Hydrodynamic inline force prediction on vertical cylinders: a comparative study of neural network and its adaptive wavelets (wavenets)

In order to solve the problem that the traditional long-term high-speed traffic forecasting algorithm is affected by the approximation ability of the function and easy to fall into the local mass value, we wrote a multivariate-based highway traffic forecasting algorithm scaling and convolutional networks. Because the feedforward wavelet neural network algorithm predicts the short-term traffic flow in different areas, it is necessary to examine the ability to predict the difference between different models. From the standard feedforward wavelet neural network algorithm using global optimization capabilities, we improve the wolf pack algorithm, improve the search accuracy of the algorithm, get the best solution of the estimated value of the work according to the search results when completing the research objectives, and get the ability to predict the work of the model. Feedforward neural network algorithm: we develop and obtain the best short-term high-speed traffic forecast values. The results are as follows: after using the author’s algorithm, the processing time increases by 1.5 seconds, but the average percentage of errors decreases by more than 50%, in fact the error and the root mean square error decreased by about 30%, and the smoothing coefficient increased by about 1%. The prediction of the author’s algorithm for short-term high-speed traffic is better than the wavelet neural network prediction algorithm, and the prediction accuracy and stability of the author’s algorithm are higher.

The Sixth International Symposium on Neural Networks (ISNN 2009)

Nonlinear dynamic systems are characterized with uncertainties in terms of structure and parameters. These uncertainties cannot be described by deterministic models. The modelling and identification of nonlinear dynamic systems through the measured experimental data is a problem in engineering and technical processes. Therefore, field of system identification have become an important area of research. Fuzzy technology is an effective tool for dealing with complex nonlinear processes that are characterized with uncertain factors. In this paper, a novel approach based on Local Linear method learning in dynamical filter weights neurons for the identification of non-linear dynamic systems is presented. The fuzzy wavelet neural network combines wavelet theory with fuzzy logic and neural networks. Learning fuzzy rules and parameter update in fuzzy wavelet neural network is based on gradient decent method. The proposed approach is said to be Fuzzy Local Linear Wavelet Neural Network based model. It has been explained through examples. The structure is tested for the identification with both wavelet neural network and Fuzzy Local Linear Wavelet Neural Network that shows the comparative performance.KeywordsSystem IdentificationNon-linear SystemWavelet Neural NetworkFuzzy Wavelet Neural NetworkLocal Linear Wavelet Neural NetworkFuzzy Local Linear Wavelet Neural Network

In this paper, we aim to achieve two specific objectives. The first one is to examine the applicability of wavelet neural network (WNN) technique in ore grade estimation, which is based on integration between wavelet theory and Artificial Neural Network (ANN). Different wavelets are applied as activation functions to estimate Cu grade of borehole data in the hypogene zone of porphyry ore deposit, Shahr-e-Babak district, SE Iran. WNN parameters such as dilation and translation are fixed and only the weights of the network are optimized during its learning process. The efficacy of this type of network in function learning and estimation is compared with Ordinary Kriging (OK). Secondly, we aim to delineate the potassic and phyllic alteration regions in the hypogene zone of Cu porphyry deposit based on the estimation obtained of WNN and OK methods, and utilize Concentration–Volume (C–V) fractal model. In this regard, at first C–V log–log plots are generated based on the results of OK and WNN. The plots then are used to determine the Cu threshold values of the alteration zones. To investigate the correlation between geological model and C-V fractal results, the log ratio matrix is applied. The results showed that, Cu values less than 1.1% from WNN have more overlapped voxels with phyllic alteration zone by overall accuracy (OA) of 0.74. Spatial correlation between the potassic alteration zones resulted from 3D geological modeling and high concentration zones in C-V fractal model showed that the alteration zone has Cu values between 1.1% and 2.2% with OA of 0.72 and finally have an appropriate overlap with Cu values greater than 2.2% with OA of 0.7. Generally, the results showed that the WNN (Morlet activation function) with OA greater than OK can be can be a suitable and robust tool for quantitative modeling of alteration zones, instead of qualitative methods.

The application of wavelets in the fields of mathematics and engineering has grown rapidly in the past few years. One interesting application is to use wavelets as the activation functions in neural networks. This paper discusses the theoretical background involving wavelets from which feedforward wavelet neural networks are simply a direct consequence and evaluates a design procedure for developing these multiresolution networks. Two different wavelet neural network design examples are presented in order to demonstrate the issues involved in the design of wavelet networks. One example is to use a wavelet neural network to solve a two dimensional nonlinear function approximation problem. The other example is to use a wavelet neural network for feathering the position of the solar arrays of the Space Station.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

With the increase of the capacity of PV generated systems, how to eliminate the problem caused by the randomness of power output for photovoltaic system becomes more significant. Most of the existing photovoltaic prediction is Based on the solar radiation. However, it's difficult to implement in China due to insufficient solar radiation station available and poor forecasting performance. In addition, indirect forecasting cannot consider the factors related with PV system. A novel power forecasting model using historical power is proposed to solve the problems. Furthermore, in order to adapt sudden weather changes, the future weather type was recognized by using self-organizing feature map(SOM). Then, PV power generation in each weather type could be forecasted from its corresponding forecast network and the over fitting issue of single network model could be addressed. Wavelet neural network is combined with wavelet analysis and neural network. It is compatible with the good time-frequency property and good fault tolerant ability of neural network. Wavelet neural network can optimize the forecasting model. The experimental results indicate that the prediction has high precision and can be applied in stable operation of photovoltaic generation system.

Wavelet transformation has the ability of representing a function and revealing the properties of the function in the joint local regions of the time frequency space. Based on wavelet and artificial neural network, a Wavelet Neural Network (WNN) model predicting the average post-dry out Nusselt number for upward flow in vertical narrow annuli with bilateral heating has been developed. The WNN mode combining the properties of the wavelet transform and the advantages of Artificial Neural Networks (ANN) has some advantages of solving non-linear problem.

The main purpose of this paper is to propose the use of Group Method of Data Handling (GMDH) to predict software reliability. The GMDH algorithm presented in this paper is a heuristic self-organization method. It establishes the input-output relationship of a complex system using multilayered perception type structure that is similar to a feed forward multilayer neural network. The effectiveness of GMDH is demonstrated on a dataset taken from literature. Its performance is compared with that of multiple linear regression (MLR), back propagation trained neural networks (BPNN), threshold accepting trained neural network (TANN), general regression neural network (GRNN), pi-sigma network (PSN), dynamic evolving neuro-fuzzy inference system (DENFIS), TreeNet, multivariate adaptive regression splines (MARS) and wavelet neural network (WNN) in terms of normalized root mean square error (NRMSE). Based on experiments conducted, it is found that GMDH predicted reliability with least error compared to other techniques. Hence, GMDH can be used a sound alternative to the existing techniques for software reliability prediction.KeywordsSoftware reliability forecastingGroup method of Data handlingIntelligent Techniques

Electronic tongues are bioinspired systems that employ an array of sensors for analysis, recognition or identification of chemical species in liquids. This work presents the use of a Wavelet Neural Network (WNN) with multiple outputs to model a multianalyte quantification from a highly complex sensor signal. In this case, WNN accomplishes data reduction, feature extraction and modeling. WNN is implemented with a feedforward multilayer perceptron architecture, whose activation functions in its hidden layer neurons are wavelet functions, in our case, the first derivative of a Gaussian function. The neural network is trained using a backpropagation algorithm, adjusting the connection weights along with the wavelet parameters. The principle is applied to the simultaneous quantification of heavy metals present in a solution. Lead, Cadmium and Copper were therefore accurately determined in the 0.01-0.1ppm range in presence of Thallium and Indium with no need elimination of dissolved oxygen, as it is normally required in the standard chemical laboratory.

In 2014, the relevant research data from the Ministry of Environmental Protection and the Ministry of Land and Resources showed that the total exceedance rate of soil heavy metal pollution in China had reached 16.1%, and in the construction of ecological civilization in the 13th Five-Year Plan, China has made the prevention and control of soil heavy metal pollution as the focus of prevention and control. Therefore, in this paper, four neural optimization network models, that is, radial basis neural network (RBFNN), generalized regression neural network (GRNN), wavelet neural network (WNN), and fuzzy neural network (FNN), are simulated and created to measure and correlate the soil heavy metal content in a city in northwest China and a city in central China from the actual situation in China. The simulations were conducted. Finally, by analyzing the comparison of predicted and true values of these four models on the test data of two sets of experimental data, the distribution of predicted differences to true values, and the calculation results of three error indicators, we found that WNN has the best prediction performance when using RBFNN, GRNN, WNN, and FNN for soil heavy metal content prediction.

Prediction of wind pressures on tall buildings using wavelet neural network

The approximation of general continuous functions by nonlinear networks is very useful for system modeling and identification. Such approximation methods can be used, for example, in black-box identification of nonlinear systems, signal processing, control, statistical data analysis, speech recognition, and artificial intelligence. Recently neural networks have been established as a general approximation tool for fitting nonlinear models from input/output data due to their ability of learning rather than complicated process functions (Gao, 2002). Their attractive property is the self-learning ability. A neural network can extract the system features from historical training data using the learning algorithm, requiring little or no a priori knowledge about the process (Patan, 2008). This is why during the past few years the nonlinear dynamic modelling of processes by neural networks has been extensively studied (Narendra & Parthasarathy, 1990; Nerrand et al., 1993; Levin, 1992; Rivals & Personnaz, 1996). In standard neural networks, the nonlinearities are approximated by superposition of sigmoidal functions (Cybenko, 1989). In the other hand, the wavelet theory has found many applications in function approximation, numerical analysis and signal processing. Though this attractive theory has offered efficient algorithms for various purposes, their implementations are usually limited to wavelets of small dimension. The reason is that constructing and storing wavelet basis of large dimension are of prohibitive cost. In order to handle problems of larger dimension, it is necessary to develop algorithms whose implementation is less sensitive to the dimension. And it is known that neural networks are powerful tools for handling problems of large dimension. Due to the similarity between wavelet decomposition and one-hidden-layer neural networks, the idea of combining both wavelets and neural networks has been proposed in various works (Zhang & Benveniste, 1992; Pati & Krishnaprasad, 1993; Hong, 1992; Bakshi & Stephanopoulos, 1993; Tsatsanis & Giannakis, 1993;et al., 1994; Delyon et al., 1995; Saad Saoud & Khellaf, 2009). For example, in (Zhang & Benveniste, 1992) wavelet network is introduced as a class of feedforward networks composed of wavelets, in (Pati & Krishnaprasad, 1993) the discrete wavelet transform is used for analyzing and synthesizing

Apart from the existing technology on image compression represented by series of JPEG, MPEG and H.26x standards, new technology such as Wavelet Neural Networks (WNN) and genetic algorithms are being developed to explore the future of image coding. Successful applications of WNN in the case of function approximation become well established. This paper presents a direct solution method based on Multi Library WNN for color image compression and coding which consists to transform an RGB image into Luminance-Chrominance space and then segment the luminance in a set of m blocks n by n pixels. These blocks should be transferred row by row (1D input vector) to the input of our wavelet network. Every input vector will be considered as unknown functional mapping and then it will be approximated by the network.

A novel method based on a physics informed data driven model is developed to design an origami composite crash tube. The structure consists of two axially stacked basic components, called modules. Each module presents lower and upper square sections with an octagonal section in the middle. The parameters of the octagonal cross-section and the height of each module are optimized to maximize the energy absorption of the tube when subjected to an axial impact. In contrast to standard surrogate modelling techniques, whose accuracy only depends on the amount of available data, a Physics-informed Neural Network (PINN) scheme is adopted to correlate the crushing response of the single modules to that of the whole origami tube, constraining the data driven method to physically consistent predictions. The PINN is first trained on the results obtained with an experimentally validated Finite Element model and then used to optimize the structure. Results show that the PINN can accurately predict the crushing response of the origami tube, while consistently reducing the computational effort required to explore the whole design domain. Also, the comparison with a standard Feed Forward Neural Network (FFNN) shows that the PINN scheme leads to more accurate results.

Prediction of programmed-temperature retention values of naphthas by wavelet neural networks