Multiple Support Vector Regression Research Articles

Analysis of bioconvection and oxytactic microorganisms in a porous cavity with nano-enhanced phase change materials and quadrant heater: Application of support vector regression based model

In this numerical study, two-dimensional simulations are performed to obtain the bioconvection flow in a quadrant heater located porous closed space saturated with nano-enhanced phase change material (NePCM). The Galerkin finite element method (GFEM) is employed to compute the governing equations for the considered system by developing a computer code. The study is performed for wide range of parameters as aspect ratio, Darcy number, Hartmann number, nanoparticle fraction, bioconvection Rayleigh number and natural convection Rayleigh number were tested. Also, the analysis is supported via artificial intelligent by using multiple support vector regression based model. The tests were performed with artificial intelligence on temperature values. After the analysis, it is found that radius of the curvilinear shaped heater plays role on both heat transfer and fluid flow, oxygen distribution, density of motile microorganism and heat capacity. Application of support vector machine technique gives good agreement with computational fluid dynamics results. Heat and mass transfer are improved with increasing of nanoparticle addition but decrease with increasing of strength of magnetic field.

Inferring Line-of-sight Velocities and Doppler Widths from Stokes Profiles of GST/NIRIS Using Stacked Deep Neural Networks

Obtaining high-quality magnetic and velocity fields through Stokes inversion is crucial in solar physics. In this paper, we present a new deep learning method, named Stacked Deep Neural Networks (SDNN), for inferring line-of-sight (LOS) velocities and Doppler widths from Stokes profiles collected by the Near InfraRed Imaging Spectropolarimeter (NIRIS) on the 1.6 m Goode Solar Telescope (GST) at the Big Bear Solar Observatory (BBSO). The training data for SDNN are prepared by a Milne–Eddington (ME) inversion code used by BBSO. We quantitatively assess SDNN, comparing its inversion results with those obtained by the ME inversion code and related machine-learning (ML) algorithms such as multiple support vector regression, multilayer perceptrons, and a pixel-level convolutional neural network. Major findings from our experimental study are summarized as follows. First, the SDNN-inferred LOS velocities are highly correlated to the ME-calculated ones with the Pearson product–moment correlation coefficient being close to 0.9 on average. Second, SDNN is faster, while producing smoother and cleaner LOS velocity and Doppler width maps, than the ME inversion code. Third, the maps produced by SDNN are closer to ME’s maps than those from the related ML algorithms, demonstrating that the learning capability of SDNN is better than those of the ML algorithms. Finally, a comparison between the inversion results of ME and SDNN based on GST/NIRIS and those from the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory in flare-prolific active region NOAA 12673 is presented. We also discuss extensions of SDNN for inferring vector magnetic fields with empirical evaluation.

A novel remaining useful life prediction method based on multi-support vector regression fusion and adaptive weight updating

Remaining useful life prediction is of huge significance in preventing equipment malfunctions and reducing maintenance costs. Currently, machine learning algorithms have become hotspots in remaining useful life prediction due to their high flexibility and convenience. However, machine learnings require large amounts of data, and their prediction performance depends heavily on the selection of hyper-parameters. To overcome these shortcomings, a novel remaining useful life prediction method for small sample cases is proposed based on multi-support vector regression fusion. In the offline training phase, the fusion model is established, consisting of multiple support vector regression sub-models To obtain the optimal sub-model parameters, the Bayesian optimization algorithm is applied and an improved optimization target is formulated with various metrics describing regression and prediction performance. In the online prediction phase, an adaptive weight updating algorithm based on dynamic time warping is developed to measure the fitness of each sub-model and determine the corresponding weight value. The C-MAPSS engine dataset is used to test the performance of the proposed method, along with some existing machine learning methods as comparison. The proposed method only requires 30% of the training data sample to achieve high accuracy, with a root mean square error of 14.98, which is superior to other state-of-the-art methods. The results demonstrate the superiority of the proposed method.

Experimental Evaluation of PSO Based Transfer Learning Method for Meteorological Visibility Estimation

Estimation of Meteorological visibility from image characteristics is a challenging problem in the research of meteorological parameters estimation. Meteorological visibility can be used to indicate the weather transparency and this indicator is important for transport safety. This paper summarizes the outcomes of the experimental evaluation of a Particle Swarm Optimization (PSO) based transfer learning method for meteorological visibility estimation method. This paper proposes a modified approach of the transfer learning method for visibility estimation by using PSO feature selection. Image data are collected at fixed location with fixed viewing angle. The database images were gone through a pre-processing step of gray-averaging so as to provide information of static landmark objects for automatic extraction of effective regions from images. Effective regions are then extracted from image database and the image features are then extracted from the Neural Network. Subset of Image features are selected based on the Particle Swarming Optimization (PSO) methods to obtain the image feature vectors for each effective sub-region. The image feature vectors are then used to estimate the visibilities of the images by using the Multiple Support Vector Regression (SVR) models. Experimental results show that the proposed method can give an accuracy more than 90% for visibility estimation and the proposed method is effective and robust.

Inferring Vector Magnetic Fields from Stokes Profiles of GST/NIRIS Using a Convolutional Neural Network

Abstract We propose a new machine-learning approach to Stokes inversion based on a convolutional neural network (CNN) and the Milne–Eddington (ME) method. The Stokes measurements used in this study were taken by the Near InfraRed Imaging Spectropolarimeter (NIRIS) on the 1.6 m Goode Solar Telescope (GST) at the Big Bear Solar Observatory. By learning the latent patterns in the training data prepared by the physics-based ME tool, the proposed CNN method is able to infer vector magnetic fields from the Stokes profiles of GST/NIRIS. Experimental results show that our CNN method produces smoother and cleaner magnetic maps than the widely used ME method. Furthermore, the CNN method is four to six times faster than the ME method and able to produce vector magnetic fields in nearly real time, which is essential to space weather forecasting. Specifically, it takes ∼50 s for the CNN method to process an image of 720 × 720 pixels comprising Stokes profiles of GST/NIRIS. Finally, the CNN-inferred results are highly correlated to the ME-calculated results and closer to the ME’s results with the Pearson product-moment correlation coefficient (PPMCC) being closer to 1, on average, than those from other machine-learning algorithms, such as multiple support vector regression and multilayer perceptrons (MLP). In particular, the CNN method outperforms the current best machine-learning method (MLP) by 2.6%, on average, in PPMCC according to our experimental study. Thus, the proposed physics-assisted deep learning–based CNN tool can be considered as an alternative, efficient method for Stokes inversion for high-resolution polarimetric observations obtained by GST/NIRIS.

Applying hybrid support vector regression and genetic algorithm to water alternating CO2gas EOR

AbstractWater alternating CO2gas injection (WAG CO2) is one of the most promising enhanced oil recovery techniques. The optimization of this process requires performing many time‐consuming simulations. In this paper, an intelligent hybridization based on support vector regression (SVR) and genetic algorithm (GA) is introduced for the WAG process optimization in the presence of time‐dependent constraints. Multiple SVRs are used as dynamic proxy to mimic numerical simulator behavior in real time. Latin hypercube design (LHD) is applied to generate the proper runs to train the proxy and ten supplementary runs are randomly chosen to validate it. The goal of GA in this study is twofold. First, it is employed during the training of multiple SVRs to find their appropriate hyper‐parameters. Second, once the training and validation of the dynamic proxy are done, the GA is coupled with it to find the optimum WAG parameters which maximize field oil production total (FOPT) subject to time‐dependent water‐cut constraint and some domain constraints. The task is formulated as a non‐linear constrained optimization problem. A semi‐synthetic WAG CO2case is used to examine the reliability of the approach. The results show that the established dynamic proxy is fast and accurate in reproducing the simulator outputs. The hybridization proxy‐GA is demonstrated to be reliable for the real‐time optimization of the formulated WAG process. © 2020 The Authors.Greenhouse Gases: Science and Technologypublished by Society of Chemical Industry and John Wiley & Sons, Ltd.

Dynamic Emotion Understanding in Human–Robot Interaction Based on Two-Layer Fuzzy SVR-TS Model

Two-layer fuzzy support vector regression-Takagi–Sugeno (TLFSVR-TS) model is proposed for emotion understanding in human–robot interaction (HRI), where the real-time dynamic emotion is recognized according to facial expression, and emotional intention understanding is obtained mainly based on human emotions and identification information. It aims to make robots capable of recognizing and understanding human emotions, in such a way that make HRI run smoothly. TLFSVR-TS considers about the priori knowledge inferred from human personal preference to reduce the uncertainty of various people, and multiple support vector regression (SVR) corresponding to different genders/provinces/ages of human to guarantee the local learning ability. Preliminary application experiments are performed in the developing emotional social robot system, where 30 volunteers experience the scenario of “drinking in the bar.” Results show that the proposal receives higher understanding accuracy than that of TLFSVR, kernel fuzzy ${c}$ -means clustering is fused with SVR, and SVR.

SVR ensemble-based continuous blood pressure prediction using multi-channel photoplethysmogram

In this paper, a continuous non-occluding blood pressure (BP) prediction method is proposed using multiple photoplethysmogram (PPG) signals. In the new method, BP is predicted by a committee machine or ensemble learning framework comprising multiple support vector regression (SVR) machines. The existing methods for continuous BP prediction rely on a single calibration model obtained from a single arterial segment. Our ensemble framework is the first BP estimation method which uses multiple SVR models for calibration from multiple arterial segments. This permits reducing of the mean prediction error and the risk of overfitting associated with a single model. Each SVR in the ensemble is trained on a comprehensive feature set that is constructed from a distinct PPG segment. The feature set includes pulse morphological parameters such as systolic pulse amplitude and area under the curve, heart rate variability (HRV) frequency, time domain parameters and the pulse wave velocity (PWV). Empirical evaluation using 40 volunteers with no serious health conditions shows that the proposed method is more reliable for estimating both the systolic and diastolic BP than similar methods employing a single calibration model under identical settings. Moreover, the combined output is found to be more stable than the output of any of the constituent models in the ensemble for both the systolic and diastolic cases.

Robust Life-Cycle Production Optimization With a Support-Vector-Regression Proxy

Summary We design a new and general work flow for efficient estimation of the optimal well controls for the robust production-optimization problem using support-vector regression (SVR), where the cost function is the net present value (NPV). Given a set of simulation results, an SVR model is built as a proxy to approximate a reservoir-simulation model, and then the estimated optimal controls are found by maximizing NPV using the SVR proxy as the forward model. The gradient of the SVR model can be computed analytically so the steepest-ascent algorithm can easily and efficiently be applied to maximize NPV. Then, the well-control optimization is performed using an SVR model as the forward model with a steepest-ascent algorithm. To the best of our knowledge, this is the first SVR application to the optimal well-control problem. We provide insight and information on proper training of the SVR proxy for life-cycle production optimization. In particular, we develop and implement a new iterative-sampling-refinement algorithm that is designed specifically to promote the accuracy of the SVR model for robust production optimization. One key observation that is important for reservoir optimization is that SVR produces a high-fidelity model near an optimal point, but at points far away, we only need SVR to produce reasonable approximations of the predicting output from the reservoir-simulation model. Because running an SVR model is computationally more efficient than running a full-scale reservoir-simulation model, the large computational cost spent on multiple forward-reservoir-simulation runs for robust optimization is significantly reduced by applying the proposed method. We compare the performance of the proposed method using the SVR runs with the popular stochastic simplex approximate gradient (StoSAG) and reservoir-simulations runs for three synthetic examples, including one field-scale example. We also compare the optimization performance of our proposed method with that obtained from a linear-response-surface model and multiple SVR proxies that are built for each of the geological models.

Short‐term wind power forecasting and uncertainty analysis using a hybrid intelligent method

This study proposes a hybrid intelligent method for short-term wind power forecasting and uncertainty analysis. In practice, the power output of a wind turbine is a direct function of wind speed. Owing to the intermittent and irregular nature of wind, the wind power generation is not easily dispatched and the prediction of wind power is highly uncertain. To allow a procedure for more accurate forecasting, a deterministic wind power prediction method that uses multiple support vector regression (SVR) models is established based on the wind power capacity and wind speed forecasts obtained from the Taiwan Central Weather Bureau (TCWB). An enhanced harmony search (EHS) algorithm is then used to estimate the parameters for each SVR model. To assess the risk that is associated with wind power forecasts in a power grid, an EHS-based quantile regression method that accurately reflects the confidence intervals for wind power forecasts is presented. The proposed approach provides wind power forecasts for future 3 h in steps of 15 min and the associated forecasting uncertainty. During testing on three practical wind power generation systems, the proposed method gives better forecasting accuracy and produces more reasonable confidence intervals than existing methods.

Silicon content prediction and industrial analysis on blast furnace using support vector regression combined with clustering algorithms

Silicon content prediction is quite significant for supervising the state of blast furnace and is usually selected as the indicator to represent the thermal state. In practical industry, the fluctuation exists in the operation of blast furnace all the time. What's worse, it is inaccurate to build the predictive model with many outliers. To solve these problems, this paper has developed a model to predict the silicon content using support vector regression (SVR) combined with clustering algorithms, including hard C-means (HCM) clustering and fuzzy C-means (FCM) clustering. Through data processing, the data points are clustered based on the similarity, and then different SVR models are established. In order to make full use of FCM, a new method using multiple SVRs and FCM based on membership degree (MFCM-SVRs) is proposed where the membership degree is applied to eliminate the outliers. Simulation results verify that the multiple SVRs based on HCM (HCM-SVRs) and MFCM-SVRs possess superiority in terms of accuracy and speed, which makes the method serve better for practical production.

Robotic Adaptive Impedance Control Based On Visual Guidance

Abstract Uncalibrated visual servoing based on SVR-Jacobian estimator is proposed in unknown environment. Multiple support vector regression (SVR) machines are used to estimate the Jacobian matrix of images, and the nonlinear mapping between the image features of the curved line and the robot joint angle is constructed, uncalibrated robot impedance control can be carried out. Image Jacobian matrix expression with Gaussian kernel is put forward, the effectiveness of the presented approach is verified by using a 6 DOF robot with a CCD camera and a force/torque sensor installed in its end effector

Iterated time series prediction with multiple support vector regression models

Support vector regression (SVR) model has been widely applied to time series prediction. In general iterative methods, the multi-step-ahead prediction is based on the iteration of the exact one-step prediction. Even if the one-step prediction model is very exact, the iteration procedure would accumulate prediction errors when repeating one-step-ahead prediction, which results in bad prediction performance. This paper deals with iterated time series prediction problem by using multiple SVR models, which are trained independently based on the same training data with different targets. In other words, the n-th SVR model performs an n-step-ahead prediction. The prediction outputs of these models are considered as the next input state variables to perform further prediction. Since each SVR model is an exact prediction model, the accumulate prediction error would be reduced by using multiple SVR models possibly. Actually, the MSVR method can be taken as a compromise of the iterative method and the direct method. Experimental results on time series data show that the multiple SVR model method is effective.

ℓp-Norm Multikernel Learning Approach for Stock Market Price Forecasting

Linear multiple kernel learning model has been used for predicting financial time series. However, ℓ 1-norm multiple support vector regression is rarely observed to outperform trivial baselines in practical applications. To allow for robust kernel mixtures that generalize well, we adopt ℓ p-norm multiple kernel support vector regression (1 ≤ p < ∞) as a stock price prediction model. The optimization problem is decomposed into smaller subproblems, and the interleaved optimization strategy is employed to solve the regression model. The model is evaluated on forecasting the daily stock closing prices of Shanghai Stock Index in China. Experimental results show that our proposed model performs better than ℓ 1-norm multiple support vector regression model.

Gaze tracking based on active appearance model and multiple support vector regression on mobile devices

Gaze tracking technology is a convenient interfacing method for mobile devices. Most previous studies used a large-sized desktop or head-mounted display. In this study, we propose a novel gaze tracking method using an active appearance model (AAM) and multiple support vector regression (SVR) on a mobile device. Our research has four main contributions. First, in calculating the gaze position, the amount of facial rotation and translation based on four feature values is computed using facial feature points detected by AAM. Second, the amount of eye rotation based on two feature values is computed for measuring eye gaze position. Third, to compensate for the fitting error of an AAM in facial rotation, we use the adaptive discrete Kalman filter (DKF), which applies a different velocity of state transition matrix to the facial feature points. Fourth, we obtain gaze position on a mobile device based on multiple SVR by separating the rotation and translation of face and eye rotation. Experimental results show that the root mean square (rms) gaze error is 36.94 pixels on the 4.5-in. screen of a mobile device with a screen resolution of 800×600 pixels.

Multiple Support Vector Regression for Antenna Array Characterization and Synthesis

The support vector regression framework is proposed as the basis for a new antenna array characterization technique able to model radiating structures including all the coupling effects between the elements of the array from experimental data. The obtained model can then be used to solve practical synthesis problems with high accuracy and using an appropriate cost function for template-based specification handling. A design example is presented to show the efficiency of the proposed method.