity and gain tolerance and is applied for selecting the test models. The selecting of the appropriate wavelet function based on particular switched current fault signal is discussed, and the number of network input and output nodes are determined by the circuit status and dimension of eigenvector which is the energy of wavelet decomposition coefficient. To simplify configuration of the neural network, the sampled data was preprocessed by wavelet transform. Illustrative examples show that the proposed wavelet neural network method for testing of switched current circuits is effective.

Research on the amplitude frequency characteristics compensation based on wavelet neural network for vibration velocity transducer

A method of amplitude frequency characteristics compensation is presented to realize ultra-low frequency vibration measurement based on wavelet neural network(WNN) for vibration velocity transducer. In this method, a dynamic compensation network can be set up according to measurement data of dynamic response of vibration velocity transducer. The compensation principle is introduced and the geometrical structure of the network is analyzed and the algorithms for the training and initialization of network parameters are given. The weights of network, scale factor and displacement factor are trained by the steepest descent method and the network parameters initialization is integrated with the wavelet type, time-frequency parameters of wavelet and the training samples. The results show that the proposed wavelet neural network has good robustness, on-line correction ability, and higher precision and faster training speed than the BP neural network when used in the amplitude frequency characteristics compensation of vibration velocity transducer, and has practical value in measurement field.

Wavelet neural network approach for fault diagnosis of analogue circuits

A systematic method for fault diagnosis of analogue circuits based on the combination of neural networks and wavelet transforms is presented. Using wavelet decomposition as a tool for removing noise from the sampled signals, optimal feature information is extracted by wavelet noise removal, multi-resolution decomposition, PCA (principal component analysis) and data normalisation. The features are applied to the proposed wavelet neural network and the fault patterns are classified. Diagnosis principles and procedures are described. The reliability of the method and comparison with other methods are shown by two active filter examples.

비선형 함수 학습 근사화를 위한 퍼지 개념을 이용한 웨이브렛 신경망

In this paper, it is proposed wavelet neural network using the fuzzy concept with the fuzzy and the multi-resolution analysis(MRA) of wavelet transform. Also, it wishes to improve any nonlinear function learning approximation using this system. Here, the fuzzy concept is used the bell type fuzzy membership function. And the composition of wavelet has a unit size. It is used the backpropagation algorithm for learning of wavelet neural network using the fuzzy concept. It is used the multi-resolution analysis of wavelet transform, the bell type fuzzy membership function and the backpropagation algorithm for learning. This structure is confirmed to be improved approximation performance than the conventional algorithms from one dimension and two dimensions function through simulation.