Neural Networks for Applied Sciences and Engineering

Samarasinghe, Sandhya

doi:10.1201/9781420013061

Cited by 108 publications

(83 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This a kind of combination of first order and second derivatives of error with a free parameter. It has a good convergence rate compared to others algorithm and has good accuracy performance and suitable for time series forecasting [10], [26].…”

Section: Methodsmentioning

confidence: 99%

“…This ANN usage for forecasting comes to some considerations: 1) neural network can adapt to data so there is no need to make prior assumption about the data, 2) neural network can do generalization, 3) neural network is a universal approximator [9]; 4) neural network is a nonlinear model that is suitable for exchange rate [10], [11]. The neural network is also known as a good model to explain dynamic time series [12], [13] complex, noisy and partial time series [14].…”

Section: Literature Revi Ewmentioning

confidence: 99%

See 1 more Smart Citation

Exchange rates forecasting using nonlinear autoregressive

Sihabuddin¹,

Hartati²

2016

AIP Conference Proceedings

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Section: Literature Revi Ewmentioning

confidence: 99%

Exchange rates forecasting using nonlinear autoregressive

Sihabuddin¹,

Hartati²

2016

AIP Conference Proceedings

View full text Add to dashboard Cite

“…In on-line methods the weights are changed after each presentation of a training pattern. For some problems, this method may yield effective results, especially for problems where data arrives in real time, (Samarasinghe, 2006). Using on-line training it is possible to reduce training times significantly.…”

Section: 3training a Wavelet Network With Back-propagationmentioning

confidence: 99%

“…Moreover a bad regularization parameter,  , can severely restrict the growth of weights and as result the network will be under-fitted, (Samarasinghe, 2006). Finally in pruning methods the significance of each weight usually is not measured in a statistical way, (Anders & Korn, 1999).…”

Section: Model Selectionmentioning

confidence: 99%

“…First, there is a possibility that the training will stop before the presentation of each training pattern to the network. Second, by changing the weights after each pattern, they could bounce back and forth with each iteration, possibly resulting in a substantial amount of wasted time, (Samarasinghe, 2006). Hence, in order to ensure the stability of the algorithms, offline training is used in this study.…”

Section: 3training a Wavelet Network With Back-propagationmentioning

confidence: 99%

See 1 more Smart Citation

Wavelet neural networks: A practical guide

2013

View full text Add to dashboard Cite

Abstract-Wavelet networks (WNs) are a new class of networks which have been used with great success in a wide range of application. However a general accepted framework for applying WNs is missing from the literature. In this study, we present a complete statistical model identification framework in order to apply WNs in various applications. The following subjects were thorough examined: the structure of a WN, training methods, initialization algorithms, variable significance and variable selection algorithms, model selection methods and finally methods to construct confidence and prediction intervals. In addition the complexity of each algorithm is discussed. Our proposed framework was tested in two simulated cases, in one chaotic time series described by the Mackey-Glass equation and in three real datasets described by daily temperatures in Berlin, daily wind speeds in New York and breast cancer classification. Our results have shown that the proposed algorithms produce stable and robust results indicating that our proposed framework can be applied in various applications.

show abstract

Artificial neural network prediction of thermal and mechanical properties forBi₂O₃‐polybenzoxazinenanocomposites

Hassan

Derradji

Ali

et al. 2022

J of Applied Polymer Sci

View full text Add to dashboard Cite

Polybenzoxazine (BA-a) based nanocomposites with varying amounts of Bi 2 O 3 particles reinforcement (10, 20, and 30 wt%) were produced. The structures of the Bi 2 O 3 before and after surface silane treatment, as well as the structures of the BA-a matrix and its nanocomposites, were all evaluated using Fourier transform infrared spectroscopy (FTIR). The thermal stability of the samples was evaluated by thermogravimetric analysis (TGA) and the resistance to bending was studied using the three-point bending test. Then, an artificial neural network approach was used to estimate the thermal degradation and flexural strengths of the polybenzoxazine matrix and its nanocomposites. The results of the TGA analysis showed that when Bi 2 O 3 content increased, the char yield (Y c ) of the nanocomposites also increased from 27.98% to 43.53% for the experimental data and from 27.95% to 43 0.57% for the prediction, with all SDs less than 0.02. Moreover, both the experimental and predicted values of the flexural strengths for the unfilled BA-a displayed 100.40 and 102.96 MPa, respectively and these values increased to 119.65 and 114.95 MPa when 10 wt % of fillers were incorporated into the matrix. However, for higher filler contents, 20 and 30 wt%, these values decreased to 112.94 and 108.01 MPa for the experiments, and 106.35 and 103.20 MPa for the prediction, respectively. The very small deviations (<0.05) between the experimental and predicted values demonstrated that the prediction approach using the artificial neural network is reliable and accurate.

show abstract

Neural Networks for Applied Sciences and Engineering

Cited by 108 publications

References 0 publications

Exchange rates forecasting using nonlinear autoregressive

Exchange rates forecasting using nonlinear autoregressive

Wavelet neural networks: A practical guide

Artificial neural network prediction of thermal and mechanical properties forBi₂O₃‐polybenzoxazinenanocomposites

Contact Info

Product

Resources

About

Neural Networks for Applied Sciences and Engineering

Cited by 108 publications

References 0 publications

Exchange rates forecasting using nonlinear autoregressive

Exchange rates forecasting using nonlinear autoregressive

Wavelet neural networks: A practical guide

Artificial neural network prediction of thermal and mechanical properties forBi2O3‐polybenzoxazinenanocomposites

Contact Info

Product

Resources

About

Artificial neural network prediction of thermal and mechanical properties forBi₂O₃‐polybenzoxazinenanocomposites