A hybrid SVM-PSO model for forecasting monthly streamflow

Ch, Sudheer; Rathinasamy, Maheswaran; Panigrahi, B. K.; Mathur, Shashi

doi:10.1007/s00521-013-1341-y

Cited by 142 publications

(67 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The MLMs included artificial neural network (ANN) [1,8], neuro-fuzzy (NF) [9], support vector machines (SVMs) (for regression, also called support vector regression (SVR)) [10,11], random forest (RF) [12], least squares support vector machine (LSSVM) (for regression, also called least squares support vector regression (LSSVR)) [13,14] and extreme learning machine (ELM) [15,16]. The MLMs are able to deal with nonlinearity and non-stationarity inherent in rainfall-runoff relationship and streamflow time series effectively.…”

Section: Introductionmentioning

confidence: 99%

“…First, to improve the model performance, the MLMs have been combined with statistical methods, including phase-space reconstruction [22,23], principal component analysis [24,25], fuzzy c-means clustering [7,22], k-means clustering [26,27], self-organizing map (SOM) [28,29] and bootstrap [30]. Second, the MLMs have been coupled with evolutionary optimization algorithms, including genetic algorithm (GA) [31,32], particle swarm optimization (PSO) [11,33], artificial bee colony [34], bat algorithm [35], and firefly algorithm [36]. The addressed algorithms were very helpful for efficient model learning and optimal parameter searching.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Models Coupled with Variational Mode Decomposition: A New Approach for Modeling Daily Rainfall-Runoff

2018

View full text Add to dashboard Cite

Accurate modeling for nonlinear and nonstationary rainfall-runoff processes is essential for performing hydrologic practices effectively. This paper proposes two hybrid machine learning models (MLMs) coupled with variational mode decomposition (VMD) to enhance the accuracy for daily rainfall-runoff modeling. These hybrid MLMs consist of VMD-based extreme learning machine (VMD-ELM) and VMD-based least squares support vector regression (VMD-LSSVR). The VMD is employed to decompose original input and target time series into sub-time series called intrinsic mode functions (IMFs). The ELM and LSSVR models are selected for developing daily rainfall-runoff models utilizing the IMFs as inputs. The performances of VMD-ELM and VMD-LSSVR models are evaluated utilizing efficiency and effectiveness indices. Their performances are also compared with those of VMD-based artificial neural network (VMD-ANN), discrete wavelet transform (DWT)-based MLMs (DWT-ELM, DWT-LSSVR, and DWT-ANN) and single MLMs (ELM, LSSVR, and ANN). As a result, the VMD-based MLMs provide better accuracy compared with the single MLMs and yield slightly better performance than the DWT-based MLMs. Among all models, the VMD-ELM and VMD-LSSVR models achieve the best performance in daily rainfall-runoff modeling with respect to efficiency and effectiveness. Therefore, the VMD-ELM and VMD-LSSVR models can be an alternative tool for reliable and accurate daily rainfall-runoff modeling.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine Learning Models Coupled with Variational Mode Decomposition: A New Approach for Modeling Daily Rainfall-Runoff

2018

View full text Add to dashboard Cite

show abstract

“…The PSO algorithm is derived from the migration mechanism of birds during foraging, which has advantages of fast convergence, efficient parallel computing and strong universality which is able to efficiently avoid local optimum [23,24]. Moreover, the iteration velocity of particle is influenced by the sum of current velocity, historical particle value, current global optimal value and random interferences, which avoids local optima to a large extent and improves search coverage and effectiveness.…”

Section: Pso Parameter Calibration Methodsmentioning

confidence: 99%

Comparative Analysis of ANN and SVM Models Combined with Wavelet Preprocess for Groundwater Depth Prediction

Zhou

Wang

Yang

2017

Water

115

View full text Add to dashboard Cite

Reliable prediction of groundwater depth fluctuations has been an important component in sustainable water resources management. In this study, a data-driven prediction model combining discrete wavelet transform (DWT) preprocess and support vector machine (SVM) was proposed for groundwater depth forecasting. Regular artificial neural networks (ANN), regular SVM, and wavelet preprocessed artificial neural networks (WANN) models were also developed for comparison. These methods were applied to the monthly groundwater depth records over a period of 37 years from ten wells in the Mengcheng County, China. Relative absolute error (RAE), Pearson correlation coefficient (r), root mean square error (RMSE), and Nash-Sutcliffe efficiency (NSE) were adopted for model evaluation. The results indicate that wavelet preprocess extremely improved the training and test performance of ANN and SVM models. The WSVM model provided the most precise and reliable groundwater depth prediction compared with ANN, SVM, and WSVM models. The criterion of RAE, r, RMSE, and NSE values for proposed WSVM model are 0.20, 0.97, 0.18 and 0.94, respectively. Comprehensive comparisons and discussion revealed that wavelet preprocess extremely improves the prediction precision and reliability for both SVM and ANN models. The prediction result of SVM model is superior to ANN model in generalization ability and precision. Nevertheless, the performance of WANN is superior to SVM model, which further validates the power of data preprocess in data-driven prediction models. Finally, the optimal model, WSVM, is discussed by comparing its subseries performances as well as model performance stability, revealing the efficiency and universality of WSVM model in data driven prediction field.

show abstract

“…Support vector machine is a new machine learning algorithm and it can find global optimization solution under the condition of less training samples and nonlinear and it has a good application prospect in the field of face recognition. The performance of SVM greatly depends on the selection of parameters (mainly the penalty parameter c and kernel function parameter g) [12] .…”

Section: The Svm Parameter Selection Based On Particle Swarm Optimizamentioning

confidence: 99%

Face Recognition Method Based on 2DLDA and SVM Optimated by PSO Algorithm

Zou¹,

Zhang²

2016

Proceedings of the 2016 6th International Conference on Mechatronics, Computer and Education Informationization (MCEI 2016)

View full text Add to dashboard Cite

Abstract. Concerning the "Small Samples Size" problem in LDA algorithm and reduce the effects to the SVM face recognition rate caused by random parameters set by human. An algorithm based on combination with the PSO algorithm which was originated form artificial life and evolutionary computation to SVM's parameters election and optimization, and Wavelet Transform , two-dimensional LDA(2DLDA) was proposed. Firstly, the original images were decomposed into high-frequency and low-frequency Components by Wavelet Transform (WT). The high-frequency components were ignored, while the low-frequency components can be obtained. Then, the liner discriminant features were extracted by two-dimensional LDA (2DLDA). Finally, we use the PSO algorithm to SVM's parameters election and optimization. Experimental results based on ORL face database show the validity of the algorithm this paper proposed for face recognition and it can reach the recognition rate of 98%.

show abstract

A hybrid SVM-PSO model for forecasting monthly streamflow

Cited by 142 publications

References 17 publications

Machine Learning Models Coupled with Variational Mode Decomposition: A New Approach for Modeling Daily Rainfall-Runoff

Machine Learning Models Coupled with Variational Mode Decomposition: A New Approach for Modeling Daily Rainfall-Runoff

Comparative Analysis of ANN and SVM Models Combined with Wavelet Preprocess for Groundwater Depth Prediction

Face Recognition Method Based on 2DLDA and SVM Optimated by PSO Algorithm

Contact Info

Product

Resources

About