Proposed Support Vector Regression Model Research Articles

Seismic response of soil-structure interaction using the support vector regression

In this paper, a different technique to predict the effects of soil-structure interaction (SSI) on seismic response of building systems is investigated. The technique use a machine learning algorithm called Support Vector Regression (SVR) with technical and analytical results as input features. Normally, the effects of SSI on seismic response of existing building systems can be identified by different types of large data sets. Therefore, predicting and estimating the seismic response of building is a difficult task. It is possible to approximate a real valued function of the seismic response and make accurate investing choices regarding the design of building system and reduce the risk involved, by giving the right experimental and/or numerical data to a machine learning regression, such as SVR. The seismic response of both single-degree-of-freedom system and six-storey RC frame which can be represent of a broad range of existing structures, is estimated using proposed SVR model, while allowing flexibility of the soil-foundation system and SSI effects. The seismic response of both single-degree-of-freedom system and six-storey RC frame which can be represent of a broad range of existing structures, is estimated using proposed SVR model, while allowing flexibility of the soil-foundation system and SSI effects. The results show that the performance of the technique can be predicted by reducing the number of real data input features. Further, performance enhancement was achieved by optimizing the RBF kernel and SVR parameters through grid search.

Prediction of golden time using SVR for recovering SIS under severe accidents

Nuclear power plants (NPPs) are designed in consideration of design basis accidents (DBAs). However, if the safety injection system (SIS) is not working properly in a loss-of-coolant-accident (LOCA) situation, it can induce a severe accident that exceeds DBAs. Therefore, it is important to properly actuate the SIS before a DBA becomes a severe accident. If the SIS is not working in time, the reactor core may be uncovered and the reactor vessel (RV) may be damaged. In this paper, we defined the golden time as the available time from an initial SIS malfunction for actuating the SIS to prevent reactor core uncovery and RV failure. A support vector regression (SVR) model was applied to predict the golden time. The input variables and parameters of the SVR model were selected and optimized by using a genetic algorithm. The data set of severe accident scenarios was obtained by using the Modular Accident Analysis Program (MAAP) code. An optimized power reactor (OPR1000) was used for the simulations. It was shown that that the proposed SVR model could predict the golden time accurately.

Survival Prediction and Feature Selection in Patients with Breast Cancer Using Support Vector Regression.

The Support Vector Regression (SVR) model has been broadly used for response prediction. However, few researchers have used SVR for survival analysis. In this study, a new SVR model is proposed and SVR with different kernels and the traditional Cox model are trained. The models are compared based on different performance measures. We also select the best subset of features using three feature selection methods: combination of SVR and statistical tests, univariate feature selection based on concordance index, and recursive feature elimination. The evaluations are performed using available medical datasets and also a Breast Cancer (BC) dataset consisting of 573 patients who visited the Oncology Clinic of Hamadan province in Iran. Results show that, for the BC dataset, survival time can be predicted more accurately by linear SVR than nonlinear SVR. Based on the three feature selection methods, metastasis status, progesterone receptor status, and human epidermal growth factor receptor 2 status are the best features associated to survival. Also, according to the obtained results, performance of linear and nonlinear kernels is comparable. The proposed SVR model performs similar to or slightly better than other models. Also, SVR performs similar to or better than Cox when all features are included in model.

Learning-Based Emulation of Sea Surface Wind Fields From Numerical Model Outputs and SAR Data

The availability of sea surface wind conditions with a high-resolution (HR) space-time sampling is a critical issue for a wide range of applications. Currently, no observation systems nor model forecasts provide relevant information with a high sampling rate in both space and time. Synthetic aperture radar (SAR) satellite systems deliver HR sea surface fields, with a spatial resolution below 0.01°, but they are also characterized by a large revisit time up 7 to 10 days for temperate zones. Meanwhile, operational model predictions typically involve a high temporal resolution (e.g., every 6 h), but also a low spatial resolution (0.5°). With a view to leveraging both data sources, we investigate statistical downscaling schemes. In this study, a new model based on a machine learning method, namely support vector regression (SVR), is built to reconstruct HR sea surface wind fields from low-resolution operational model forecasts. The considered case study off Norway demonstrates the relevance of the proposed SVR model. It outperforms state-of-the-art approaches [namely, linear, analog, and empirical orthogonal function (EOF) downscaling models] in terms of mean square error. It also realistically reproduces complex space-time variabilities of the observed SAR wind fields. We further discuss the SVR model as a generalization of the popular linear and analog models.

NR-Bitstream video quality metrics for SSIM using encoding decisions in AVC and HEVC coded videos

We propose a no-reference compressed video quality model to predict the full-reference SSIM metrics for AVC (Advanced Video Coding, H.264) and HEVC (High Efficiency Video Coding) videos. The model we use is support vector regression (SVR) model. We use only encoding decisions made during motion estimation to perform the prediction, and do not need the information from pixel domain. We show that the Block-Partition-related features have great importance in SSIM prediction, especially for HEVC videos, due to its partition decisions being more complex than those of AVC. The proposed SVR model trained by data of two different encoding configurations can predict SSIM well for AVC videos (0.78 correlation) and for HEVC videos (0.88 correlation). The proposed models are also compared with a state-of-the-art no-reference-bitstream-pixel SSIM prediction model. We show that the proposed methods provide higher prediction correlation (as high as 13.13% improvement in correlation) with much lower complexity.

Support Vector Machine Regression for project control forecasting

Support Vector Machines are methods that stem from Artificial Intelligence and attempt to learn the relation between data inputs and one or multiple output values. However, the application of these methods has barely been explored in a project control context. In this paper, a forecasting analysis is presented that compares the proposed Support Vector Regression model with the best performing Earned Value and Earned Schedule methods. The parameters of the SVM are tuned using a cross-validation and grid search procedure, after which a large computational experiment is conducted. The results show that the Support Vector Machine Regression outperforms the currently available forecasting methods. Additionally, a robustness experiment has been set up to investigate the performance of the proposed method when the discrepancy between training and test set becomes larger.

High reliability estimation of product quality using support vector regression and hybrid meta-heuristic algorithms

Online estimation of product quality is a complicated task in refining processes. Data driven soft sensors have been successfully employed as a supplement to the online hardware analyzers that are often expensive and require high maintenance. Support Vector Regression (SVR) is an efficient machine learning technique that can be used for soft sensor design. However, choosing optimal hyper-parameter values for the SVR is a hard optimization problem. In order to determine the parameters as fast and accurate as possible, some Hybrid Meta-Heuristic (HMH) algorithms have been developed in this study. A comprehensive study has been carried out comparing the meta-heuristic algorithms of GA and PSO to the HMH algorithms of GA⿿SQP and PSO⿿SQP for prediction of sulfur quality in treated gas oil using the SVR technique. Experimental data from a hydrodesulfurization (HDS) setup were collected to validate the proposed SVR model. The SVR model yields better performances both in accuracy and computation time (CT) for predicting the sulfur quality with hyper parameters optimized by HMH algorithms. Applying the PSO⿿SQP algorithm gives the best performance with AARE=0.133 and CT=15.88s compared to the other methods.

Comparative study of computational intelligence approaches for NOx reduction of coal-fired boiler

This paper focuses on NOx emission prediction and operating parameters optimization for coal-fired boilers. Support Vector Regression (SVR) model based on CGA (Conventional Genetic Algorithm) was proposed to model the relationship between the operating parameters and the concentration of NOx emission. Then CGA and two modified algorithms, the Quantum Genetic Algorithm (QGA) and SAGA (Simulated Annealing Genetic Algorithm), were employed to optimize the operating parameters of the coal-fired boiler to reduce NOx emission. The results showed that the proposed SVR model was more accurate than the widely used Artificial Neural Network (ANN) model when employed to predict the concentration of NOx emission. The mean relative error and correlation coefficient calculated by the proposed SVR model were 2.08% and 0.95, respectively. Among the three optimization algorithms implemented in this paper, the SAGA showed superiority to the other two algorithms considering the quality of solution within a given computing time. The SVR plus SAGA method was preferable to predict the concentration of NOx emission and further to optimize the operating parameters to achieve low NOx emission for coal-fired boilers.

A novel support vector regression model to estimate the phycocyanin concentration in turbid inland waters from hyperspectral reflectance

This study develops a novel support vector regression (SVR) model for retrieving the specific cyanobacterial pigment C-phycocyanin (C-PC) concentrations in cyanobacteria-dominated large turbid lakes of China. Lake Taihu, Lake Chaohu, and Lake Dianchi in China were our study areas. Five field cruises were carried out to collect data sets of optical and water quality parameters. To retrieve the C-PC, three types of reflectance forms, including single band, band ratio, and three-band-combination, were compared. The band ratio was the best candidate to serve for algorithm development. On this basis, two types of models, including linear models and a SVR model, were originally established. The previous typical algorithms were also examined. The obtained results showed that the best-performing model was the SVR model. By our validation data set, the proposed SVR model also presented accurate prediction results, with the lowest errors among all methods. The novelty of the SVR model compared to the previous ones lies in the inclusion of band ratios that are located outside of the main pigment absorption peaks but hold information on inflection points, curvature, etc., into empirical optimization. The implications of these findings indicates the potential applicability of the SVR models in lakes of the similar type.

Estimating the shift size in the process mean with support vector regression and neural networks

Control charts are usually used in manufacturing and service industries to determine whether a process is performing as intended or if there are some unnatural causes of variation. Once the control chart detects a process change, the next issue is to “search for assignable causes”, or “take corrective actions”, etc. Before corrective actions are taken, it is critical to search for the cause of the out-of-control situation. During this search process, knowledge of the current parameter level can be helpful to narrow the set of possible assignable causes. Sometimes, the process/product parameters might be adjusted following the out-of-control signal to improve quality. An accurate estimate of the parameter will naturally provide a more precise adjustment of the process. A distinct weakness of most existing control charts techniques is that they merely provide out-of-control signals without predicting the magnitudes of changes. In this paper, we develop a support vector regression (SVR) model for predicting the process mean shifts. Firstly, a cumulative sum (CUSUM) chart is employed to detect shifts in the mean of a process. Next, an SVR-based model is used to estimate the magnitude of shifts as soon as CUSUM signals an out-of-control situation. The performance of the proposed SVR was evaluated by estimating mean absolute percent errors (MAPE) and normalized root mean squared errors (NRMSE) using simulation. To evaluate the prediction ability of SVR, we compared its performance with that of neural networks and statistical methods. Overall results of performance evaluations indicate that the proposed support vector regression model has better estimation capabilities than CUSUM and neural networks.

Correlating Lattice Constant of Cubic Perovskites to Atomic Parameters Using Support Vector Regression

Recently, due to problems arising from lattice mismatch in thin film growth in semiconductor manufacturing industry, researchers have shown great interest in modeling the physiochemical properties of cubic perovskite of types ABX3. They have put sizeable efforts to reduce error in the prediction of lattice constant (LC) of cubic perovskites. However, linear prediction models were developed using linear regression techniques, which may not be able to find precisely the underlying nonlinearity in correlating LC to atomic parameters of perovskites. This causes a reduction in the prediction accuracy of linear model. To address this problem, in this work, support vector regression (SVR) technique is proposed to design and develop LC prediction model for cubic perovskites. To investigate the generalization of SVR model, we collected data for new cubic and pseudocubic compounds from the current literature of material science. Our analysis shows an improved prediction performance of SVR models than existing linear models. The proposed SVR model demonstrates lower overall error values of 0.286, 0.528, and 0.615 for training, validation, and newly collected compounds, respectively.

Calculation of the power peaking factor in a nuclear reactor using support vector regression models

Local power density (LPD) at the hottest part of a hot nuclear fuel rod should be estimated accurately to confirm that the rod does not melt. The power peaking factor (PPF) is defined as the highest LPD divided by the average power density in the reactor core. In this paper, the PPF is calculated by support vector regression (SVR) models using numerous measured signals from the reactor cooling system. SVR models are regression analysis models using a kernel function for artificial neural networks. Their neural network weights are found by solving a quadratic programming problem under linear constraints. SVR models are trained using a training data set and then verified against another test data set. The proposed SVR models were applied to the first fuel cycle of the Yonggwang nuclear power plant unit 3. The root mean square errors of the SVR model, with and without in-core neutron flux sensor signal inputs, were 0.1113% and 0.0968%, respectively. This level of errors is sufficiently low for use in LPD monitoring.