Algorithm-based Support Vector Regression Research Articles

Magnetocaloric effect modeling of dysprosium-transition metal based intermetallic alloys for magnetic refrigeration application using hybrid genetic algorithm based support vector regression intelligent method.

Intermetallic alloy containing rare earth dysprosium ions with the associated unfilled 4f shell electrons and sub-lattice of 3d-transition metal, results into fascinating magnetic properties which are useful for green refrigeration technological application. Magnetocaloric effect remains the fundamental principle upon which magnetic refrigeration technology is based while this cooling technology has advantages of cost effectiveness, high efficiency and environmental friendliness as compared with the existing conventional gas compression systems. Maximum magnetic entropy change (which controls the hugeness of magnetocaloric effect) of intermetallic alloy Dy-T-X (where T = transition metal and X = any other metal or nonmetal) is modeled in this work using hybrid genetic algorithm based support vector regression (GSVR) computational intelligent method with applied magnetic field, ionic concentration and ionic radii descriptors. The developed GSVR-G model with kernel Gaussian function outperforms GSVR-P model with polynomial function with improvement of 85.23%, 78.82% and 78.67% on the basis of the computed correlation coefficient (CC), mean absolute error (MAE) and root mean square error (RMSE) on testing sample, respectively. The developed model further investigates the influence of applied external magnetic field on magnetocaloric effect of DyCuAl intermetallic alloy. The developed models in this work circumvent experimental challenges of magnetocaloric effect determination while the recorded precision of the developed model further opens doors for possible exploration of these intermetallic compounds for addressing environmental challenges associated with the present system of cooling.

Bayesian optimization algorithm based support vector regression analysis for estimation of resilient modulus of crushed rock materials for pavement design

The precise determination of the resilient modulus (MR) of the base and sub-base materials is a major preoccupation and a key criterion in the flexible pavement design process. The experimental determination of MR implies a challenging process which requires usually very difficult test procedures and extreme precautions and manpower. This is why soft computing techniques are increasingly popular and of growing importance. Many prediction techniques based primarily on linear and non-linear regression could not provide flexible use and consistent prediction of MR for practical engineering. This article introduces a hybrid of the Bayesian optimization algorithm (BOA) and support vector regression (SVR) as a new modelling tool for the MR prediction of crushed stone materials used as base and sub-base layers for pavement design. For this purpose, an experimental database was utilized to generate the hybrid BOA-SVR model of indirect estimation of the resilient modulus based on material type, basic engineering characteristics and loading conditions. The database consists of 260 experimental datasets obtained from repeated loading triaxial tests performed by the laboratory of the Central Transportation Agency located in Algiers, Algeria. To develop the model, all hyperparameters were optimised using the BOA technique. It was found that the average, median, standard deviation, minimum, maximum and interquartile range of the expected values of the developed hybrid model are very close to the experimental results. Results revealed that the hybrid BOA-SVR model predict the MR of the crushed stone materials with a coefficient of determination of 99.91% and root mean squared error of 3.55. Comparisons with traditional and other Artificial intelligence models showed that BOASVR hybrid model predictions are more accurate and robust than those of other models.

Modeling the band gap of spinel nano-ferrite material using a genetic algorithm based support vector regression computational method

Abstract Spinel nano-ferrite compounds have attracted significant interest in industrial, scientific and technological communities as a result of their promising and unique features especially at nano-scale range. The present and future potentials of spinel nano-ferrite materials cut across several applications such as biotechnology, magnetic storage, sensors, magnetic hyperthermia, microwave absorbance and photo-catalysis. Enhancing the photocatalytic application of spinel nano-ferrite materials involves accommodation of foreign materials into the parent compound as well as appropriate fabrication technique which respectively alter the crystal structure and nano-size of the spinel nano-ferrite materials. This work implements the crystal lattice distortion and the size of nano-particles to develop, for the first time, hybridization of a support vector regression algorithm with a genetic algorithm for estimating the energy gap of doped spinel nano-ferrite materials. The developed hybrid genetic algorithm based support vector regression model was built using two hundred different spinel nano-ferrite materials doped with varieties of materials and synthesized through various methods. The developed genetic algorithm based support vector regression model that is characterized by low root mean square error and mean squared error of 0.3075 eV and 0.095 eV respectively, was further validated using eighteen different spinel nano-ferrite materials and the estimated energy gaps agree excellently with the experimental values. The influence of magnesium, aluminum and lanthanum on the band gap of spinel ferrite nanoparticles was investigated and studied using the developed genetic algorithm based support vector regression model. The developed model in this work ultimately provides a quick, accurate and precise method of characterizing the band gap of spinel nano-ferrite materials while circumventing experimental stress with conservation of appreciable time and other valuable resources.

Specific Surface Area Characterization of Spinel Ferrite Nanostructure Based Compounds for Photocatalysis and Other Applications Using Extreme Learning Machine Method

Nanocrystalline spinel ferrite based compounds are technological driven materials with interesting potentials in photocatalysis for renewable energy generation, gas sensing for pollution control, magnetic drug delivery, rod antennas, storage media (high density) and supercapacitive materials, among others. Specific surface area of spinel ferrite based compounds contributes immensely to the application of this semiconductor in industrial domains. Experimental determination of specific surface area is laborious and costly and consumes appreciable time. Compositional substitutions in crystal structure effectively improve physical properties and enhance specific surface area through alteration of moment distribution between tetrahedral oxygen sites and octahedral coordination. With the aid of distorted lattice parameters due to compositional substitution and the spinel ferrite nanocrystallite size as model descriptors, this present work models the specific surface area of spinel ferrite nanomaterial through extreme learning machine (ELM) based intelligent modeling method. The developed sigmoid activation function-based ELM (S-ELM) model shows superior performance over genetic algorithm based support vector regression (GBSVR) and stepwise regression (STWR) models existing in the literature with performance improvement of 61.31% and 70.01%, respectively, using root mean square error performance metric. The significances of cobalt and lanthanum compositional substitution on the specific surface area of spinel ferrite nanomaterials were investigated using S-ELM model. Ease of implementation of S-ELM model as compared with the existing GBSVR model, coupled with the demonstrated improved performance and persistent closeness of its predictions with the experimental values, would be highly meritorious for quick and precise characterization of specific surface area of spinel ferrite nanomaterials for various desired applications.

Modeling optical energy gap of strontium titanate multifunctional semiconductor using stepwise regression and genetic algorithm based support vector regression

Strontium titanate semiconductor is multi-functional metallic oxide with perovskite structure and wide range of applications in oxygen gas sensors (in storage batteries), superconductivity, ferro-electricity, dielectric constant materials, dye-sensitized solar cells photo-electrodes, optoelectronics applications and photocatalysis. The wide band gap of strontium titanate metal oxide constrains its response to ultraviolent light with light harvesting capacity of 5% for incoming solar energy in generating photocatalytic activity. Anions and cations incorporation into the parent strontium titanate compound strongly break the semiconductor symmetry and ultimately influence the energy gap with stretches as well as distortions in perovskite structural architecture. This work develops genetic algorithm based support vector regression (GABSVR) hybrid model and stepwise regression algorithm (SRA) for modeling the energy gap of distorted strontium titanate semiconductor using structural lattice constants and the size of its nano-particles as model descriptors. The developed GABSVR model performs better than SRA model with performance improvement of 62.98%, 79.12% and 81.05% using coefficient of correlation (CC), mean absolute error (MAE) and root mean square error (RMAE) metrics, respectively. The developed model investigates the influence of preparation method, silver dopants, nitrogen dopants and sulfur incorporation on energy gap of strontium titanate photocatalytic activity. The developed GABSVR model was further validated externally for determining the significance of cobalt dopants on the activity of strontium titanate and the obtained energy gaps agree well with the measured values. High level of precision demonstrated by the developed hybrid model is of enormous significance for strengthening light harvesting capacity of the semiconductor for optoelectronics and photocatalysis applications.

Bayesian optimization algorithm based support vector regression analysis for estimation of shear capacity of FRP reinforced concrete members

The use of fiber-reinforced polymer (FRP) rebars in lieu of steel rebars has led to some deviations in the shear behavior of concrete members. Several methods have been proposed to forecast the shear capacity of such members. Nonetheless, there are differences in the methods of considering the various parameters affecting shear capacity, and some of them provide widely scattered and conservative results. This paper presents a hybrid of the Bayesian optimization algorithm (BOA) and support vector regression (SVR) as a novel modeling tool for the prediction of the shear capacity of FRP-reinforced members with no stirrups. For this purpose, a large dataset of simply supported beams and unidirectional slabs reinforced with FRP were utilized. The model performance was assessed using several statistical performance indicators and compared with the Japan Society of Civil Engineers (JSCE), British Institution of Structural Engineers (BISE), Canadian Standard Association (CSA), and American Concrete Institute (ACI) design codes and guidelines, as well as some other artificial intelligence (AI) models. For development of the model, all the hyperparameters, i.e., kernel function type, epsilon, box constraint, and kernel scale, were optimized using the BOA technique. The k-fold cross validation approach was utilized to avoid overfitting of the model. It was found that the mean, median, standard deviation, minimum, maximum, and interquartile range of the developed hybrid model predictions are very close to the experimental results. The predicted results overlap the experimental data with a coefficient of determination of 95.5%. The plot of relative deviations and residual plots are scattered around the zero reference line with low deviation, which indicates that the model is reliable and valid. The error terms (e.g., mean absolute error, root mean square error) obtained for all specimens were 4.85 and 11.03, which are very low values. The correlation coefficient (R) and fractional bias (FB) were found to be 0.977 and 0.0033, which are very close to 1 and 0, respectively, thus implying a reliable prediction. The comparative investigations with other codes and guidelines show that the hybrid BOA–SVR model predictions are more accurate and robust than those of the other models.

Estimation of minimum ignition energy of explosive chemicals using gravitational search algorithm based support vector regression

Adequate knowledge of minimum ignition energy (MIE) of a flammable chemical compound plays a significant role while handling and characterizing the hazardous materials and further ensures reliable ignition of fuel-air mixtures in many engines. Despite the significances of this parameter (MIE), its experimental determination is very dangerous, expensive and might be time consuming. The challenges associated with the experimental determination of minimum ignition energy are addressed in this present work through hybridization of gravitational search algorithm (GSA) with support vector regression (SVR) for estimating MIE using relatively few descriptors which include the number of carbon and hydrogen atoms as well as molecular weight of the compound. Novelties of this approach as compared with existing methods include (i) hybridization of GSA with SVR for modeling MIE for the first time, (ii) utilization of relatively few (three) descriptors and (iii) the ease with which the descriptors can be assessed. On the basis of root mean square error, the developed hybrid GSA-SVR shows superior performance as compared with the existing Beibei Wang et al. model with performance improvement of 24.03%. The accuracy of the proposed hybrid GSA-SVR model coupled with the ease of its implementation would definitely ensure quick estimation of MIE of compounds, prevent accidental explosion of hazardous chemicals in industry and enhance aviation safety.

Taiwanese export trade forecasting using firefly algorithm based K-means algorithm and SVR with wavelet transform

In order to develop a prediction system for export trade value, this study proposes a three-stage forecasting model which integrates wavelet transform, firefly algorithm-based K-means algorithms and firefly algorithm-based support vector regression (SVR). First, wavelet transform is utilized to reduce the noise in data preprocessing. Then, the firefly algorithm-based K-means algorithm is employed for cluster analysis. Finally, a forecasting model is built for each cluster individually. For evaluation, this study compares methods with and without clustering. In addition, both non-wavelet transform and wavelet transform for data preprocessing are investigated. The experimental results indicate that the forecasting algorithm with both wavelet transform and clustering has better performance. Besides, firefly algorithm-based SVR outperforms the other algorithms.

Forecasting monthly groundwater level fluctuations in coastal aquifers using hybrid Wavelet packet–Support vector regression

AbstractThis research demonstrates the state-of-the-art capability of Wavelet packet analysis in improving the forecasting efficiency of Support vector regression (SVR) through the development of a novel hybrid Wavelet packet–Support vector regression (WP–SVR) model for forecasting monthly groundwater level fluctuations observed in three shallow unconfined coastal aquifers. The Sequential Minimal Optimization Algorithm-based SVR model is also employed for comparative study with WP–SVR model. The input variables used for modeling were monthly time series of total rainfall, average temperature, mean tide level, and past groundwater level observations recorded during the period 1996–2006 at three observation wells located near Mangalore, India. The Radial Basis function is employed as a kernel function during SVR modeling. Model parameters are calibrated using the first seven years of data, and the remaining three years data are used for model validation using various input combinations. The performance of b...

Support vector regression with chaos-based firefly algorithm for stock market price forecasting

Due to the inherent non-linearity and non-stationary characteristics of financial stock market price time series, conventional modeling techniques such as the Box–Jenkins autoregressive integrated moving average (ARIMA) are not adequate for stock market price forecasting. In this paper, a forecasting model based on chaotic mapping, firefly algorithm, and support vector regression (SVR) is proposed to predict stock market price. The forecasting model has three stages. In the first stage, a delay coordinate embedding method is used to reconstruct unseen phase space dynamics. In the second stage, a chaotic firefly algorithm is employed to optimize SVR hyperparameters. Finally in the third stage, the optimized SVR is used to forecast stock market price. The significance of the proposed algorithm is 3-fold. First, it integrates both chaos theory and the firefly algorithm to optimize SVR hyperparameters, whereas previous studies employ a genetic algorithm (GA) to optimize these parameters. Second, it uses a delay coordinate embedding method to reconstruct phase space dynamics. Third, it has high prediction accuracy due to its implementation of structural risk minimization (SRM). To show the applicability and superiority of the proposed algorithm, we selected the three most challenging stock market time series data from NASDAQ historical quotes, namely Intel, National Bank shares and Microsoft daily closed (last) stock price, and applied the proposed algorithm to these data. Compared with genetic algorithm-based SVR (SVR-GA), chaotic genetic algorithm-based SVR (SVR-CGA), firefly-based SVR (SVR-FA), artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFIS), the proposed model performs best based on two error measures, namely mean squared error (MSE) and mean absolute percent error (MAPE).

Grid Resource Prediction based on Support Vector Regression and Simulated Annealing Algorithms

Accurate grid resources prediction is crucial for a grid scheduler. In this study, support vector regression (SVR), which is a novel and effective regression algorithm, is applied to grid resources prediction. In order to build an effective SVR model, SVR’s parameters must be selected carefully. Therefore, we develop a simulated annealing algorithm-based SVR (SA-SVR) model that can automatically determine the optimal parameters of SVR with higher predictive accuracy and generalization ability simultaneously. The performance of the hybrid model (SA-SVR), the back-propagation neural network (BPNN) and traditional SVR model whose parameters are obtained by trial-and-error procedure (T-SVR) have been compared with benchmark data set. Experimental results demonstrate that SA-SVR model works better than the other two models.