Domain Adaptation for Pathologic Oscillations

  • Rory Lewis
  • Chad A. Mello
  • James Ellenberger
  • Andrew M. White
Conference paper

DOI: 10.1007/978-3-642-41218-9_40

Volume 8170 of the book series Lecture Notes in Computer Science (LNCS)
Cite this paper as:
Lewis R., Mello C.A., Ellenberger J., White A.M. (2013) Domain Adaptation for Pathologic Oscillations. In: Ciucci D., Inuiguchi M., Yao Y., Ślęzak D., Wang G. (eds) Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing. RSFDGrC 2013. Lecture Notes in Computer Science, vol 8170. Springer, Berlin, Heidelberg

Abstract

This paper presents a platform to bridge datamining techniques and concepts in the field of neurosciences with state-of-the-art data mining, in particular domain adaptation. In non-clinical environs, once an exhaustive search for a particular item of knowledge seems to be impractical, there is the natural tendency to switch to heuristic methods to expedite the search. Conversely, when neuroscientists are in the same situation, they will trust exhaustive searches rather than heuristics such as clinical decision-support systems (CDSS). This is particularly when electroencephalography (EEG) sequences are used to search for pathologic oscillations in the brain. The purpose of this paper is to promising results illustrating how an intelligent agent can data mine explicit types of pathologic oscillations in the human brain.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Rory Lewis
    • 1
    • 2
  • Chad A. Mello
    • 2
  • James Ellenberger
    • 2
  • Andrew M. White
    • 1
  1. 1.Departments of Pediatrics & NeurologyUniversity of Colorado DenverAuroraUSA
  2. 2.Department of Computer ScienceUniversity of Colorado at Colorado SpringsColorado SpringsUSA