Generalization performance of support vector machines and neural networks in runoff modeling

Behzad, Mohsen; Asghari, Keyvan; Eazi, Morteza; Palhang, Maziar

doi:10.1016/j.eswa.2008.09.053

Cited by 229 publications

(91 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, Behzad et al (2009) reported that SVMs are able to generalize better than ANNs, though there is still some danger of under-or overfitting to the training data (Han et al, 2007) (true to some extent of virtually any model). The SVMs are also able to learn from a much smaller training set than ANNs, and the global minimum of the linear optimization is easily obtainable, whereas there is a risk of becoming trapped in a local minimum of the non-linear ANN objective function (Behzad et al, 2009). …”

Section: Approaches To Hydrological Modellingmentioning

confidence: 99%

“…Han et al (2007) compared the RBF and linear kernel functions and found that even within the same catchment, the ideal function can change under different circumstances. Despite being a relatively new approach to hydrological modelling, SVMs and SVRs have been applied to many of the same problems as ANNs, including rainfallrunoff modelling for water resources planning and flood forecasting at various lead-times (Asefa et al, 2006;Han et al, 2007;Behzad et al, 2009;Rasouli et al, 2012), hydraulic modelling (Liong and Sivapragasam, 2002) and downscaling of GCM output (Tripathi et al, 2006). Genetic Programming (GP; Koza, 1992) is another soft computing approach to non-linear modelling and is based on Darwin's theory of evolution by natural selection.…”

Section: Approaches To Hydrological Modellingmentioning

confidence: 99%

See 1 more Smart Citation

Streamflow Modelling: A Primer on Applications, Approaches and Challenges

2012

View full text Add to dashboard Cite

This article examines the current practice of streamflow modelling, a field under development for over a century. A sample of the wide range of assessment and planning applications of streamflow models is presented. The diversity in the use of these models is mirrored in the diversity of model complexity, and modelling approaches ranging from empirical to physically based and from lumped to fully distributed are described with examples. Predictions derived from hydrological models are subject to many sources of error; these are discussed along with methods for error minimization or anticipation. Model error is generally quantified using an ensemble of forecasts meant to sample the range of predictive uncertainty. This ensemble can be used to generate reliable probabilistic forecasts of hydrological quantities if all sources of error are accounted for. To date, applications of ensemble methods in streamflow forecasting have typically focused on only one or two error sources. A challenge will be to develop ensemble streamflow forecasts that sample a wider range of predictive uncertainty.

show abstract

Section: Approaches To Hydrological Modellingmentioning

confidence: 99%

Section: Approaches To Hydrological Modellingmentioning

confidence: 99%

Streamflow Modelling: A Primer on Applications, Approaches and Challenges

2012

View full text Add to dashboard Cite

show abstract

“…The basic principle of learning in SVM is that it searches for an optimal hyperplane which satisfies the request of classification, then uses an algorithm to make the margin of the separation beside the optimal hyperplane maximum while ensuring the accuracy of correct classification (Yeh et al 2010). It produces a binary classifier, so-called optimal separating hyperplanes, and results in a uniquely global optimum, high generalization performance, and does not suffer from a local optima problem (Behzad et al, 2009). The principle of SVM can be described as follows.…”

Section: Support Vector Machinesmentioning

confidence: 99%

“…Since the successfulness of SVM depends on the choice of kernel function K and hyper parameters, a cross-validation procedure should be performed for adjusting those parameters (Min and Lee, 2005;Behzad et al, 2009). Linear, polynomial, RBF, and exponential kernels were used in our experiments, where gamma coefficient for polynomial and RBF kernel was 0.0625, degree was 3, coefficient varied from 0 to 0.1, c=10.…”

Section: Support Vector Machinesmentioning

confidence: 99%

A Comparison of Machine Learning Methods in a High-Dimensional Classification Problem

Zekić–Sušac

Pfeifer

Šarlija

2014

Business Systems Research Journal

View full text Add to dashboard Cite

Background: Large-dimensional data modelling often relies on variable reduction methods in the pre-processing and in the post-processing stage. However, such a reduction usually provides less information and yields a lower accuracy of the model. Objectives: The aim of this paper is to assess the high-dimensional classification problem of recognizing entrepreneurial intentions of students by machine learning methods. Methods/Approach: Four methods were tested: artificial neural networks, CART classification trees, support vector machines, and k-nearest neighbour on the same dataset in order to compare their efficiency in the sense of classification accuracy. The performance of each method was compared on ten subsamples in a 10-fold cross-validation procedure in order to assess computing sensitivity and specificity of each model. Results: The artificial neural network model based on multilayer perceptron yielded a higher classification rate than the models produced by other methods. The pairwise t-test showed a statistical significance between the artificial neural network and the k-nearest neighbour model, while the difference among other methods was not statistically significant. Conclusions: Tested machine learning methods are able to learn fast and achieve high classification accuracy. However, further advancement can be assured by testing a few additional methodological refinements in machine learning methods.

show abstract

“…Nevertheless, variations will appear in the accuracy of a pattern recognition algorithm when the training sample data are changed [11,12]. Therefore, the stability of the classification algorithms for different data sample sets has become an obstacle for the widespread application of PD UHF on-line monitoring for power transformers.…”

Section: Introductionmentioning

confidence: 99%

Improved Bagging Algorithm for Pattern Recognition in UHF Signals of Partial Discharges

Jiang

Yao

et al. 2011

Energies

View full text Add to dashboard Cite

This paper presents an Improved Bagging Algorithm (IBA) to recognize ultra-high-frequency (UHF) signals of partial discharges (PDs). This approach establishes the sample information entropy for each sample and the re-sampling process of the traditional Bagging algorithm is optimized. Four typical discharge models were designed in the laboratory to simulate the internal insulation faults of power transformers. The optimized third order Peano fractal antenna was applied to capture the PD UHF signals. Multi-scale fractal dimensions as well as energy parameters extracted from the decomposed signals by wavelet packet transform were used as the characteristic parameters for pattern recognition. In order to verify the effectiveness of the proposed algorithm, the back propagation neural network (BPNN) and the support vector machine (SVM) based on the IBA were adopted in this paper to carry out the pattern recognition for PD UHF signals. Experimental results show that the proposed approach of IBA can effectively enhance the generalization capability and also improve the accuracy of the recognition for PD UHF signals.

show abstract

Generalization performance of support vector machines and neural networks in runoff modeling

Cited by 229 publications

References 18 publications

Streamflow Modelling: A Primer on Applications, Approaches and Challenges

Streamflow Modelling: A Primer on Applications, Approaches and Challenges

A Comparison of Machine Learning Methods in a High-Dimensional Classification Problem

Improved Bagging Algorithm for Pattern Recognition in UHF Signals of Partial Discharges

Contact Info

Product

Resources

About