Optimized Support Vector Regression Research Articles

Spatiotemporal Hybrid Random Forest Model for Tea Yield Prediction Using Satellite-Derived Variables

Crop yield forecasting is critical for enhancing food security and ensuring an appropriate food supply. It is critical to complete this activity with high precision at the regional and national levels to facilitate speedy decision-making. Tea is a big cash crop that contributes significantly to economic development, with a market of USD 200 billion in 2020 that is expected to reach over USD 318 billion by 2025. As a developing country, Bangladesh can be a greater part of this industry and increase its exports through its tea yield and production with favorable climatic features and land quality. Regrettably, the tea yield in Bangladesh has not increased significantly since 2008 like many other countries, despite having suitable climatic and land conditions, which is why quantifying the yield is imperative. This study developed a novel spatiotemporal hybrid DRS–RF model with a dragonfly optimization (DR) algorithm and support vector regression (S) as a feature selection approach. This study used satellite-derived hydro-meteorological variables between 1981 and 2020 from twenty stations across Bangladesh to address the spatiotemporal dependency of the predictor variables for the tea yield (Y). The results illustrated that the proposed DRS–RF hybrid model improved tea yield forecasting over other standalone machine learning approaches, with the least relative error value (11%). This study indicates that integrating the random forest model with the dragonfly algorithm and SVR-based feature selection improves prediction performance. This hybrid approach can help combat food risk and management for other countries.

Proposing a hybrid metaheuristic optimization algorithm and machine learning model for energy use forecast in non-residential buildings

The building sector is the largest energy consumer accounting for 40% of global energy usage. An energy forecast model supports decision-makers to manage electric utility management. Identifying optimal values of hyperparameters of prediction models is challenging. Therefore, this study develops a novel time-series Wolf-Inspired Optimized Support Vector Regression (WIO-SVR) model to predict 48-step-ahead energy consumption in buildings. The proposed model integrates the support vector regression (SVR) and the grey wolf optimizer (GWO) in which the SVR model serves as a prediction engine while the GWO is used to optimize the hyperparameters of the SVR model. The 30-min energy data from various buildings in Vietnam were adopted to validate model performance. Buildings include one commercial building, one hospital building, three authority buildings, three university buildings, and four office buildings. The dataset is divided into the learning data and the test data. The performance of the WIO-SVR was superior to baseline models including the SVR, random forests (RF), M5P, and decision tree learner (REPTree). The WIO-SVR model obtained the highest value of correlation coefficient (R) with 0.90. The average root-mean-square error (RMSE) of the WIO-SVR was 2.02 kWh which was more accurate than those of the SVR model with 10.95 kWh, the RF model with 16.27 kWh, the M5P model with 17.73 kWh, and the REPTree model with 26.44 kWh. The proposed model improved 442.0–1207.9% of the predictive accuracy in RMSE. The reliable WIO-SVR model provides building managers with useful references in efficient energy management.

Modeling and multi-objective optimization of microalgae biomass production and CO2 biofixation using hybrid intelligence approaches

This study investigates the impacts of temperature, light-dark cycles (LD), and nitrogen-phosphorus ratios (NP) on Chlorella vulgaris microalgae biomass productivity (BP) and CO2 biofixation (RCO2). Three artificial intelligence (AI) modeling approaches - boosted regression tree (BRT), artificial neural networks (ANN), and support vector regression (SVR) were applied. Bayesian optimization algorithm (BOA) was combined with each AI approach to predict BP and RCO2. Real-life experimental data, according to Box-Behnken design (BBD) were employed to assess the models using relative error (RE), coefficient of determination (R2), mean absolute error (MAE), mean absolute relative error (MARE), root mean square error (RMSE), and fractional bias (FB). The performance of the ANN and SVR models are comparable. However, the SVR model performs much better than the BRT and ANN models. Regarding RCO2, the SVR model yields low errors (MAE of 0.0128, MARE of 0.4131, RMSE of 0.0189) with a high R2 of 0.911. The value of FB is close to zero (0.0088), suggesting the model is reliable. The SVR model shows a better prediction capability of RCO2 compared to BBD with a performance improvement of 17.16%. MARE of BBD for RCO2 is 0.7409, which is higher than that of SVR model. Finally, the crow search algorithm was combined with the SVR for multi-objective optimization to determine the global optimal conditions for maximizing BP and RCO2, respectively. The optimum conditions were calculated to be 40 °C, 1:1 of N/P, and 12/12 h/h of LD with BP and RCO2 of 0.0979 g L−1d−1 and 0.1408 g L−1d−1, respectively.

Crack extension identification based on distributed fiber sensing measurement and optimized support vector regression

Crack is one of the main causes for the failure of marine structure due to the action of waves and ocean. It is necessary to monitor the initiation and extension of the crack timely and accurately, so as to provide effective suggestion for maintenance and prolong the service life of the structure. A novel distributed optical fiber sensing tape based on optical frequency domain reflectometer (OFDR) has been proposed in previous research, which can be used to find and locate cracks. In this paper, distributed optical fiber sensing (DOFS) technology is used to obtain the strain data around the crack, and the identification of crack extension is carried out based on the strain data combining with support vector regression (SVR). The parameter set of the SVR is optimized by particle swarm optimization (PSO) to improve the accuracy of the identification model. The results show that the crack extension identification system has a root mean square error (RMSE) as low as 3.59 when no noise is added. The influence of noise is investigated by simulation. The results show that the mean relative error (MRE) is 0.066 when 5% Gaussian white noise is added, which indicates that the crack extension length can still be identified accurately under the influence of noise.

Predicting Axial Impairment in Parkinson's Disease through a Single Inertial Sensor.

Background: Current telemedicine approaches lack standardised procedures for the remote assessment of axial impairment in Parkinson’s disease (PD). Unobtrusive wearable sensors may be a feasible tool to provide clinicians with practical medical indices reflecting axial dysfunction in PD. This study aims to predict the postural instability/gait difficulty (PIGD) score in PD patients by monitoring gait through a single inertial measurement unit (IMU) and machine-learning algorithms. Methods: Thirty-one PD patients underwent a 7-m timed-up-and-go test while monitored through an IMU placed on the thigh, both under (ON) and not under (OFF) dopaminergic therapy. After pre-processing procedures and feature selection, a support vector regression model was implemented to predict PIGD scores and to investigate the impact of L-Dopa and freezing of gait (FOG) on regression models. Results: Specific time- and frequency-domain features correlated with PIGD scores. After optimizing the dimensionality reduction methods and the model parameters, regression algorithms demonstrated different performance in the PIGD prediction in patients OFF and ON therapy (r = 0.79 and 0.75 and RMSE = 0.19 and 0.20, respectively). Similarly, regression models showed different performances in the PIGD prediction, in patients with FOG, ON and OFF therapy (r = 0.71 and RMSE = 0.27; r = 0.83 and RMSE = 0.22, respectively) and in those without FOG, ON and OFF therapy (r = 0.85 and RMSE = 0.19; r = 0.79 and RMSE = 0.21, respectively). Conclusions: Optimized support vector regression models have high feasibility in predicting PIGD scores in PD. L-Dopa and FOG affect regression model performances. Overall, a single inertial sensor may help to remotely assess axial motor impairment in PD patients.

Hybrid Ensemble-Learning Approach for Renewable Energy Resources Evaluation in Algeria

In order to achieve a highly accurate estimation of solar energy resource potential, a novel hybrid ensemble-learning approach, hybridizing Advanced Squirrel-Search Optimization Algorithm (ASSOA) and support vector regression, is utilized to estimate the hourly tilted solar irradiation for selected arid regions in Algeria. Long-term measured meteorological data, including mean-air temperature, relative humidity, wind speed, alongside global horizontal irradiation and extra-terrestrial horizontal irradiance, were obtained for the two cities of Tamanrasset-and-Adrar for two years. Five computational algorithms were considered and analyzed for the suitability of estimation. Further two new algorithms, namely Average Ensemble and Ensemble using support vector regression were developed using the hybridization approach. The accuracy of the developed models was analyzed in terms of five statistical error metrics, as well as the Wilcoxon rank-sum and ANOVA test. Among the previously selected algorithms, K Neighbors Regressor and support vector regression exhibited good performances. However, the newly proposed ensemble algorithms exhibited even better performance. The proposed model showed relative root mean square errors lower than 1.448% and correlation coefficients higher than 0.999. This was further verified by benchmarking the new ensemble against several popular swarm intelligence algorithms. It is concluded that the proposed algorithms are far superior to the commonly adopted ones.

Optimized Support Vector Regression for Predicting Leishmaniasis Incidences

Support Vector Regression (SVR) is a new approach in machine learning for time series prediction showing good performance. A big challenge for achieving optimal accuracy is the choice of appropriate parameters. In this paper, a Novel Enhanced Differential Evolution (NEDE) algorithm is proposed to calculate the optimal SVR parameters, and the combination approach (NEDE-SVR) was applied to predict the incidences of Zoonotic Cutaneous Leishmaniasis (ZCL) diseases. The NEDE-SVR based prediction model incorporates the climate factors as predictor variables, determined by analyzing their time lags related to the ZCL incidence. Conducted experiments have shown that NEDE-SVR exhibits good competitive performance using past diseases and climate data to predict the future cases of the ZCL disease. Accurate and timely ZCL disease predictions could aid structure health responses by informing key preparation and mitigation efforts.

Estimating Yield and Water Productivity of Tomato Using a Novel Hybrid Approach

Water productivity (WP) of crops is affected by water–fertilizer management in interaction with climatic factors. This study aimed to evaluate the efficiency of a hybrid method of season optimization algorithm (SO) and support vector regression (SVR) in estimating the yield and WP of tomato crops based on climatic factors, irrigation–fertilizer under the drip irrigation, and plastic mulch. To approve the proposed method, 160 field data including water consumption during the growing season, fertilizers, climatic variables, and crop variety were applied. Two types of treatments, namely drip irrigation (DI) and drip irrigation with plastic mulch (PMDI), were considered. Seven different input combinations were used to estimate yield and WP. R2, RMSE, NSE, SI, and σ criteria were utilized to assess the proposed hybrid method. A good agreement was presented between the observed (field monitoring data) and estimated (calculated with SO–SVR method) values (R2 = 0.982). The irrigation–-fertilizer parameters (PMDI, F) and crop variety (V) are the most effective in estimating the yield and WP of tomato crops. Statistical analysis of the obtained results showed that the SO–SVR hybrid method has high efficiency in estimating WP and yield. In general, intelligent hybrid methods can enable the optimal and economical use of water and fertilizer resources.

Ultimate Axial Load Prediction Model for X65 Pipeline with Cracked Welding Joint Based on the Failure Assessment Diagram Method

Crack defects in the girth welds of pipelines have become an important factor affecting the safe operation of in-service oil pipelines. Therefore, it is necessary to analyze the factors affecting the safe operation of pipelines and determine the ultimate load during pipeline operation. Based on the failure assessment diagram (FAD) method described in the BS 7910 standard, the key factors affecting the evaluation results of the suitability of X65 pipeline girth welds are analyzed, and the effects of crack size, pipe geometry, and material properties on the evaluation results are investigated. The results indicate that the crack depth is more crucial to the safe operation of the pipeline than the crack length. While the effect of wall thickness is not significant, the misalignment can seriously aggravate the stress concentration. In general, the higher the yield ratio and tensile strength of the pipe material, the more dangerous the condition at the weld. The ultimate axial load that a crack-containing girth weld can withstand under different combinations of the above factors was determined. Furthermore, a data driven model via the optimized support vector regression method for the ultimate axial load of the X65 pipe was developed for engineering application, and the comparison results between the FEM results and the predicted results proved its accuracy and reliability.

Online Monitoring Data Processing Method of Transformer Oil Chromatogram Based on Association Rules

AbstractThe oil chromatography online monitoring system can monitor the insulation status of power transformers continuously and real‐time. The accuracy of its detection data directly affects the stable operation of the transformers. Aiming at the problem of abnormal data in the current transformer online monitoring data set, this paper proposes an online oil chromatographic data processing method based on association rules and support vector regression (SVR) analysis. First, using piecewise linearization to convert numerical variables into Boolean variables, and then exploring gas indicators with strong correlations in oil chromatogram. Then, using the improved box plot method to detect the abnormal value points in it, and distinguish the data of different abnormal patterns based on the association rules. Finally, the advanced particle swarm optimization support vector regression (APSO‐SVR) algorithm is used to repair the data to improve the credibility of the data set. Using actual transformer oil chromatographic monitoring data for testing, the results show that the proposed data processing method can effectively improve the accuracy of oil chromatographic online monitoring data. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Online health assessment and fault prediction for wind turbine generator

A health assessment and fault prediction method for wind turbine generators is proposed in this article. In health assessment module, considering generator status transferring along with environment and wind turbine–self operating, variables under wind turbine normal working are divided into two parameter spaces and recognized, namely operating conditions and status parameters. Then generator health benchmark models based on Gaussian mixture model are established in different operating condition sub-spaces after the data imbalance problem solved. For online health assessment, health deterioration index based on condition recognition models is calculated and a dual-threshold alarm scheme is proposed. When an alarm is raised by degraded health deterioration index, the program could access fault prediction module, where the generator rear bearing temperature trend and fault remaining time can be predicted through weights redistribution and hyper-parameter optimized support vector regression. In experiments, the proposed health assessment and fault prediction was verified in a real wind farm, and results showed this method could assess generator condition accurately and improve special fault prediction performance.

Energy gap estimation of zinc sulfide metal chalcogenide nanostructure semiconductor using genetically hybridized support vector regression

Zinc sulfide is a metal chalcogenide semiconductor with promising potentials in environmental sensors, short wavelength light emitting diodes, biomedical imaging, display light sources, transistors, flat panel displays, optoelectronics, and photocatalysis. Adjusting the energy gap (EG) of zinc sulfide for light response enhancement that is suitable for desired applications involves foreign material incorporation through chemical doping or co-doping mechanisms with structural distortion and host symmetry breaking. This work optimizes support vector regression (SVR) parameters with a genetic algorithm to develop a hybrid genetically optimized SVR (HGSVR-EG) model with the precise capacity to estimate the EG of a doped zinc sulfide semiconductor using the crystal lattice constant and the crystallite size as descriptors. The precision of the developed HGSVR-EG model is compared with that of the stepwise regression based model for EG estimation (STR-EG) using different error metrics. The developed HGSVR-EG model outperforms the STR-EG model with a performance improvement of 64.47%, 74.52%, and 49.52% on the basis of correlation coefficient, mean squared error, and root mean square error, respectively. The developed HGSVR-EG model explores and investigates the zinc sulfide bandgap reduction effect of manganese and chromium nano-particle incorporation in the host semiconductor, and the obtained EGs agree well with the measured values. The developed HGSVR-EG model was further validated with an external set of data, and an excellent agreement between the measured and estimated EGs was obtained. The outstanding performance of the developed predictive models in this work would ultimately facilitate EG characterization of zinc sulfide without experimental stress.

An optimized support vector regression for prediction of bearing degradation

Machine learning and deep learning models are gradually being applied to predict the remaining useful life of bearings. But, still extracting effective features from the bearing signals and enhancing the prediction accuracy is a major concern. Therefore, an optimized support vector regression (SVR) model for prediction of bearing degradation is proposed. Firstly, the original time domain and frequency domain features extracted from the bearing vibration signal are learned by using the deep neural network (DNN) to improve the quality of degradation features. Secondly, a novel multi-population fruit fly optimization algorithm (MPFOA) is proposed by introducing multi-population mechanism. Thirdly, MPFOA is employed to choose the parameters of SVR, then we use MPFOA-SVR to predict the bearing remaining useful life through the degradation features learned by DNN. At last, CEC 2017 unconstrained benchmark functions and a real bearing dataset (IEEE 2012 PHM) are used to verify the performance of MPFOA and optimized SVR models respectively. Numerical experimental results show that MPFOA has a better optimization ability than the compared meta-heuristic algorithms. The optimized SVR model has a higher prediction accuracy in predicting the bearing remaining useful life.

Prediction of House Price Index Based on Bagging Integrated WOA-SVR Model

Aiming at the shortcomings of a single machine learning model with low model prediction accuracy and insufficient generalization ability in house price index prediction, a whale algorithm optimized support vector regression model based on bagging ensemble learning method is proposed. Firstly, gray correlation analysis is used to obtain the main influencing factors of house prices, and the segmentation forecasting method is used to divide the data set and forecast the house prices in the coming year using the data of the past ten years. Secondly, the whale optimization algorithm is used to find the optimal parameters of the penalty factor and kernel function in the SVR model, and then, the WOA-SVR model is established. Finally, in order to further improve the model generalization capability, a bagging integration strategy is used to further integrate and optimize the WOA-SVR model. The experiments are conducted to forecast the house price indices of four regions, Beijing, Shanghai, Tianjin, and Chongqing, respectively, and the results show that the prediction accuracy of the proposed integrated model is better than the comparison model in all cases.

Development of a new NIR-machine learning approach for simultaneous detection of diesel various properties

The computer aided detection of diesel multiple properties is an active field of energy and chemical research as a result of the need for quality control and brands management of diesel raw materials. Based on this premise, this paper aimed to detect the diesel density, viscosity, freezing point, boiling point, cetane number and total aromatics using near infrared spectroscopy (NIRS) data combined with improved XY co-occurrence distance (ISPXY) and improved grey wolf optimized support vector regression (IGWO-SVR). The outcomes of average recovery, mean square error, mean absolute percentage error and determination coefficient of the proposed model are all better than other machine learning models. Further, this method is green, simple, effective, rapid, and can be embedded in the industrial network as a unit, which provides intelligent guidance for refineries to accurately control the quality of diesel oil.

Hybrid support vector regression and crow search algorithm for modeling and multiobjective optimization of microalgae-based wastewater treatment

Microalgae-based wastewater treatment (and biomass production) is an environmentally benign and energetically efficient technique as compared to traditional practices. The present study is focused on optimization of the major treatment variables such as temperature, light-dark cycle (LD), and nitrogen (N)-to-phosphate (P) ratio (N/P) for the elimination of N and P from tertiary municipal wastewater utilizing Chlorella kessleri microalgae species. In this regard, a hybrid support vector regression (SVR) technique integrated with the crow search algorithm has been applied as a novel modeling/optimization tool. The SVR models were formulated using the experimental data, which were furnished according to the response surface methodology with Box-Behnken Design. Various statistical indicators, including mean absolute percentage error, Taylor diagram, and fractional bias, confirmed the superior performance of SVR models as compared to the response surface methodology (RSM) and generalized linear model (GLM). Finally, the best SVR model was hybridized with the crow search algorithm for single/multi-objective optimizations to acquire the global optimal treatment conditions for maximum N and P removal efficiencies. The best-operating conditions were found to be 29.3°C, 24/0 h/h of LD, and 6:1 of N/P, with N and P elimination efficiencies of 99.97 and 93.48%, respectively. The optimized values were further confirmed by new experimental data.

Ship Track Prediction Based on DLGWO-SVR

To improve the accuracy of ship track prediction, the improved Grey Wolf Optimizer (GWO) and Support Vector Regression (SVR) models are incorporated for ship track prediction. The hunting strategy of dimensional learning was used to optimize the move search process of GWO and balance exploration and exploitation while maintaining population diversity. Selection and updating procedures keep GWO from being stuck in locally optimal solutions. The optimal parameters obtained by modified GWO were substituted into the SVR model to predict ship trajectory. Dimension Learning Grey Wolf Optimizer and Support Vector Regression (DLGWO-SVR), Grey Wolf Optimized Support Vector Regression (GWO-SVR), and Differential Evolution Grey Wolf Optimized Support Vector Regression (DEGWO-SVR) model trajectory prediction simulations were carried out. A comparison of the results shows that the trajectory prediction model based on DLGWO-SVR has higher prediction accuracy and meets the requirements of ship track prediction. The results of ship track prediction can not only improve the efficiency of marine traffic management but also prevent the occurrence of traffic accidents and maintain marine safety.

Bayesian Support Vector Regression for Reliability-Based Design Optimization

Solving reliability-based design optimization (RBDO) by combining surrogate models is a powerful tool to deal with the output variation induced by uncertainties during actual engineering design. This paper aims to develop a strategy for solving RBDO problems by support vector regression (SVR) under the Bayesian inference, referred to as Bayesian SVR (BSVR). The BSVR model possesses the features of original SVR as well as providing the prediction variance to direct the sequential sampling process for probabilistic analysis in RBDO. In the meanwhile, a learning function combined with the sample pool truncation strategy is proposed to select the new training samples to adaptively update the BSVR model, which can accurately and efficiently approximate the important probabilistic constraint boundaries in the desired regions, and the newly selected training samples tend to be far away from the existing training points under the current design to avoid clustering. The computational capability and the good engineering applicability of the proposed method are verified by three numerical examples and two engineering applications about a stiffened rib of the wing edge and a latch-lock mechanism of the cabin hatch.

Global solar radiation prediction: Application of novel hybrid data-driven model

One of the significant prerequisites for harvesting solar energy is precise global solar radiation (GHI) forecasts. However, variability and uncertainty are inherent characteristics of solar radiation. It is challenging to show better generalization using current data analysis approaches. Thus, this research presents a new intelligence framework by hybridizing Support Vector Regression (SVR) with the Grasshopper Optimization Algorithm (GOA) and the Boruta-based feature selection algorithm (BA) for forecasting GHI values at different sites of Saudi Arabia. Interestingly, the most significant distinction that differentiates this proposed prediction model (SVR-GOA-BAK) from other models is that the GOA is automatically employed to search for optimal SVR’s hyperparameters. In contrast, these hyperparameters are chosen randomly and manually in conventional models. Consequently, the contribution helps save time, reduce cost, and avoid the possibility of models’ overfitting or underfitting caused by random and manual selection. A diversity of statistical measures has justified the proposed model’s effectiveness and superiority. In terms of mean absolute percentage error (MAPE), the proposed model outperformed the standalone SVR models by 32.15–39.69% at different study sites. In tuning the SVR’s parameters, GOA outperforms popular optimization algorithms. All the simulation test results demonstrate the superiority of the proposed model. Hence, the proposed approach provides a foundation for precise solar radiation forecasting, which can aid in the growth of renewable-energy-based technologies.

Hotspot Temperature Prediction of Dry-Type Transformers Based on Particle Filter Optimization with Support Vector Regression

Both poor cooling methods and complex heat dissipation lead to prominent asymmetry in transformer temperature distribution. Both the operating life and load capacity of a power transformer are closely related to the winding hotspot temperature. Realizing accurate prediction of the hotspot temperature of transformer windings is the key to effectively preventing thermal faults in transformers, thus ensuring the reliable operation of transformers and accurately predicting transformer operating lifetimes. In this paper, a hot spot temperature prediction method is proposed based on the transformer operating parameters through the particle filter optimization support vector regression model. Based on the monitored transformer temperature, load rate, transformer cooling type, and ambient temperature, the hotspot temperature of a dry-type transformer can be predicted by a support vector regression method. The hyperparameters of the support vector regression are dynamically optimized here according to the particle filter to improve the optimization accuracy. The validity and accuracy of the proposed method are verified by comparing the proposed method with a traditional support vector regression method based on the real operating data of a 35 kV dry-type transformer.