Inspection of separability of normal and migraine fNIRS data using LDA and PCA


Sen I., Akin A.

IEEE 14th Signal Processing and Communications Applications, Antalya, Turkey, 16 - 19 April 2006, pp.643-644 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/siu.2006.1659789
  • City: Antalya
  • Country: Turkey
  • Page Numbers: pp.643-644

Abstract

Functional near infrared spectroscopy (fNIRS) is an exciting, relatively new method to measure cognitive activity in the brain. Since the method measures blood oxygenation, it can be used for examining the differences between migraineurs and healthy people since migraine is a neurovascular disease. The aim of this study is to inspect the differences in neurovascular dynamics of healthy subjects and migraineurs. To achieve this aim, linear discriminant analysis (LDA) and principal component analysis (PCA) have been applied to acquired fNIRS signals, and parametric classification has been performed to quantify the separability.