@Article{Haware_Wright_Morris-Data_fusio_Fouri-2011,
  author =	 {Haware, Rahul V. and Wright, Patrick R. and Morris, Kenneth 
                  R. and Hamad, Mazen L.},
  title =	 {Data fusion of {Fourier} transform infrared spectra and 
                  powder {X}-ray diffraction patterns for pharmaceutical 
                  mixtures},
  journal =	 {J Pharm Biomed Anal},
  year =	 {2011},
  volume =	 {56},
  number =	 {5},
  pages =	 {944-9},
  user =	 {wrightp},
  pmid =	 {21873013},
  doi = 	 {10.1016/j.jpba.2011.08.018},
  issn = 	 {1873-264X},
  issn = 	 {0731-7085},
  abstract =	 {Fusing complex data from two disparate sources has been 
                  demonstrated to improve the accuracy in quantifying active 
                  ingredients in mixtures of pharmaceutical powders. A 
                  four-component simplex-centroid design was used to prepare 
                  blended powder mixtures of acetaminophen, caffeine, aspirin 
                  and ibuprofen. The blends were analyzed by Fourier transform 
                  infra-red spectroscopy (FTIR) and powder X-ray diffraction 
                  (PXRD). The FTIR and PXRD data were preprocessed and 
                  combined using two different data fusion methods: fusion of 
                  preprocessed data (FPD) and fusion of principal component 
                  scores (FPCS). A partial least square (PLS) model built on 
                  the FPD did not improve the root mean square error of 
                  prediction. However, a PLS model built on the FPCS yielded 
                  better accuracy prediction than PLS models built on 
                  individual FTIR and PXRD data sets. The improvement in 
                  prediction accuracy of the FPCS may be attributed to the 
                  removal of noise and data reduction associated with using 
                  PCA as a preprocessing tool. The present approach 
                  demonstrates the usefulness of data fusion for the 
                  information management of large data sets from disparate 
                  sources.}
}