Application of Generalized Dynamic Neural Networks to Biomedical Data

Author

Leistritz, L. ; Galicki, M. ; Kochs, E. ; Zwick, E.B. ; Fitzek, C. ; Reichenbach, J.R. ; Witte, H.

Author_Institution

Inst. of Med. Stat., Comput. Sci., & Documentation, Friedrich-Schiller-Univ., Jena

Volume

53

Issue

11

fYear

2006

Firstpage

2289

Lastpage

2299

Abstract

This paper reviews the application of continuous recurrent neural networks with time-varying weights to pattern recognition tasks in medicine. A general learning algorithm based on Pontryagin´s maximum principle is recapitulated, and possibilities of improving the generalization capabilities of these networks are given. The effectiveness of the methods is demonstrated by three different real-world examples taken from the fields of anesthesiology, orthopedics, and radiology

Keywords

bioelectric potentials; biomedical MRI; gait analysis; learning (artificial intelligence); maximum principle; medical image processing; pattern recognition; recurrent neural nets; reviews; Pontryagin maximum principle; anesthesiology; biomedical data; continuous recurrent neural networks; general learning algorithm; generalized dynamic neural networks; orthopedics; pattern recognition; radiology; reviews; Bioinformatics; Documentation; Medical diagnostic imaging; Neural networks; Orthopedic surgery; Pattern recognition; Radiology; Recurrent neural networks; Signal processing algorithms; Statistics; Classification of temporal sequences; dynamic neural networks (DNNs); optimal control; pattern recognition; Algorithms; Biomedical Engineering; Databases, Factual; Diagnosis, Computer-Assisted; Information Storage and Retrieval; Neural Networks (Computer); Pattern Recognition, Automated; Signal Processing, Computer-Assisted;

fLanguage

English

Journal_Title

Biomedical Engineering, IEEE Transactions on

Publisher

ieee

ISSN

0018-9294

Type

jour

DOI

10.1109/TBME.2006.881766

Filename

1710171