Tuesday, November 27, 2012

Feature selection strategies for quality screening of diesel samples by infrared spectrometry and linear discriminant analysis

CATEGORY: DIESEL
Talanta, Available online 20 November 2012, In Press, Accepted Manuscript
Feature selection strategies for quality screening of diesel samples by infrared spectrometry and linear discriminant analysis
Mohammadreza Khanmohammadi a, Amir Bagheri Garmarudi a, b, Miguel de la Guardia c
a Chemistry Department, Faculty of Science, IKIU, Qazvin, Iran
b Department of Chemistry & Polymer Laboratories, Engineering Research Institute, Tehran, Iran
c Department of Analytical Chemistry, University of Valencia, 50 Dr. Moliner Street, E-46100 Burjassot, Valencia, Spain
Abstract
Describes a rapid approach developed for the characterization of diesel quality, based on attenuated total reflectance – Fourier transform infrared (ATR-FTIR) spectrometry.  The method could be useful for diagnosing sample quality condition.
Linear discriminant analysis (LDA) was employed as a supervised technique to process the spectrometric data. The role of variable selection methods was also evaluated.  Researchers applied successive projection algorithm (SPA) and genetic algorithm (GA) feature selection techniques prior to the discriminative procedure.  Its purpose was to compare the effect of feature selection procedures on classification capability of IR spectrometry for the diesel samples according to their quality passed or quality failed situation.  Authors propose SPA-LDA together with ATR-FTIR spectrometry as a fast screening analytical test for the evaluation of quality passed/failed situation in diesel samples.
Full Text Source (Subscription or Fee): http://www.sciencedirect.com/science/article/pii/S0039914012009769

No comments:

Post a Comment