Seizure detection on prolonged-EEG videos

Author

Shen, Yu Ting ; Chung, Pau Choo ; Thonnet, Monnique ; Chauvel, Patrick

Author_Institution

Dept. of Electr. Eng., Nat. Cheng Kung Univ., Tainan

fYear

2008

fDate

18-21 May 2008

Firstpage

2030

Lastpage

2033

Abstract

This paper develops the fusion of audio and video features by Dempster-Shafer theory for seizure detection. In audio analysis, Mel frequency cepstral coefficient (MFCC) and zero-crossing rate (ZCR) are applied to hidden Markov model (HMM) for audio type classification and probability computation. The results are transferred to belief of evidence and combined with the results from videos. Results have been tested by data obtained from several seizure patients and showed promising results.

Keywords

audio signal processing; electroencephalography; hidden Markov models; medical image processing; medical signal detection; video signal processing; Dempster-Shafer theory; HMM; Mel frequency cepstral coefficient; audio type classification; hidden Markov model; prolonged-EEG videos; seizure detection; zero-crossing rate; Cepstral analysis; Cepstrum; Electroencephalography; Epilepsy; Feature extraction; Hidden Markov models; Mel frequency cepstral coefficient; Storms; Testing; Videos; Dempster-Shafer fusion; Hidden Markov Model (HMM); multimodal fusion; seizure detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2008. ISCAS 2008. IEEE International Symposium on

Conference_Location

Seattle, WA

Print_ISBN

978-1-4244-1683-7

Electronic_ISBN

978-1-4244-1684-4

Type

conf

DOI

10.1109/ISCAS.2008.4541846

Filename

4541846