Ischemia detection using supervised learning for hierarchical neural networks based on Kohonen-maps

L. Vladutu, S. Papadimitriou, S. Mavroudi, A. Bezerianos

Research output: Contribution to journalConference articlepeer-review

Abstract

The detection of ischemic episodes is a difficult pattern classification problem. The motivation for developing the Supervising Network - Self Organizing Map (sNet-SOM) model is to design computationally effective solutions for the particular problem of ischemia detection and other similar applications. The sNET-SOM uses unsupervised learning for the regions where the classification is not ambiguous and supervised for the "difficult" ones-in a two-stage learning process. The unsupervised learning approach extends and adapts the Self-Organizing Map (SOM) algorithm of Kohonen. The basic SOM is modified with a dynamic expansion process controlled with an entropy based criterion that allows the adaptive formation of the proper SOM structure. This extension proceeds until the total number of training patterns that are mapped to neurons with high entropy (therefore with ambiguous classification) reduces to a size manageable numerically with a proper supervised model. The second learning phase (supervised training) has the objective of constructing better decision boundaries of the ambigous regions. In this phase, a special supervised network is trained for the task of reduced computationally complexity- to perform the classification only of the ambiguous regions. After we tried with different classes of supervised networks, we obtained the best results with the Support Vector Machines (SVM) as local experts.

Original languageEnglish (US)
Pages (from-to)1688-1691
Number of pages4
JournalAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
Volume2
StatePublished - Dec 1 2001
Event23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Istanbul, Turkey
Duration: Oct 25 2001Oct 28 2001

Keywords

  • Computational complexity
  • Divide and conquer algorithms
  • Entropy
  • Ischemia
  • Principal component analysis
  • Radial basis functions
  • Self-organizing maps
  • Support vector machines
  • Vapnik-Chervonenkis dimension

ASJC Scopus subject areas

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

Fingerprint Dive into the research topics of 'Ischemia detection using supervised learning for hierarchical neural networks based on Kohonen-maps'. Together they form a unique fingerprint.

Cite this