DocumentCode
636409
Title
Automatic optimization of parameters for seizure detection systems
Author
Dollfuss, P. ; Hartmann, Manfred M. ; Skupch, A. ; Furbass, F. ; Kluge, T.
Author_Institution
Austrian Inst. of Technol., Vienna, Austria
fYear
2013
fDate
3-7 July 2013
Firstpage
1976
Lastpage
1979
Abstract
A parameter optimization method for an automatic seizure detection algorithm using the Nelder Mead algorithm is presented. A suitable cost function for joint optimization of sensitivity and false alarm rate is proposed. The optimization is done using EEG datasets from 23 patients and validated on datasets from another 23 patients. The resulting sensitivity was 82.3% with a false alarm rate of 0.24 FA/h. This is a reduction of the false alarm rate by 1.58 FA/h with an acceptable loss of sensitivity of 4.3%.
Keywords
electroencephalography; medical disorders; medical signal detection; optimisation; parameter estimation; EEG datasets; Nelder Mead algorithm; automatic seizure detection algorithm; cost function; false alarm rate; parameter automatic optimization; parameter optimization method; seizure detection system; sensitivity joint optimization; Cost function; Electroencephalography; Epilepsy; Optimization methods; Sensitivity; Training;
fLanguage
English
Publisher
ieee
Conference_Titel
Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE
Conference_Location
Osaka
ISSN
1557-170X
Type
conf
DOI
10.1109/EMBC.2013.6609916
Filename
6609916
Link To Document