A Hybrid Model of Maximum Margin Clustering Method and Support Vector Regression for Noninvasive Electrocardiographic Imaging

Noninvasive electrocardiographic imaging, such as the reconstruction of myocardial transmembrane potentials (TMPs) distribution, can provide more detailed and complicated electrophysiological information than the body surface potentials (BSPs). However, the noninvasive reconstruction of the TMPs from BSPs is a typical inverse problem. In this study, this inverse ECG problem is treated as a regression problem with multi-inputs (BSPs) and multioutputs (TMPs), which will be solved by the Maximum Margin Clustering- (MMC-) Support Vector Regression (SVR) method. First, the MMC approach is adopted to cluster the training samples (a series of time instant BSPs), and the individual SVR model for each cluster is then constructed. For each testing sample, we find its matched cluster and then use the corresponding SVR model to reconstruct the TMPs. Using testing samples, it is found that the reconstructed TMPs results with the MMC-SVR method are more accurate than those of the single SVR method. In addition to the improved accuracy in solving the inverse ECG problem, the MMC-SVR method divides the training samples into clusters of small sample sizes, which can enhance the computation efficiency of training the SVR model.

Download Full-text

Development of a Hierarchical Support Vector Regression-Based In Silico Model for Caco-2 Permeability

Pharmaceutics ◽

10.3390/pharmaceutics13020174 ◽

2021 ◽

Vol 13 (2) ◽

pp. 174 ◽

Cited By ~ 1

Author(s):

Giang Huong Ta ◽

Cin-Syong Jhang ◽

Ching-Feng Weng ◽

Max K. Leong

Keyword(s):

Drug Discovery ◽

Support Vector Regression ◽

Human Colon ◽

Qsar Model ◽

Quantitative Structure Activity Relationship ◽

Support Vector ◽

Human Colon Carcinoma Cell ◽

Drug Discovery And Development ◽

Training Samples ◽

Experimental Values

Drug absorption is one of the critical factors that should be taken into account in the process of drug discovery and development. The human colon carcinoma cell layer (Caco-2) model has been frequently used as a surrogate to preliminarily investigate the intestinal absorption. In this study, a quantitative structure–activity relationship (QSAR) model was generated using the innovative machine learning-based hierarchical support vector regression (HSVR) scheme to depict the exceedingly confounding passive diffusion and transporter-mediated active transport. The HSVR model displayed good agreement with the experimental values of the training samples, test samples, and outlier samples. The predictivity of HSVR was further validated by a mock test and verified by various stringent statistical criteria. Consequently, this HSVR model can be employed to forecast the Caco-2 permeability to assist drug discovery and development.

Download Full-text

Support Vector Regression for the Modeling and Synthesis of Near-Field Focused Antenna Arrays

Electronics ◽

10.3390/electronics8111352 ◽

2019 ◽

Vol 8 (11) ◽

pp. 1352 ◽

Cited By ~ 1

Author(s):

Rafael González Ayestarán

Keyword(s):

Support Vector Regression ◽

Antenna Arrays ◽

Near Field ◽

Computational Cost ◽

Support Vector ◽

Analysis Tool ◽

Training Samples ◽

Learning Capabilities ◽

Novel Method ◽

The Individual

The powerful support vector regression framework is proposed in a novel method for near-field focusing using antenna arrays. By using this machine-learning method, the set of weights required in the elements of an array can be calculated to achieve an assigned near-field distribution focused on one or more positions. The computational cost is concentrated in an initial training process so that the trained system is fast enough for applications where moving devices are involved. The increased learning capabilities of support vector machines allow using a reduced number of training samples. Thus, these training samples may be generated with a prototype or a convenient electromagnetic analysis tool, and hence realistic effects, such as coupling or the individual radiation patterns of the elements of the arrays, are accounted for. Illustrative examples are presented.

Download Full-text

Wine Evaluation Modeling Based on Lasso and Support Vector Regression

Journal of Advanced Computational Intelligence and Intelligent Informatics ◽

10.20965/jaciii.2017.p0998 ◽

2017 ◽

Vol 21 (6) ◽

pp. 998-1008

Author(s):

Yanyun Yao ◽

Bing Xu ◽

Jinghui He ◽

◽

Keyword(s):

Support Vector Regression ◽

Nonlinear Effect ◽

Evaluation System ◽

Evaluation Model ◽

Digital Simulation ◽

Objective Evaluation ◽

Support Vector ◽

Lasso Regression ◽

Wine Quality ◽

Training Samples

Wine consumption is gaining popularity, and significant attention has been given to its quality. In the present paper, an objective evaluation model along with a reliability test via Lasso and nonlinear effect test via support vector regression (SVR) is proposed. The digital simulation is finished with the experimental data obtained from the A problem of CUMCM-2012 (China Undergraduate Mathematical Contest in Modeling in 2012). The results of Lasso regression show that the wine quality mainly depends upon eight physicochemical indicators. Further research results of SVR imply that with several training samples, a good evaluation can be realized, denoting that our model based on Lasso SVR can significantly reduce the costs of measurement and appraisal. Compared to other relevant articles, this paper builds an objective and credible wine evaluation system where the physicochemical indicators and the latent nonlinear effect are considered. Moreover, the evaluation costs are taken into account.

Download Full-text

Research on water pollution prediction of township enterprises based on support vector regression machine

E3S Web of Conferences ◽

10.1051/e3sconf/202122802014 ◽

2021 ◽

Vol 228 ◽

pp. 02014

Author(s):

Yue Wang ◽

Song Xue ◽

Junming Ding

Keyword(s):

Water Pollution ◽

Support Vector Regression ◽

Rural Areas ◽

Rural Economy ◽

Negative Impact ◽

Water Environment ◽

Small Sample ◽

Support Vector ◽

Rural Water

The construction and development of township enterprises plays a key role in promoting the development of rural economy. With the implementation of the rural revitalization strategy, township enterprises develop rapidly, but there are problems in the development process that have a negative impact on the quality of local rural water environment. Rural water environment is related to the health of farmers, the healthy development of agriculture and the sustainable development of rural areas, so it is necessary to predict the water pollution of township enterprises. The application of support vector regression forecasting model to the prediction of water pollution of township enterprises can better predict the water pollution of township enterprises with the characteristics of complexity, nonlinear and small sample. This intelligent forecasting method will help to scientifically prevent the development of township enterprises from having negative impact on the quality of local water environment.

Download Full-text

Research on Patch Near-Field Acoustic Holography

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.105-107.196 ◽

2011 ◽

Vol 105-107 ◽

pp. 196-199 ◽

Cited By ~ 1

Author(s):

Hai Chao Zhu ◽

Zhi Min Chen ◽

Xiang Hua Du ◽

Rong Fu Mao

Keyword(s):

Support Vector Regression ◽

Sound Pressure ◽

Near Field ◽

Measured Data ◽

Experimental Results ◽

Support Vector ◽

Reconstruction Accuracy ◽

Acoustic Holography ◽

Training Samples ◽

Regression Functions

Support vector regression is used to establish a kind of patch near-field acoustic holography. The regression functions are constructed by treating the measured data on the patch holography as training samples, and then the data outside the measurement aperture are extrapolated. The experimental results show that the extrapolation of the sound pressure outside the smaller initial hologram aperture may be realized easily and effectively, and the reconstruction accuracy is satisfactory.

Download Full-text

Forest Coverage Prediction Based on Least Squares Support Vector Regression Algorithm

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.446-449.2978 ◽

2012 ◽

Vol 446-449 ◽

pp. 2978-2982

Author(s):

Fang Xiao

Keyword(s):

Regression Model ◽

Least Squares ◽

Support Vector Regression ◽

Prediction Error ◽

Support Vector ◽

Support Vector Regression Model ◽

Training Samples ◽

Forest Coverage ◽

Coverage Prediction ◽

Mean Prediction Error

Forest coverage prediction based on least squares support vector regression algorithm is presented in the paper.Forest coverage data of Heilongjiang from 1994 to 2005 are used to study the effectiveness of least squares support vector regression algorithm.The prediction results of the proposed least squares support vector regression model by using the training samples with the different dimensional input vector are given in the study. It can be seen that the prediction results of the proposed least squares support vector regression model by using the training samples with the 3-dimensional input vector have best prediction results.The comparison of forest coverage forecasting error between the proposed least squares support vector regression model and the support vector regression model is given, among which mean prediction error of the proposed least squares support vector regression model is 0.0149 and mean prediction error of the support vector regression model is 0.0322 respectively.The experimental results show that the proposed least squares support vector regression model has more excellent forest coverage forecasting results than the support vector regression model.

Download Full-text

Mapping Burn Severity of Forest Fires in Small Sample Size Scenarios.

10.32920/14638737.v1 ◽

2021 ◽

Author(s):

Zhong Zheng ◽

Yongnian Zeng ◽

Songnian Li ◽

Wei Huang

Keyword(s):

Regression Analysis ◽

Support Vector Regression ◽

Forest Fires ◽

Small Sample Size ◽

Mapping Method ◽

Small Sample ◽

Burn Severity ◽

Support Vector ◽

Analysis Method ◽

Field Plots

Mapping burn severity of forest fires can contribute significantly to understanding, quantifying and monitoring of forest fire severity and its impacts on ecosystems. In recent years, several remote sensing-based methods for mapping burn severity have been reported in the literature, of which the implementations are mainly dependent on several field plots. Therefore, it is a challenge to develop alternative method of mapping burn severity using limited number of field plots. In this study, we proposed a support vector regression based method using multi-temporal satellite data to map the burn severity, evaluated its performance by calculating correlations between the predicted and the observed Composite Burn Index, and compared the performance with that of the regression analysis method (based on dNBR). The results show that the performance of support vector regression based mapping method is more accurate (RMSE = 0.46–0.57) than that of regression analysis method (RMSE = 0.53–0.68). Even with fewer training sets, it can map the detailed distribution of burn severity of forest fires and can achieve relatively better generalization, compared to regression analysis burn severity mapping methods. It could be concluded that the proposed support vector regression based mapping method is an alternative to the regression analysis method in small sample size scenarios. This method with excellent generalization performance should be recommended for future studies on burn severity of forest fires.

Download Full-text

Benchmarking support vector regression against partial least squares regression and artificial neural network: Effect of sample size on model performance

Journal of Near Infrared Spectroscopy ◽

10.1177/0967033517734945 ◽

2017 ◽

Vol 25 (6) ◽

pp. 381-390 ◽

Cited By ~ 8

Author(s):

Rikke Ingemann Tange ◽

Morten Arendt Rasmussen ◽

Eizo Taira ◽

Rasmus Bro

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Sample Size ◽

Support Vector Regression ◽

Real World ◽

Model Performance ◽

Small Sample ◽

Support Vector ◽

High Dimensions ◽

Artificial Neural

It has become easy to obtain multivariate chemical data of high dimensions. However, it may be expensive or time consuming to obtain a large number of samples or to acquire reference measures, so the number of samples available for multivariate calibration modelling may be limited. If data contains nonlinear relationships, nonlinear methods are required for the calibration task. The combination of limited amounts of data of high dimensions and highly flexible nonlinear methods may result in overfitted models which in turn perform badly on new data. Therefore, for real world applications, it is desirable to understand how the sample size affects model prediction performance. For this purpose, we compared partial least squares regression, artificial neural network, and support vector regression applied to three real world nonlinear datasets of which two were of high dimensions. We evaluated the effect of calibration sample size (i) on test set performance, including variation in test set performance due to sampling variation and (ii) tested if the cross-validated performance was adequate for assessing the predictive ability. We demonstrated the applicability of artificial neural network and support vector regression for real world data of limited size and showed that support vector regression had advantages over artificial neural network: (i) fewer calibration samples were required to obtain a desired model performance, (ii) support vector regression was less sensitive to sampling variation for small sample sets and (iii) cross-validation was an approximately unbiased option for evaluating the true support vector regression model performance even for small sample sets.

Download Full-text

Quantum Support Vector Regression for Disability Insurance

Risks ◽

10.3390/risks9120216 ◽

2021 ◽

Vol 9 (12) ◽

pp. 216

Author(s):

Boualem Djehiche ◽

Björn Löfdahl

Keyword(s):

Support Vector Regression ◽

Quantum Computer ◽

Transition Probabilities ◽

Disability Insurance ◽

Quantum States ◽

Inner Product ◽

Support Vector ◽

Insurance Company ◽

Regression Problem ◽

Quantum Feature

We propose a hybrid classical-quantum approach for modeling transition probabilities in health and disability insurance. The modeling of logistic disability inception probabilities is formulated as a support vector regression problem. Using a quantum feature map, the data are mapped to quantum states belonging to a quantum feature space, where the associated kernel is determined by the inner product between the quantum states. This quantum kernel can be efficiently estimated on a quantum computer. We conduct experiments on the IBM Yorktown quantum computer, fitting the model to disability inception data from a Swedish insurance company.

Download Full-text