Application of neural networks and an adapted wavelet packet for generating artificial ground motion

2011 ◽  
Vol 37 (6) ◽  
pp. 575-592 ◽  
Author(s):  
A. Asadi ◽  
M. Fadavi ◽  
A. Bagheri ◽  
G. Ghodrati Amiri
Keyword(s):  
Neural Networks ◽  
Ground Motion ◽  
Wavelet Packet ◽  
Artificial Ground Motion

Generation of critical aftershocks using stochastic neural networks and wavelet packet transform

2019 ◽  
Vol 26 (5-6) ◽  
pp. 331-351
Author(s):  
Elham Rajabi ◽  
Gholamreza Ghodrati Amiri
Keyword(s):  
Neural Networks ◽  
Principal Component Analysis ◽  
Response Spectrum ◽  
Wavelet Packet ◽  
Principal Component ◽  
Response Spectra ◽  
Component Analysis ◽  
Wavelet Packet Transform ◽  
Stochastic Neural Networks ◽  
Transform Coefficients

This paper proposes a methodology using wavelet packet transform, principal component analysis, and neural networks in order to generate artificial critical aftershock accelerograms which are compatible with the response spectra. This procedure uses the learning abilities of neural networks, principal component analysis as a dimension reduction technique, and decomposing capabilities of wavelet packet transform on consecutive earthquakes. In fact, the proposed methodology consists of two steps and expands the knowledge of the inverse mapping from mainshock response spectrum to aftershock response spectrum and aftershock response spectrum to wavelet packet transform coefficients of the aftershocks. This procedure results in a stochastic ensemble of response spectra of aftershock (first step) and corresponding wavelet packet transform coefficients (second step) which are then used to generate the aftershocks through applying the inverse wavelet packet transform. Finally, in order to demonstrate the effectiveness of the proposed method, three examples are presented in which recorded critical successive ground motions are used to train and test the neural networks.

A Supervised Classification System of Financial Data Based on Wavelet Packet and Neural Networks

2013 ◽  
Vol 4 (4) ◽  
pp. 72-84 ◽  
Author(s):  
Salim Lahmiri ◽  
Mounir Boukadoum ◽  
Sylvain Chartier
Keyword(s):  
Neural Networks ◽  
Stock Market ◽  
Classification System ◽  
Wavelet Packet ◽  
Original Data ◽  
Financial Data ◽  
Standard Approach ◽  
Support Vector ◽  
Financial Industry ◽  
Approximation Coefficients

The purpose of this paper is to present an automated system to classify financial data patterns as indicators of stock market future upward or downward moves. The classification system uses wavelet packet transform (WPT) for data decomposition and backpropagation neural networks (BPNN) for classification task. Its results are compared to those of a common classification system found in the literature which is based on ordinary wavelet transform (WT) and BPNN. In particular, the WPT is applied to the stock market data to obtain two categories of patterns: (i) approximation coefficients that represent major trend of the original data, and (ii) the residuals of the original data that capture its short-time variations. Therefore, those patterns are both complementary information used as inputs to classify stock market future shifts. For comparison purpose, BPNN and support vector machine (SVM) are separately used to classify patterns. Using S&P500 price index data, simulation results showed that both BPNN and SVM perform better with WPT extracted patterns (residuals and approximation coefficients) than standard approach based on WT approximation coefficients. In addition, BPNN outperform SVM. The WPT-NN based approach for financial data classification is more effective and promising than the standard approach adopted in the literature. The finding supports the adoption of the proposed classification system as an appropriate decision-making system in financial industry to classify financial data for forecasting purpose.

Sign in / Sign up

Export Citation Format

Share Document