Pattern recognition algorithms for tissue diagnosis by near-infrared FT-Raman spectroscopy

S. Nie, Y. Li, D. C.B. Redd, N. T. Yu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A preliminary study on near-infrared laser-excited Fourier-transform (FT)-Raman spectroscopy is presented. Several conventional pattern classification algorithms are evaluated for accuracy and effectiveness, including multivariate linear regression, principal component analysis, mean difference projection, decision plane analysis, Bayes decision theory, and principal peak ratio. Pattern recognition schemes based on neural networks are also tested, such as backpropagation and K-nearest neighbors methods. It is demonstrated that pattern recognition algorithms are useful in the diagnosis and classification of diseased and healthy tissues.

Original languageEnglish (US)
Title of host publicationProceedings of the Annual Conference on Engineering in Medicine and Biology
PublisherPubl by IEEE
Pages1747-1748
Number of pages2
Editionpt 4
ISBN (Print)0780302168
StatePublished - 1991
Externally publishedYes
EventProceedings of the 13th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Orlando, FL, USA
Duration: Oct 31 1991Nov 3 1991

Publication series

NameProceedings of the Annual Conference on Engineering in Medicine and Biology
Numberpt 4
Volume13
ISSN (Print)0589-1019

Other

OtherProceedings of the 13th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
CityOrlando, FL, USA
Period10/31/9111/3/91

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Fingerprint

Dive into the research topics of 'Pattern recognition algorithms for tissue diagnosis by near-infrared FT-Raman spectroscopy'. Together they form a unique fingerprint.

Cite this