Hybrid Support Vector Regression Research Articles

Hybrid and individual least square support vector regression methods for estimating the optimal moisture content of stabilized soil

Hybrid and individual least square support vector regression methods for estimating the optimal moisture content of stabilized soil

Hybrid genetic algorithm and support vector regression for predicting the shear capacity of recycled aggregate concrete beam

Hybrid genetic algorithm and support vector regression for predicting the shear capacity of recycled aggregate concrete beam

A new experimental design to predict carbon dioxide emissions using Boruta feature selection and hybrid support vector regression techniques

A new experimental design to predict carbon dioxide emissions using Boruta feature selection and hybrid support vector regression techniques

A new experimental design to predict carbon dioxide emissions using Boruta feature selection and hybrid support vector regression techniques

A new experimental design to predict carbon dioxide emissions using Boruta feature selection and hybrid support vector regression techniques

Support vector regression optimized by black widow optimization algorithm combining with feature selection by MARS for mining blast vibration prediction

Ground vibration induced by mine blasting is the most significant adverse effect on nearby residents and surroundings. Accurate prediction of blasting vibration using limited monitor data is a viable option to control ground vibration. This study proposed a novel integration modeling method based on multivariate adaptive regression splines (MARS), support vector regression (SVR) and black widow optimization algorithm (BWOA) for predicting the peak particle velocity (PPV) and frequency. Feature selection was implemented first using the MARS. Subsequently, the variables selected by the MARS were used as the input to build the SVR model. To increase the performance of the SVR model, we introduced the BWOA to tune the hyperparameters of the SVR model. Moreover, two hybrid SVR models also were developed to compare with the hybrid MARS-BWOA-SVR model. The results indicate that the prediction accuracy of the three hybrid models is superior to the standalone SVR model. Among the three hybrid models, the MARS-BWOA-SVR model yields the highest prediction accuracy. The hybrid MARS-BWOA-SVR model not only outperforms other SVR models but also discerns the relative importance of the input variables. There are four main variables with higher relative importance, namely, distance, maximum charge per delay, integrity coefficient and pre-split penetration ratio. The results demonstrate that the hybrid MARS-BWOA-SVR model is a promising tool for blasting vibration prediction.

Application of data-driven models to predict the dimensions of flow separation zone.

In this research, the effect of a submerged multiple-vane system on the dimensions of flow separation zone (DFSZ) is assessed via 192 measured datasets. The vanes' shape comprised two segments, curved and flat plates which are located in the connection of main channel to the lateral intake channel with an angle of 55°. In this direction, a butterfly's array for the vanes' arrangement along with different main controlling factors such as distances of vanes along the flow (δl), degree of curvature (β), and angles of attack to the local primary flow direction (θ) is utilized. Through capturing photos and utilizing AutoCAD and SURFER software, maximum relative length and width are calculated. Based on the experimental measurements, maximum percentage reduction of DFSZ, in comparison with the controlled test (without submerged vanes), is obtained with θ = 30°, β = 34°, and δl = 10cm with value of 78 and 76%, respectively. Moreover, several data-driven models, namely, gene expression programming (GEP), support vector regression (SVR), and a robust hybrid SVR with an ant colony optimization algorithm (ACO) (i.e., hybrid SVR-ACO model), are developed in order to predict DFSZ via the operative dimensionless variables realized by Spearman's rho and Pearson's coefficient processes. In accordance with the statistical metrics, model grading process, scatter plot, and the hybrid SVR(RBF)-ACO model are preferred as the best and most precise model to predict maximum relative length and width with a total grade (TG) of 6.75 and 5.8, respectively. The generated algebraic formula for DFSZ under the optimal scenario of GEP is equated with the corresponding measured ones and the results are within 0-10%.

Biohydrogen from food waste: Modeling and estimation by machine learning based super learner approach

This study demonstrated the application of a hybrid Bayesian algorithm (BA) and support vector regression (SVR) as a potential super-learner tool (BA-SVR) to predict biohydrogen production from food waste-originated feedstocks. The novelty of the present approach, as compared to the existing response surface methodology (RSM), includes (i) hybridization of BA with SVR for modeling of biohydrogen production and minimization of biomethane formation, (ii) performance evaluation and comparison of the developed BA-SVR models with the existing RSM models based on the several indicators such as coefficient of determination (R2), relative error (RE), mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE), (iii) analysis of the robustness of the model and (iv) testing generalization ability. The calculated values of these indicators suggested that the proposed super leaner models demonstrated better performance predicting the biohydrogen and biomethane (products) responses than those using the existing RSM models - as reported in Rafieenia et al. 2019 [45]. The estimated low errors for biohydrogen: MAE = 0.5919, RMSE = 0.592, MAPE = 11.1387; for biomethane: MAE = 0.2681, RMSE = 0.2688, MAPE = 0.3708, signifie the reliable model predictions. The BA-SVR model also provided high adj R2 (>0.99 for both biohydrogen and biomethane), indicating an excellent fitting of the model. Concerning the MAPE, the proposed BA-SVR models for both the biohydrogen and biomethane responses showed superior performances (as compared to the RSM models) with a performance enhancement of 64.16% and 98.81%, respectively.

New hybrid support vector regression methods for predicting fresh and hardened properties of self-compacting concrete

Most of the published literature on concrete containing fly ash was limited to predicting the hardened properties of concrete. It is understood that exist so restricted studies focusing on forecasting both hardened and fresh features of self-compacting concrete (SCC). Hence, it is goaled for developing models for predicting the fresh and hardened properties of SCC by the support vector regression method (SVR). This study aims to specify SVR method key parameters using Ant lion optimization (ALO) and Biogeography-based optimization (BBO) algorithms. The considered properties of SCC in the fresh phase are the L-box test, V-funnel test, slump flow, and in the hardened phase is CS. Results demonstrate powerful potential in the learning section for all considered properties as well as approximating in the testing phase. It can be seen that the proposed models have R2 incredible value in the learning and testing phase. It means that the correlation between observed and predicted properties of SCC from hybrid models is acceptable so that it represents high accuracy in the training and approximating process. All in all, in most of the cases, the SVR model developed by ALO outperforms BBO-SVR, which depicts the capability of the ALO algorithm for determining the optimal parameters of the considered method.

Capillary water absorption values estimation of building stones by ensembled and hybrid SVR models

The absorption of capillary water is one of the most crucial factors in the flow of groundwater in rocks (CWA). Although meticulous experimental studies are needed to determine a rock’s CWA, predictive techniques might cut down on the expense and effort. There are various data mining methods for this purpose, but the considered algorithms in this study were not proposed so far for predicting the CWA. Different rock samples were taken for this purpose from various locations, yielding diverse rocks. For the prediction procedures, four support vector regression (SVR) models were created: a traditional SVR, two ensembled models, and a hybrid SVR model using the whale optimization technique (WOA - SVR). Results show that all models have acceptable performance in predicting the CWA with R2 larger than 0.797 and 0.806 for the training and testing data, respectively, representing the acceptable correlation between observed and predicted values. Regarding developed models, the conventional SVR model has the worst performance of all models. All statistical evaluation criteria were improved by assembling models, which present the ability of additive regression and bagging predictions in improving prediction processes. The hybrid WOA - SVR model has the best performance considering all indices. This hybrid model could also gain the lowest values of error indices between all SVR models, which leads to outperforming the WOA - SVR model compared to other methods.

Enhancement Support Vector Regression Using Black Widow Optimization for Predicting Foreign Exchange Rate

Prediction of foreign exchange rates is one of the time series problems that have fluctuating value movements. There are several algorithms that can make predictive models for this problem, one of which is Support Vector Regression (SVR). In this study, foreign exchange rate predictions were made using Hybrid SVR and Black Widow Optimization (BWO). This is done with the aim of improving the performance of the SVR in order to produce a better predictive model for the EUR/USD foreign exchange rate data in 2020. The results of the proposed algorithm get better performance in terms of R2, MSE, RMSE, MAE, and MAPE compared to SVR.

Enhancement Support Vector Regression Using Black Widow Optimization for Predicting Foreign Exchange Rate

Prediction of foreign exchange rates is one of the time series problems that have fluctuating value movements. There are several algorithms that can make predictive models for this problem, one of which is Support Vector Regression (SVR). In this study, foreign exchange rate predictions were made using Hybrid SVR and Black Widow Optimization (BWO). This is done with the aim of improving the performance of the SVR in order to produce a better predictive model for the EUR/USD foreign exchange rate data in 2020. The results of the proposed algorithm get better performance in terms of R2, MSE, RMSE, MAE, and MAPE compared to SVR.

Support vector regression-bald eagle search optimizer-based hybrid approach for short-term wind power forecasting

AbstractWind power forecasting deals with the prediction of the expected generation of wind farms in the next few minutes, hours, or days. The application of machine learning techniques in wind power forecasting has become of great interest due to their superior capability to perform regression, classification, and clustering. Support vector regression (SVR) is a powerful and suitable forecasting tool that has been successfully used for wind power forecasting. However, the performance of the SVR model is extremely dependent on the optimal selection of its hyper-parameters. In this paper, a novel forecast model based on hybrid SVR and bald eagle search (BES) is proposed for short-term wind power forecasting. In the proposed model, the BES algorithm, which is characterized by a few adjustable parameters, a simplified search mechanism, and accurate results, is used to enhance the accuracy of the forecasted output by optimizing the hyper-parameters of the SVR model. To evaluate the performance of the developed wind power forecaster, a case study has been conducted on real wind power data from Sotavento Galicia in Spain. The developed model is compared to other forecasting techniques such as decision tree (DT), random forest (RF), traditional SVR, hybrid SVR, and gray wolf optimization algorithm (SVR–GWO) and hybrid SVR and manta ray foraging optimizer (SVR–MRFO). Obtained results uncovered that the proposed hybrid SVR−BES is more accurate than other methods.

Prediction of long-term maximum settlement deformation of concrete face rockfill dams using hybrid support vector regression optimized with HHO algorithm

Prediction of long-term maximum settlement deformation of concrete face rockfill dams using hybrid support vector regression optimized with HHO algorithm

20 New Insights on Data Integration and Artificial Intelligence to Predict Primiparous Lactation Curves Capturing Genotype-by-Environment Interactions

Abstract We are developing a Dairy Brain by applying precision dairy farming, big data analytics, artificial intelligence, and the internet of things with the aim to accomplish a near real-time, data-integrated, data-driven, continuous decision-making engine through which management decisions can be better informed by integrated data streams to improve the economics of the farm and to positively benefit the individual animal and the overall farm through descriptive, predictive, and prescriptive analytics. Within this general concept, we have developed a machine learning hybrid K-medoids, random forest and support vector regression (K-R-S) approach for predicting the lactation curves of individual primiparous cows within a targeted environment using monthly milk production data from their dams and paternal siblings for 6,400 calves born in Wisconsin farms in year 2016. Our K-R-S hybrid approach outperformed the mean of paternal siblings in predicting first lactation test-day milk yield of primiparous cows 74.2% of the predictions. The algorithm has the ability to predict all data points required to construct primiparous cows’ full lactation curves even before they have started their productive life. Our approach allows the genotype-by-environment interactions to be portrayed in the prediction algorithm. Our current model uses only test-day (monthly) production data, but the artificial intelligence architecture is prepared to accommodate more frequent farm records (e.g., daily milk records from milking parlor) or other phenotype measures such as reproductive or health parameters for better characterization of the animals and their production environment towards improved prediction accuracy. We envision the prediction architecture will serve as an engine of farm-specific continuous prediction relaying on a constant flux of integrated data from different farm data sources following the Dairy Brain notion of data integration, analytics, and decision making.

Development of hybrid models using metaheuristic optimization techniques to predict the carbonation depth of fly ash concrete

• Intelligent prediction models of carbonation depth of fly ash concrete are developed based on machine learning techniques. • Binder content, fly-ash replacement level, water-to-binder ratio, CO 2 concentration, relative humidity and time of exposure are considered as effective influenced factors for carbonation depth. • Support vector regression combined with chicken swarm optimization algorithms achieved the best comprehensive prediction results. Carbonation is one of the utmost serious issues affecting the long-term durability of reinforced concrete. When H 2 O is present, a reaction between CO 2 gas and Ca(OH) 2 occurs, forming powdered CaCO 3 , which affects the microstructure of the concrete by lowering the pH level and causing corrosion, shortening the structure's service life. The complexity of the interaction between important parameters is difficult to capture for conventional carbonation prediction models. As a result, implementing powerful machine learning (ML) algorithms to overcome a lack of understanding of the consequences of such governing input parameters is critical. ML-based carbonation prediction models that blend four metaheuristic algorithms with Support Vector Regression (SVR) were developed to increase the accuracy and methodology of the prediction. 300 datasets from previous researches were used to develop, train, and test the SVR model. For the estimate of carbonation depth using experimental data, the possible hybrid SVR, which is made up of a Chicken Swarm Optimization (CSO), Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), and Seagull Optimization Algorithm (SOA), was used. The modelling accuracy was verified using four distinct performance indexes: Coefficient of determination (R2), Mean Square Error (MSE), Mean Absolute Error (MAE), and Variance Accounted For (VAF). The training and test sets of AI models (CSO-SVR, GWO-SVR, PSO-SVR, and SOA-SVR) exhibit a strong correlation (R2 > 0.95) between the actual and predicted carbonation depth values. The application of this model for numerical research on the parameters affecting the carbonation depth in fly-ash concrete is successful, according to this study, and it gives scientific direction for durability design.

Hybrid Artificial Intelligence Models with Multi Objective Optimization for Prediction of Tribological Behavior of Polytetrafluoroethylene Matrix Composites

This study presents multi-response optimization and prediction tribological behaviors polytetrafluoroethylene (PTFE) matrix composites. For multi-response optimization, the Taguchi model was hybridized with grey relational analysis to produce grey relational grades (GRG). A support vector regression (SVR) model was combined with novel Harris Hawks’ optimization (HHO) and swarm particle optimization (PSO) models to form hybrid SVR–HHO and SVR–PSO models to predict the GRG. The prediction ability of the models was appraised using the coefficient of determination (R2), correlation coefficient (R), mean square error (MSE), root mean square (RMSE), and mean absolute percentage error (MAPE). The results of the multi-response optimization revealed that the optimal combination of parametric values of GRG for minimum tribological rate was 9 N-1000 mesh-0.14 ms−1-55 m (L3G1SD3SS3). An analysis of variance of the GRG showed that a grit size of 94.56% was the most significant parameter influencing the tribological behavior of PTFE matrix composites. The validation results revealed that an improvement of 52% in GRG was achieved. The prediction results of all models showed that the SVR–PSO and SVR–HHO models were superior to the SVR model. Furthermore, the SVR–HHO model produced superior prediction error and the best goodness of fit over the SVR–PSO model. These findings concluded that hybrids models are promising tools in the multi-response optimization and prediction of tribological behaviors of PTFE matrix composites. They can serve as a guide in the design and development of tribological materials.

A Hybrid Method for Prediction of Ash Fouling on Heat Transfer Surfaces

Soot blowing optimization is a key, but challenging question in the health management of coal-fired power plant boiler. The monitoring and prediction of ash fouling for heat transfer surfaces is an important way to solve this problem. This study provides a hybrid data-driven model based on advanced machine-learning techniques for ash fouling prediction. First, the cleanliness factor is utilized to represent the level of ash fouling, which is the original data from the distributed control system. The wavelet threshold denoising algorithm is employed as the data preprocessing approach. Based on the empirical mode decomposition (EMD), the denoised cleanliness factor data is decoupled into a series of intrinsic mode functions (IMFs) and a residual component. Second, the support vector regression (SVR) model is used to fit the residual, and the Gaussian process regression (GPR) model is applied to estimate the IMFs. The cleanliness factor data of ash accumulation on the heat transfer surface of diverse devices are deployed to appraise the performance of the proposed SVR + GPR model in comparison with the sole SVR, sole GPR, SVR + EDM and GPR + EDM models. The illustrative results prove that the hybrid SVR + GPR model is superior to other models and can obtain satisfactory effects both in one-step- and the multistep-ahead cleanliness factor predictions.

Optimization and prediction of tribological behaviour of filled polytetrafluoroethylene composites using Taguchi Deng and hybrid support vector regression models

This study presents optimization and prediction of tribological behaviour of filled polytetrafluoroethylene (PTFE) composites using hybrid Taguchi and support vector regression (SVR) models. To achieve the optimization, Taguchi Deng was employed considering multiple responses and process parameters relevant to the tribological behaviour. Coefficient of friction (µ) and specific wear rate (Ks) were measured using pin-on-disc tribometer. In this study, load, grit size, distance and speed were the process parameters. An L27 orthogonal array was applied for the Taguchi experimental design. A set of optimal parameters were obtained using the Deng approach for multiple responses of µ and KS. Analysis of variance was performed to study the effect of individual parameters on the multiple responses. To predict µ and Ks, SVR was coupled with novel Harris Hawks’ optimization (HHO) and swarm particle optimization (PSO) forming SVR-HHO and SVR-PSO models respectively, were employed. Four model evaluation metrics were used to appraise the prediction accuracy of the models. Validation results revealed enhancement under optimal test conditions. Hybrid SVR models indicated superior prediction accuracy to single SVR model. Furthermore, SVR-HHO outperformed SVR-PSO model. It was found that Taguchi Deng, SVR-PSO and SVR-HHO models led to optimization and prediction with low cost and superior accuracy.

Hybrid support vector regression models with algorithm of innovative gunner for the simulation of groundwater level

Hybrid support vector regression models with algorithm of innovative gunner for the simulation of groundwater level

Predicting daily milk yield for primiparous cows using data of within-herd relatives to capture genotype-by-environment interactions

This study develops and illustrates a hybrid k-medoids, random forest, and support vector regression (K-R-S) approach for predicting the lactation curves of individual primiparous cows within a targeted environment using monthly milk production data from their dams and paternal siblings. The model simulation and evaluation were based on historical test-day (TD) milk production data from 2010 to 2016 for 260 Wisconsin dairy farms. Data from older paternal siblings and dams were used to create family units (n = 6,400) of individual calves, from which their future performance was predicted. Test-day milk yield (MY) records from 2010 to 2014 were used for model training, whereas monthly milk production records of Holstein calves born in 2014 were used for model evaluation. The K-R-S hybrid approach was used to generate MY predictions for 5 randomly selected batches of 320 primiparous cows, which were used to evaluate model performance at the individual cow level by cross-validation. Across all 5 batches, the mean absolute error and the root mean square error of the K-R-S predictions were lower (by 24.2 and 23.4%, respectively) than that of the mean daily MY of paternal siblings. The K-R-S predictions of TD MY were closer to actual values 74.2 ± 2.0% of the time, as compared with means of paternal siblings'. The correlation between actual TD MY and K-R-S predictions was greater (0.34 ± 0.01) than the correlation between the actual yield and the mean of paternal siblings (0.08 ± 0.01). The results of this study demonstrate the effectiveness of the K-R-S hybrid approach for predicting future first-lactation MY of dairy calves in management applications, such as milk production forecasting or decision-support simulation, using only monthly TD yields of within-herd relatives and in the absence of detailed genomic data.