Use this URL to cite or link to this record in EThOS:
Title: Investigation and application of functional data analysis technology for calibration of near-infrared spectroscopic data
Author: Jiang, Cheng
Awarding Body: University of Newcastle Upon Tyne
Current Institution: University of Newcastle upon Tyne
Date of Award: 2009
Availability of Full Text:
Access from EThOS:
This thesis focuses on the investigation and application of functional Data Analysis methodologies to address calibration challenges of spectroscopic data. Of particular interest is the area of calibration of near-infrared spectral data. Different strategies to construct functional linear calibration methodologies and a number of functional linear calibration approaches are initially discussed. A novel approach is then proposed to compare functional linear calibration methodologies with a well established and widely used methodology in the chemometrics area, Partial Least Squares (PLS). From this perspective, a common framework can be established to investigate the similarities and differences between these two methodologies. It is shown that the model structures of these two methodologies are similar but the difference is the selection of basis function to represent the original spectral data. As opposed to the loadings of PLS, B-splines capture local features of the data.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available