Spectral Data Modeling Based on Feature Extraction and Extreme Support Vector Regression

Shao Wei Liu; Dong Yan; Zhi Hua Liu; Jian Tang

doi:10.4028/www.scientific.net/AMM.128-129.297

Paper Titles

Selection and Optimization in Vibration Isolation Structure of Marine Podded SSP Propulsion
p.280

Solutions of Single Point of Failure in Intrusion Detection System
p.285

Solving Collaborative Manufacturing Resources Optimization Deployment Problems Based on Improved DNA Genetic Algorithm
p.289

Solving Decision Problems with Mathematical Expectation
p.293

Spectral Data Modeling Based on Feature Extraction and Extreme Support Vector Regression
p.297

Spectral Properties of Broadband Pumped Optical Parametric Amplification
p.301

Spline Function Method Analysis Nature Frequency of Annular Foundations
p.307

Study on Data Acquisition and Measurement System of Occupant Restraint Test Bed
p.314

Study on Driving Characteristics of Discrete Rod by Different Initiation Styles
p.318

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 128-129Spectral Data Modeling Based on Feature Extraction...

Spectral Data Modeling Based on Feature Extraction and Extreme Support Vector Regression

Abstract:

Spectral data such as near-infrared spectrum and frequency spectrum can simply the modeling of the difficulty-to-measured parameters. A novel modeling approach combined the feature extraction with extreme support vector regression (ESVR) is proposed. The latent variables space based feature extraction method can successfully complete the dimension reduction and independent variable extraction. The novel proposed ESVR leaning algorithm is realized by using extreme learning machine (ELM) kernel as SVR kernel, which is used to construct final models with better generalization. The experimental results based on the orange juice near-infrared spectra demonstrate that the proposed approach has better generalization performance and prediction accuracy.