Abstract
Classification of patients using EEG recordings is a very difficult and application relevant problem in various medical fields. It is difficult because of the very complex signal structure and bad signal quality (noise, artifacts) and it is relevant to submit diagnosis and therapy for example in psychopathology. This paper gives a short summary on current investigations with neural networks in the field of EEG analysis. It covers the important role of data preprocessing as well as some general considerations about control of learning and generalization in neural networks. Practical results of a case study discriminating three groups of subjects (depressives, psychotics and control subjects) will be given. The results had been obtained using feed forward networks with simple topologies and with problem related design, embedded in the special neural network EEG experimental environment N2E4 developed at the Research Group Neural Networks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Anderer, P., Klöppel, B., Saletu, B., Semlitsch, H.V., Werner, H.: Klassifikation Demenler Patienten basierend auf der topographischen Verteilung des Elektroenzephalogramms mit Hilfe künstlicher neuronaler Netzwerke. in “Dementielle Syndrome — eine Standortbestimmung, Teil II” (VIP Verlag), 1993
Anderer, P., Klöppel, B., Saletu, B., Semlitsch, KV, Werner, H.: Ein künstliches neuronales Netzwerk zur Klassifikation dementer Patienten basierend auf der topographischen Verteilung der langsamen EEG Aktivität Beitrag zum Deutsch-Österreichischen Neurologenkongress, Springer Verlag Wien, New York, 1993
Anderer, P.; Saletu, B.; Klöppel, B.; Semlitsch, KV; Werner, H.: Discrimination between demented patients and normals based on topographic slow wave EEG activity using artificial neural networks; to appear in EEG-Journal, 1993
Dietrich, Carsten: Einsatz von Schrittweitensteuerungen beim Training Neuronaler Netze (am Beispiel des Backpropagating Algorithmus unter Verwendung von Fuzzy Logik), Master Thesis at the Dept. of Mathematics and Computer Science, University of Kassel, 1994
Gallhofer B., Jantscher M., Klöppel B., Gruppe, H.: Funktionstopographie der Verarbeitung kognitiver Aufgaben unter dem Einfluß lateralisierter akustischer Störreize — erste Daten, (Abstract) in Brain Topography — Journal of Functional Neurophysiology (2. Deutsches EEG/EP Mapping Meeting, Gießen, 10.–11. 09. 1993
Gevins, A.S.; Stone, R. K.; Ragsdale, S.D.: Differentiating the effects of three benzodiazepines on non-REM sleep EEG spectra. A neural-network pattern classification analysis; Neuropsychobiology 19, pp 108–115, 1988
Grötzinger, M., Klöppel, B., Röschke, J: Automatic recognition of rapid eye movement (REM) sleep by artificial neural networks. Gene-Brain-Behavior, proceedings of the 21st Göttingen Neurobiology Conference, 4. — 6.6.1993: 873
Grötzinger, M, Klöppel, B.; Röschke, J.: Online evaluation of sleep EEG data by artificial neural networks, submitted to Journal of Sleep Research
Klöppel, Bert: Applications of neural networks for EEG analysis, Neuropsychobiology, Vol. 29, 1/94 p. 39–46, 1994
Klöppel, Bert: Classification of evoked potentials by neural networks, Neuropsychobiology, Vol. 29, 1/94 p. 47–52, 1994
Klöppel, Bert: Neural networks as a new method for EEG analysis, Neuropsychobiology, Vol 29, 1/94 p. 33–38, 1993
Klöppel, Bert: Neural Networks for EEG classification: First Results, Experiences and new Approaches. in Proceedings CNS Monitoring Workshop, 1992, Wien, Maudrich, in print
Klöppel, Bert: Stabilität und Kapazität neuronaler Netzwerke am Beispiel der EEG-Klassifikation; Ph.D. Thesis at the Dept. of Mathematics and Computer Science, University of Kassel, 1994
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gallhofer, B., Klöppel, B., Werner, H. (1994). Application of neural networks for the classification of depressive and psychotic patients using multi channel EEG recordings. In: Reusch, B. (eds) Fuzzy Logik. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-79386-8_31
Download citation
DOI: https://doi.org/10.1007/978-3-642-79386-8_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58649-4
Online ISBN: 978-3-642-79386-8
eBook Packages: Springer Book Archive