Document Detail

Genetic algorithm-based protocol for coupling digital filtering and partial least-squares regression: application to the near-infrared analysis of glucose in biological matrices.
MedLine Citation:
PMID:  8694264     Owner:  NLM     Status:  MEDLINE    
A multivariate calibration procedure is described that is based on the use of a genetic algorithm (GA) to guide the coupling of bandpass digital filtering and partial least-squares (PLS) regression. The measurement of glucose in three different biological matrices with near-infrared spectroscopy is employed to develop this protocol. The GA is employed to optimize the position and width of the bandpass digital filter, the spectral range for PLS regression, and the number of PLS factors used in building the calibration model. The optimization of these variables is difficult because the values of the variables employ different units, resulting in a tendency for local optima to occur on the response surface of the optimization. Two issues are found to be critical to the success of the optimization: the configuration of the GA and the development of an appropriate fitness function. An integer representation for the GA is employed to overcome the difficulty in optimizing variables that are dissimilar, and the optimal GA configuration is found through experimental design methods. Three fitness function calculations are compared for their ability to lead the GA to better calibration models. A fitness function based on the combination of the mean-squared error in the calibration set data, the mean-squared error in the monitoring set data, and the number of PLS factors raised to a weighting factor is found to perform best. Multiple random drawings of the calibration and monitoring sets are also found to improve the optimization performance. Using this fitness function and three random drawings of the calibration and monitoring sets, the GA found calibration models that required fewer PLS factors yet had similar or better prediction abilities compared to calibration models found through an optimization protocol based on a grid search method.
R E Shaffer; G W Small; M A Arnold
Related Documents :
23365864 - Radiofrequency ablation planning beyond simulation.
17592584 - Experimental study of non-linear second-order analytical data with focus on the second-...
24133454 - Methods and approaches in the topology-based analysis of biological pathways.
22923304 - Qualitative translation of relations from biopax to sbml qual.
21045324 - Overland flow computations in urban and industrial catchments from direct precipitation...
12209394 - Genetics of fluctuating asymmetry in pupal traits of the speckled wood butterfly (parar...
Publication Detail:
Type:  Journal Article; Research Support, U.S. Gov't, P.H.S.    
Journal Detail:
Title:  Analytical chemistry     Volume:  68     ISSN:  0003-2700     ISO Abbreviation:  Anal. Chem.     Publication Date:  1996 Aug 
Date Detail:
Created Date:  1996-08-29     Completed Date:  1996-08-29     Revised Date:  2007-11-14    
Medline Journal Info:
Nlm Unique ID:  0370536     Medline TA:  Anal Chem     Country:  UNITED STATES    
Other Details:
Languages:  eng     Pagination:  2663-75     Citation Subset:  IM    
Department of Chemistry, Ohio University, Athens 45701, USA.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Glucose / analysis*
Regression Analysis
Grant Support
Reg. No./Substance:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Miniature sodium-selective ion-exchange optode with fluorescent pH chromoionophores and tunable dyna...
Next Document:  Dynamic on-column pH monitoring in capillary electrophoresis: application to volume-limited outlet v...