GA based meta-modeling of BPN architecture for constrained approximate optimization

Lee, Jong-Soo; Kang, Seongkyu

doi:10.1016/j.ijsolstr.2007.02.008

Cited by 27 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(iv). Evolutionary strategies that search over topology space by varying the number of hidden layers and hidden neurons through application of genetic operators (Castillo, Merelo, Prieto, Rivas, & Romero, 2000;Lee & Kang, 2007) and evaluation of the different architectures according to an objective function (Arifovic & Gencay, 2001;Benardos & Vosniakos, 2007).…”

Section: The Ann Approach To Time Series Modelingmentioning

confidence: 99%

An artificial neural network (p,d,q) model for timeseries forecasting

Khashei

Bijari

2010

Expert Systems with Applications

647

252

View full text Add to dashboard Cite

Section: The Ann Approach To Time Series Modelingmentioning

confidence: 99%

An artificial neural network (p,d,q) model for timeseries forecasting

Khashei

Bijari

2010

Expert Systems with Applications

647

252

View full text Add to dashboard Cite

“…The basic rules are that neurons are added when training is slow or when the mean squared error is larger than a specified value and that neurons are removed when a change in a neuron's value does not correspond to a change in the network's response or when the weight values that are associated with this neuron remain constant for a large number of training epochs (Marin et al 2007). (4) Evolutionary strategies that search over topology space by varying the number of hidden layers and hidden neurons through application of genetic operators (Lee and Kang 2007) and evaluation of the different architectures according to an objective function (Benardos and Vosniakos 2007).…”

Section: Output Layermentioning

confidence: 99%

Combining seasonal ARIMA models with computational intelligence techniques for time series forecasting

2012

View full text Add to dashboard Cite

Seasonal autoregressive integrated moving average (SARIMA) models form one of the most popular and widely used seasonal time series models over the past three decades. However, in several researches it has been argued that they have two basic limitations that detract from their popularity for seasonal time series forecasting tasks. SARIMA models assume that future values of a time series have a linear relationship with current and past values as well as with white noise; therefore, approximations by SARIMA models may not be adequate for complex nonlinear problems. In addition, SARIMA models require a large amount of historical data to produce desired results. However, in real situations, due to uncertainty resulting from the integral environment and rapid development of new technology, future situations must be forecasted using small data sets over a short span of time. Using hybrid models or combining several models has become a common practice to overcome the limitations of single models and improve forecasting accuracy. In this paper, a new hybrid model, which combines the seasonal autoregressive integrated moving average (SARIMA) and computational intelligence techniques such as artificial neural networks and fuzzy models for seasonal time series forecasting is proposed. In the proposed model, these two techniques are applied to simultaneously overcome the linear and data limitations of SARIMA models and yield more accurate results. Empirical results of forecasting two well-known seasonal time series data sets indicate that the proposed model exhibits effectively improved forecasting accuracy, so that it can be used as an appropriate seasonal time series model.

show abstract

“…For a multimodal/high order nonlinear function, a conventional formulation of (17) results in the difference between actual and approximate values being positive and/or negative due to the nature of the second order least squares method; consequently, this results in a constraint violation ( Fig. 3(b)).…”

Section: Approximation Of the Inequality Constraint Functionmentioning

confidence: 99%

“…Back-propagation neural network (BPN) architecture satisfies constraint feasibility in the context of genetic algorithm-based global approximate optimization [16][17][18]. BPN-based constraint-feasible meta-models are advantageous for highly nonlinear functions, but require greater amounts of computational costs than least square methods.…”

Section: Introductionmentioning

confidence: 99%