Local output gamma feedback neural network

Uluyol, Önder; Ragheb, Magdi; Ray, Sylvian R.

doi:10.1109/ijcnn.1998.682288

Cited by 11 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Obviously, long-term prediction of solar activity is of great importance. The numerical prediction techniques including the most powerful neural and neurofuzzy models with appropriate learning methodologies [26,28,29], however, can perform the most accurate 1 year ahead predictions, cannot be used in long-term predictions. Even the error index of LLNF model, which has shown very little 1 year ahead prediction errors for the sunspot number time series [29], increases undesirably with prediction horizon.…”

Section: Ikeda Map Time Series Predictionmentioning

confidence: 99%

“…A good measure of activity level is sunspot number, which has been saved since the early eighteenth century. The sunspot number time series has been used as the test bench of many proposed predictors [26,27], but today solar activity forecasting is more than a matter of scientific curiosity. Not only the solar activity level has long-term effects on earth and satellites, but also the associated events, coronal mass ejections and solar flares are the origin of shocks in solar wind, which causes geomagnetic storms and sub-storms and has the potential to harm satellites.…”

Section: Ikeda Map Time Series Predictionmentioning

confidence: 99%

“…An excellent example is long-term solar activity forecasting. It seems that the physical precursor [16][17][18] and solar dynamo techniques [19][20][21][22][23], based on simple linear and nonlinear empirical studies, have superseded the numerical and black box techniques [24][25][26][27][28][29].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Extracting the main patterns of natural time series for long-term neurofuzzy prediction

Gholipour

Lucas

Araabi

et al. 2006

Neural Comput & Applic

View full text Add to dashboard Cite

A combination of singular spectrum analysis and locally linear neurofuzzy modeling technique is proposed to make accurate long-term prediction of natural phenomena. The principal components (PCs) obtained from spectral analysis have narrow band frequency spectra and definite linear or nonlinear trends and periodic patterns; hence they are predictable in large prediction horizon. The incremental learning algorithm initiates a model for each of the components as an optimal linear least squares estimation, and adds the nonlinear neurons if they help to reduce error indices over training and validation sets. Therefore, the algorithm automatically constructs the best linear or nonlinear model for each of the PCs to achieve maximum generalization, and the long-term prediction of the original time series is obtained by recombining the predicted components. The proposed method has been primarily tested in long-term prediction of some wellknown nonlinear time series obtained from MackeyGlass, Lorenz, and Ikeda map chaotic systems, and the results have been compared to the predictions made by multi-layered perceptron (MLP) and radial basis functions (RBF) networks. As a real world case study, the method has been applied to the long-term prediction of solar activity where the results have been compared to the long-term predictions of physical precursor and solar dynamo methods.

show abstract

Section: Ikeda Map Time Series Predictionmentioning

confidence: 99%

Section: Ikeda Map Time Series Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Extracting the main patterns of natural time series for long-term neurofuzzy prediction

Gholipour

Lucas

Araabi

et al. 2006

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…There is always a trade off between the accuracy of prediction in total test set and the accuracy of highly valued regions. This argument motivates to the search for more accurate predictions using intelligent methods (Weigend et al 1990;Uluyol et al 1998;Chen et al 1999). In the last decades, the psychological aspects of human as an intelligent existence and with sentiments, has been probed.…”

Section: Introductionmentioning

confidence: 97%

Learning based brain emotional intelligence as a new aspect for development of an alarm system

2007

View full text Add to dashboard Cite

The multi criteria and purposeful prediction approach has been introduced and is implemented by the fast and efficient behavioral based brain emotional learning method. On the other side, the emotional learning from brain model has shown good performance and is characterized by high generalization property. New approach is developed to deal with low computational and memory resources and can be used with the largest available data sets. The scope of paper is to reveal the advantages of emotional learning interpretations of brain as a purposeful forecasting system designed to warning; and to make a fair comparison between the successful neural (MLP) and neurofuzzy (ANFIS) approaches in their best structures and according to prediction accuracy, generalization, and computational complexity. The auroral electrojet (AE) index are used as practical examples of chaotic time series and introduced method used to make predictions and warning of geomagnetic disturbances and geomagnetic storms based on AE index.

show abstract

“…Given the achievements in the field of chaotic systems, several such methods can be used in the prediction of solar activity indices, namely polynomial function approximation, reconstructions using Lyapunov exponents, and the detection of periodicity in chaotic time series (Vautard and Ghil, 1989). Of these methods, the physical precursor (Brown, 1992;Thompson, 1993;Joselyn et al, 1997) and solar dynamo techniques (Schatten et al, 1978(Schatten et al, , 1996Schatten and Sofia, 1987;Schatten and Pesnell, 1993;Sofia et al, 1998), which are based on simple linear and nonlinear empirical studies, seem to have superseded the numerical and black box techniques in terms of user preference (Tong and Lim, 1980;Weigend et al, 1992;Tong, 1996;Uluyol et al, 1998;Lucas et al, 2003;Gholipour et al, 2003). In the black box modeling technique, in comparison with the white box modeling technique (both of which are fully derived by applying principles of physics, chemistry, biology, economy, etc.…”

Section: Introductionmentioning

confidence: 99%

Long-term prediction of solar and geomagnetic activity daily time series using singular spectrum analysis and fuzzy descriptor models

et al. 2009

View full text Add to dashboard Cite

Of the various conditions that affect space weather, Sun-driven phenomena are the most dominant. Cyclic solar activity has a significant effect on the Earth, its climate, satellites, and space missions. In recent years, space weather hazards have become a major area of investigation, especially due to the advent of satellite technology. As such, the design of reliable alerting and warning systems is of utmost importance, and international collaboration is needed to develop accurate short-term and long-term prediction methodologies. Several methods have been proposed and implemented for the prediction of solar and geomagnetic activity indices, but problems in predicting the exact time and magnitude of such catastrophic events still remain. There are, however, descriptor systems that describe a wider class of systems, including physical models and non-dynamic constraints. It is well known that the descriptor system is much tighter than the state-space expression for representing real independent parametric perturbations. In addition, the fuzzy descriptor models as a generalization of the locally linear neurofuzzy models are general forms that can be trained by constructive intuitive learning algorithms. Here, we propose a combined model based on fuzzy descriptor models and singular spectrum analysis (SSA) (FD/SSA) to forecast a number of geomagnetic activity indices in a manner that optimizes a fuzzy descriptor model for each of the principal components obtained from singular spectrum analysis and recombines the predicted values so as to transform the geomagnetic activity time series into natural chaotic phenomena. The method has been applied to predict two solar and geomagnetic activity indices: geomagnetic aa and solar wind speed (SWS) of the solar wind index. The results demonstrate the higher power of the proposed method-compared to other methods-for predicting solar activity.

show abstract

Local output gamma feedback neural network

Cited by 11 publications

References 14 publications

Extracting the main patterns of natural time series for long-term neurofuzzy prediction

Extracting the main patterns of natural time series for long-term neurofuzzy prediction

Learning based brain emotional intelligence as a new aspect for development of an alarm system

Long-term prediction of solar and geomagnetic activity daily time series using singular spectrum analysis and fuzzy descriptor models

Contact Info

Product

Resources

About