Wavelet Neural Network Model Research Articles

Single input-single output identification thermal response model of bridge using nonlinear ARX with wavelet networks

Model identification of a system can be used for a variety of purposes, including model updates, damage assessment, active control and original design evaluation. We used single input-single output (SISO) nonlinear regression with least square solution and nonlinear AutoRegresive with eXogenous inputs (NLARX) with wavelet neural networks models to identify the thermal response of a bridge under hard environmental effects and estimated the nonlinearity model parameters. Fu-Sui Bridge strain structural health monitoring measurements were used as a case study. Nonlinear regression analysis showed that the thermal response is a nonlinear effect with temperature changes; and the NLARX with wavelet network solution is capable of accurately predicting thermal response and can help with interpreting measurements from continuous bridge health monitoring systems.

Improved Thomas–Fiering and wavelet neural network models for cumulative errors reduction in reservoir inflow forecast

Inflow forecasting for reservoirs is a key component for reservoir operation, water resources management, and inter-regional water transfer. In this paper, to obtain enhanced accuracy in forecasting reservoir inflow, the Thomas–Fiering (TF) model as a typical stochastic model was improved through pre-defining an array in the model that was previously supposed to be a random one to find the suitable parameters for the data series for forecast errors' reduction. Also, a wavelet neural network (WNN) model was utilized to represent a machine learning approach which was improved through using an input–output matrix for the model parameter training to timely adjust input parameters according to the errors produced in the model application process, so as to reduce overall forecast errors as much as possible. Through comparing the performance of the two models within a test year, the TF model was performing better in the wet season and the WNN model had better performance in the dry seasons at the Danjiangkou Reservoir, an important water-providing area of the South-North Water Transfer Project in China. Through comparing the abilities of the improved TF and the WNN models to forecast reservoir inflow, consistencies, differences and reasonable suggestions could be obtained for helping select appropriate models over different hydrologic seasons. Thus, these two models were combined to support the forecast of reservoir inflow within an entire hydrological year. Using these models improved in this paper, the forecasted inflow to the Danjiangkou Reservoir was 4.52 × 1010 m3 in the coming year (here is 2006), which is approximately 70% of incoming frequency based on daily observed inflow data from 1980 to 2005.

Radial Wavelet Neural Network with a Novel Self-Creating Disk-Cell-Splitting Algorithm for License Plate Character Recognition

In this paper, a novel self-creating disk-cell-splitting (SCDCS) algorithm is proposed for training the radial wavelet neural network (RWNN) model. Combining with the least square (LS) method which determines the linear weight coefficients, SCDCS can create neurons adaptively on a disk according to the distribution of input data and learning goals. As a result, a disk map is made for input data as well as a RWNN model with proper architecture and parameters can be decided for the recognition task. The proposed SCDCS-LS based RWNN model is employed for the recognition of license plate characters. Compared to the classical radial-basis-function (RBF) network with K-means clustering and LS, the proposed model can make a better recognition performance even with fewer neurons.

An Image Compression Method Based on Wavelet Transform and Neural Network

Image compression is to compress the redundancy between the pixels as much as possible by using the correlation between the neighborhood pixels so as to reduce the transmission bandwidth and the storage space. This paper applies the integration of wavelet analysis and artificial neural network in the image compression, discusses its performance in the image compression theoretically, analyzes the multi-resolution analysis thought, constructs a wavelet neural network model which is used in the improved image compression and gives the corresponding algorithm. Only the weight in the output layer of the wavelet neural network needs training while the weight of the input layer can be determined according to the relationship between the interval of the sampling points and the interval of the compactly-supported intervals. Once determined, training is unnecessary, in this way, it accelerates the training speed of the wavelet neural network and solves the problem that it is difficult to determine the nodes of the hidden layer in the traditional neural network. The computer simulation experiment shows that the algorithm of this paper has more excellent compression effect than the traditional neural network method.

Wavelet Neural Network Based Wind Speed Forecasting and Wind Power Incorporated Economic Dispatch with Losses

Wind speed and wind power generation are characterized by their inherent variability and uncertainty. To overcome this drawback, an accurate prediction of wind speed is essential. The purpose of this paper is to develop a hybrid Wavelet Neural Network model for wind speed forecasting and thus, in turn, for wind power generation. The combined optimal economic scheduling of the wind generators and conventional generators has also been investigated in this paper. Three solution techniques, viz., Primal Dual Interior Point, Differential Evolution and Bacterial Foraging algorithms have been employed for optimal scheduling and tested utilizing the IEEE 118 bus system. A realistic example case, Indian utility 66 bus system is also presented. Using the simulation results, the performance of the methods proposed are compared and analyzed.

A hybrid wavelet neural network model with mutual information and particle swarm optimization for forecasting monthly rainfall

In this paper, a hybrid wavelet neural network (HWNN) model is developed for effectively forecasting monthly rainfall from antecedent monthly rainfall and climate indices by incorporating the multiresolution analysis (MRA), mutual information (MI) and particle swarm optimization (PSO) into artificial neural network (ANN) models. The standardized monthly rainfall anomaly and large-scale climate indices are first decomposed by using the maximal overlap discrete wavelet transform (MODWT) into a certain number of subseries components with different time scales. Then at each time scale, a small and appropriate subset of ANN inputs is identified by the modified partial MI algorithm from a set of candidate subseries components with different lags for forecasting the rainfall anomaly subseries at the corresponding scale. The optimal number of neurons in the hidden layers of ANNs is determined by PSO algorithm, and then each of rainfall anomaly subseries is forecasted from the selected predictor subseries. Finally, the monthly rainfall forecast is achieved by summing all the predicted anomaly subseries and applying the inverse transform of standardized monthly rainfall. The proposed HWNN method is examined with 255 rain gauge stations over Australia, and compared to the reference methods based on the undecomposed time series. The forecasting performance is compared with observed rainfall values, and evaluated by common statistics of relative absolute error and Nash–Sutcliffe efficiency. The results show that the HWNN model improves the monthly rainfall forecasting accuracy over Australia in comparison to the reference models, and the improvement is more significant for the inland stations in southeast Australia and stations in west Australia.

Prediction for Short-Term Traffic Flow Based on Optimized Wavelet Neural Network Model

Prediction for Short-Term Traffic Flow Based on Optimized Wavelet Neural Network Model

Wind power forecasting based on principle component phase space reconstruction

Forecasting of wind power is very important for both power grid and electricity market. Wind power forecasting based only on historical wind power data is carried out in this work. In a first treatment to the wind power data, Phase Space Reconstruction (PSR) is used to reconstruct the phase space of the wind dynamical system. Secondly, Principle Component Analysis (PCA) is used to minimize the influence from improper selection of the delay time and phase dimension. Finally, a prediction model, using Resource Allocating Network (RAN), is built for nonlinear mapping between the historical wind power data and the forecasting. Performance of the proposed method is compared with Persistence (PER), New-Reference (NR), and Adaptive Wavelet Neural Network (AWNN) models by using data from the US National Renewable Energy Laboratory (NREL). Analysis results indicate that the forecasting error of the proposed method is about 3% for 48 look-ahead hours, which is remarkably below the errors obtained with other forecast methods and has a probability close to 80% for 48 look-ahead hours forecasting within 12.5% error. The proposed method can also forecast wind power for turbines of different capacity and at different elevations below 10% error.

An Enhanced Wavelet Neural Network Model with Metaheuristic Harmony Search Algorithm for Epileptic Seizure Prediction

An Enhanced Wavelet Neural Network Model with Metaheuristic Harmony Search Algorithm for Epileptic Seizure Prediction

Daily precipitation predictions using three different wavelet neural network algorithms by meteorological data

In this study, three different neural network algorithms (feed forward back propagation, FFBP; radial basis function; generalized regression neural network) and wavelet transformation were used for daily precipitation predictions. Different input combinations were tested for the precipitation estimation. As a result, the most appropriate neural network model was determined for each station. Also linear regression model performance is compared with the wavelet neural networks models. It was seen that the wavelet FFBP method provided the best performance evaluation criteria. The results indicate that coupling wavelet transforms with neural network can provide significant advantages for estimation process. In addition, global wavelet spectrum provides considerable information about the structure of the physical process to be modeled.

A Wavelet-ANFIS Model to Estimate Sedimentation in Dam Reservoir

An accurate prediction of sedimentation in dam reservoir is a challenging issue due to the complex and non-linear physics of the problem. Anyhow, soft-computing-based techniques showed great ability for predicting non-linear phenomena and have been used for different purposes. The main objective of this study is to estimate the volume of sedimentation in Karaj dam using a wavelet-ANFIS (WANFIS) and a wavelet-neural network (WANN) model. Monthly average flow is used to estimate monthly averaged suspended sediment load for a thirty-year period. The amount of bed load is computed based on the suspended sediment load and the river slope and the total volume of sedimentation in the reservoir is calculated with subtracting the upstream (Karaj River) and downstream (Beylaghan River) total sediment load. In WANFIS and WANN models, monthly average flow time series are decomposed to several sub-time series using different wavelet decomposition levels. The total volume of sedimentation in Karaj dam obtained from different techniques such as WANFIS, WANN, ANFIS, ANN and hydrography are compared together. The comparison demonstrates that WANFIS model is superior to the other techniques. For WANFIS and WANN models, the best model is obtained by two and three wavelet decomposition levels respectively. Findings of this study reveal that Wavelet-ANFIS models can be applied as a successful tool to predict the volume of sedimentation.

Discussion of “Comparison of Wavelet-Based ANN and Regression Models for Reservoir Inflow Forecasting” by Krishna Budu

The discusser wishes to thank the author for investigating the accuracy of the wavelet neural network (WNN) technique in predicting daily reservoir inflows to the Malaprabha Reservoir in Belgaum, India, using daily values of rainfall, inflow, and streamflow at an upstream gauging station. The WNN results were compared with two standard neural network models along with a multiple linear regression (MLR) model and moving average (MA). It was found that the WNN model performed better than the artificial neural network (ANN) and MLR models in inflow forecasting. The discusser would like to point out some important points that the author and other researchers might consider: • According to the author, the testing data-set extremes (Xmin 1⁄4 0 and Xmax 1⁄4 1,016 m=s) fell within the training data-set limits (Xmin 1⁄4 0 and Xmax 1⁄4 1,036.4 m=s) and therefore the trained neural network models did not face difficulties in extrapolating. It is clear from Table 1, however, that Xmin 1⁄4 0.14 m=s, which was higher than the corresponding value of the testing data set and implies that these models faced difficulties in extrapolating low flow values. This can also be seen from Fig. 10, in which the WNN-BP and WNN-RB models (here BP = back propagation and RB = radial basis) slightly overestimated the low flow values. • In the study, the iteration numbers for the optimal ANN-BP, ANN-RB, WNN-BP, and WNN-RB were not provided. As seen from Table 3, the fitting accuracy of the ANN-BP model in the training period was generally similar to that of the ANN-RB model. However, WNN-BP approximated flow values in the training period much better than WNN-RB did. What might be the reason? • According to the author, it is seen from the scatter plot in Fig. 7 that the WMLR model had more values close to its predicted line and its R value was slightly higher. The discusser agrees with the author on this. However, the fit line coefficients should also have been considered in comparing the two methods. It is clear from the scatter plots (assuming that the fit line equation was y 1⁄4 axþ b) that the WNN-BP a and b coefficients were respectively closer to 1 and 0 (the ideal line is y 1⁄4 x) than were the WMLR a and b coefficients. This was also valid for Fig. 9. • The “Conclusion” section states, “Overall analysis indicates that the performance of ANN and regression models using undecomposed data is relatively lower compared to that of wavelet-decomposed data used NN and regression models; this may be plausible due to the variation in nonlinear dynamics of the rainfall runoff process that mapped effectively by waveletbased models.” In the study, however, the WMLR model was found to be better than the WNN model coupled with the RB and BP methods. The discusser wonders how the linear WMLR model could perform better than the nonlinear WNN models in such a nonlinear rainfall-runoff process, as also stated by the author. This needs clarification.

Dynamic electricity price forecasting using local linear wavelet neural network

Price forecasting has become one of the main focuses of electric power market research efforts as price is the key index to evaluate the market competition efficiency and reflects the operation condition of electricity market decision making. The work presented in this paper makes use of local linear wavelet neural networks to find the market clearing price for a given period, which is based on similar days approach. The results obtained through simulation are compared to other evolutionary optimization techniques surfaced in the recent state-of-the-art literature, including wavelet neural network model. The results presented in this paper demonstrate the potential of the proposed approach and show its effectiveness for electricity price forecasting.

Short‐term forecasting of available parking space using wavelet neural network model

The technique to forecast available parking spaces (APSs) is the foundation theory of parking guidance information systems (PGISs). This study utilises data collected on parking availability at several off-street parking garages in Newcastle upon Tyne, England, to investigate the changing characteristics of APS. Using these baseline data the research reported here aims to build up a short-term APS forecasting model and applies the wavelet neural network (WNN) method to the PGIS problem. After selecting optimal preferences, including training set size, delay time and embedding dimension, the APS short-term forecasting model based on WNN is built and tested using the real-world dataset. By experimental tests conducted using the same dataset, WNN's prediction performance is compared with the largest Lyapunov exponents (LEs) method in the aspects of accuracy, efficiency and robustness. It is found that WNN prevails through a more efficient structure and employs, barely half of the computational cost compared to the largest LEs method, which could be significant if applied to real-time operation. Moreover, WNN enjoys a more accurate performance, for its prediction average mean square error (MSE) is 6.4 ± 3.1 (in a parking building with 492 parking lots) for workdays and 8.5 ± 6.2 for weekends, compared to the MSE of largest LEs method, 18.7 and 29.0, respectively.

Forecasting of Time Series Significant Wave Height Using Wavelet Decomposed Neural Network

In this current study, a hybrid model of wavelet and Artificial Neural Network (WLNN) has been developed to forecast time series significant wave height for lead times up to 48h. The data used in the hybrid model are significant wave heights (Hs) belongs to two stations, one near to New Mangalore port, Indian ocean and another near to west of Eureka, Canada in North Pacific ocean. The three hourly significant wave height data for a period of one year was first decomposed through discrete wavelet transformation in order to obtain frequencies of different bands in the form of wavelet coefficients. Later these coefficients are used as inputs into Levenberg Marquardt artificial neural network models to forecast time series significant wave heights at multistep lead time. Two different methods WLNN-1 &WLNN-2 employed for the first station data to forecast significant wave heights at higher lead times. From the result it is found that the second method (WLNN-2) in wavelet-ANN model performed better than first method (WLNN-1).Model results obtained for two stations showed good predictions at lower lead times but slight deviation observed at higher lead times. As compared to first station results, the second station results are slightly poor because of more statistical variations in the data set.

A Hybrid Process Monitoring and Fault Diagnosis Approach for Chemical Plants

Given their potentially enormous risk, process monitoring and fault diagnosis for chemical plants have recently been the focus of many studies. Based on hazard and operability (HAZOP) analysis, kernel principal component analysis (KPCA), wavelet neural network (WNN), and fault tree analysis (FTA), a hybrid process monitoring and fault diagnosis approach is proposed in this study. HAZOP analysis helps identify the fault modes and determine process variables monitored. The KPCA model is then constructed to reduce monitoring variable dimensionality. Meanwhile, the fault features of the monitoring variables are extracted, so then process monitoring can be performed with the squared prediction error (SPE) statistics of KPCA. Then, multiple WNN models are designed through the use of low-dimensional sample data preprocessed by KPCA as the training and test samples to detect the fault mode online. Finally, FTA approach is introduced to further locate the fault root causes of the fault mode. The proposed approach is applied to process monitoring and fault diagnosis in a depropanizer unit. Case study results indicate that this approach can be applicable to process monitoring and diagnosis in large-scale chemical plants. Accordingly, the approach can serve as an early and reliable basis for technicians’ and operators’ safety management decision-making.

A wavelet neural network model for processing tomato yield forecasting

A wavelet neural network model for processing tomato yield forecasting

Improving Ann‐Based Short‐Term and Long‐Term Seasonal River Flow Forecasting with Signal Processing Techniques

AbstractOne of the key elements in achieving sustainable water resources and environmental management is forecasting the future condition of the surface water resources. In this study, the performance of a river flow forecasting model is improved when different input combinations and signal processing techniques are applied on multi‐layer backpropagation neural networks. Haar, Coiflet and Daubechies wavelet analysis are coupled with backpropagation neural networks model to develop hybrid wavelet neural networks models. Different models with different input selections and structures are developed for daily, weekly and monthly river flow forecasting in Ellen Brook River, Western Australia. Comparison of the performance of the hybrid approach with that of the original neural networks indicates that the hybrid models produce significantly better results. The improvement is more substantial for peak values and longer‐term forecasting, in which the Nash–Sutcliffe coefficient of efficiency for monthly river flow forecasting is improved from 0.63 to 0.89 in this study. Copyright © 2014 John Wiley & Sons, Ltd.

A hybrid model for integrated day‐ahead electricity price and load forecasting in smart grid

Load and price forecasting are two key issues for market participants and system operators in electricity markets. Most existing works predict load and price separately. However, a dynamic pricing type scenario is envisioned in smart grid, where consumers may have the ability to react to constantly changing price signals by shifting electricity usages from expensive hours to others, which would consequently impact electricity prices. Thus, price and load signals are strongly coupled, and previous separated forecast models may not be as effective. In this study, a two-stage integrated price and load forecasting framework is developed. The first stage provides initial price and load forecasts separately, and the second stage considers load and price interaction with initial forecasts as inputs. At each stage, a hybrid time-series and adaptive wavelet neural network (AWNN) model is used, in which multivariate autoregressive integrated moving average catches the linear relationship of price and load log return series, generalised autoregressive conditional heteroscedastic unveils heteroscedastic character of residuals and AWNN presents non-linear impacts. Several criteria such as average mean absolute percentage error and error variance are used to measure the forecasting accuracy. Illustrative forecasting examples of the New York Independent System Operator market are presented to show the efficiency of the proposed method.

Monthly discharge forecasting using wavelet neural networks with extreme learning machine

Accurate and reliable hydrological forecasting is essential for water resource management. Feedforward neural networks can provide satisfactory forecast results in most cases, but traditional gradient-based training algorithms are usually time-consum- ing and may easily converge to local minimum. Hence, how to obtain more appropriate parameters for feedforward neural networks with more precise prediction within shorter time has been a challenging task. Extreme learning machine (ELM), a new training algorithm for single-hidden layer feedforward neural networks (SLFNs), has been proposed to avoid these disadvantages. In this study, a conjunction model of wavelet neural networks with ELM (WNN-ELM) is proposed for 1-month ahead discharge forecasting. The a trous wavelet transform is used to decompose the original discharge time series into several sub-series. The sub-series are then used as inputs for SLFNs coupled with ELM algorithm (SLFNs-ELM); the output is the next step observed discharge. For comparison, the SLFNs-ELM and support vector machine (SVM) are also employed. Monthly discharge time series data from two reservoirs in southwestern China are derived for validating the models. In addition, four quantitative standard statistical performance evaluation measures are utilized to evaluate the model performance. The results indicate that the SLFNs-ELM performs slightly better than the SVM for peak discharge estimation, and the proposed model WNN-ELM provides more accurate forecast precision than SLFNs-ELM and SVM.