DocumentCode :
2504063
Title :
Seizure onset detection based on one sEMG channel
Author :
Conradsen, Isa ; Beniczky, Sándor ; Hoppe, Karsten ; Wolf, Peter ; Sams, Thomas ; Sorensen, Helge B D
fYear :
2011
fDate :
Aug. 30 2011-Sept. 3 2011
Firstpage :
7715
Lastpage :
7718
Abstract :
We present a new method to detect seizure onsets of tonic-clonic epileptic seizures based on surface electromyography (sEMG) data. The proposed method is generic and based on a single channel making it ideal for a small detection or monitoring device. The sEMG signal is high-pass filtered with a Butterworth filter with a cut-off frequency of 150 Hz. The number of zero-crossings with a hysteresis of ±50μV is the only feature extracted. The number of counts in a window of 1 second and the number of windows to make a detection is tested with a leave-one-out method. On 6 patients the method performs with a sensitivity of 100%, a median latency of 7.6 seconds and a median false detection rate of 0.04/h.
Keywords :
Butterworth filters; electromyography; feature extraction; filtering theory; high-pass filters; medical disorders; medical signal detection; medical signal processing; Butterworth filter; feature extraction; frequency 150 Hz; high-pass filter; hysteresis; median false detection; sEMG channel; seizure onset detection; surface electromyography; tonic-clonic epileptic seizures; Conferences; Epilepsy; Feature extraction; Monitoring; Muscles; Sensitivity; Training; Adult; Electromyography; False Positive Reactions; Female; Humans; Length of Stay; Male; Middle Aged; Seizures; Signal Processing, Computer-Assisted; Surface Properties; Time Factors; Young Adult;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE
Conference_Location :
Boston, MA
ISSN :
1557-170X
Print_ISBN :
978-1-4244-4121-1
Electronic_ISBN :
1557-170X
Type :
conf
DOI :
10.1109/IEMBS.2011.6091901
Filename :
6091901
Link To Document :
بازگشت