A Consensus Partial Least Squares Regression for Analysis of Near-Infrared Spectroscopy

Dan Peng; Qing Chen Nie

doi:10.4028/www.scientific.net/AMR.765-767.528

Paper Titles

Multi-Objective Coverage Alogrithm for WSN Based on Particle Swarm Optimization
p.508

Numerical Simulation of Turbulent Driven Secondary Flow in a 90° Bend Pipe
p.514

Delay Dependent H∞ Stochastic Stability Analysis for Stochastic Nonlinear Delay Hybrid Singular System
p.520

The Application of Cumulative Sum Feature Extraction Algorithm in Data Stream Anomaly Analysis before Earthquake
p.524

A Consensus Partial Least Squares Regression for Analysis of Near-Infrared Spectroscopy
p.528

Multi-Satellite Observation Scheduling Based on a Hybrid Ant Colony Optimization
p.532

Visual Modeling and Simulation of Plant Leaves
p.537

Discontinuous Deformation Analysis Visualization System Based on VTK
p.542

Research on Roles Modeling of Intelligent Force Based on Ontology
p.547

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 765-767A Consensus Partial Least Squares Regression for...

A Consensus Partial Least Squares Regression for Analysis of Near-Infrared Spectroscopy

Abstract:

To improve the prediction performance of partial least square regression algorithm (PLS), the consensus strategy was applied to develop the multivariate regression model using near-infrared (NIR) spectra and named as C-PLS. Coupled with the consensus strategy, this algorithm can take the advantage of reducing dependence on single model to obtain prediction precision and stability by randomly changing the calibration set. Through an optimization of the parameters involved in the model including criterion threshold and number of sub-models, a successful model was achieved by effectively combining many sub-models with different accuracy and diversity together. To validate the C-PLS algorithm, it was applied to measure the original extract concentration of beer using NIR spectra. The experimental results showed that the prediction ability and robustness of model obtained in subsequent partial least squares calibration using consensus strategy was superior to that obtained using conventional PLS algorithm, and the root mean square error of prediction can improve by up to 45.2%, indicating that it is an efficient tool for NIR spectra regression.