Ultra-fast epileptic seizure detection using EMD based on multichannel electroencephalogram

Tunghai University Institutional Repository > 管理學院 > 資訊管理學系所 > 會議論文 > Item 310901/24912

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://140.128.103.80:8080/handle/310901/24912

题名:	Ultra-fast epileptic seizure detection using EMD based on multichannel electroencephalogram
作者:	Chen, W.;Lam, Y.-Y.;Shen, C.-P.;Sung, H.-Y.;Lin, J.-W.;Chiu, M.-J.;Lai, F.
贡献者:	Department of Information Management, Tunghai University
日期:	2013-11-10
上传时间:	2014-06-18T06:53:57Z (UTC)
出版者:	Chania
摘要:	We present a system to detect seizure and spike in Epilepsy Electroencephalogram (EEG) analysis and characterize different epilepsy EEG types. After extracting features from three EEG types, Normal, Seizure and Spike, with Empirical Mode Decomposition (EMD), we do Analysis of variance (ANOVA) to classify conspicuous features and low-resolution features, and build Gaussian distributions of conspicuous features for probability density function (PDF) to do classification. Using EMD, the recognition rate improved from 70% to 90%. With ANOVA, the recognition rate can reach 99%. The linear model accelerates the system from 2 hours to 90 seconds compare to the previous approach. ? 2013 IEEE.
關聯:	13th IEEE International Conference on BioInformatics and BioEngineering, IEEE BIBE 2013 13th IEEE International Conference on BioInformatics and BioEngineering, IEEE BIBE 2013
显示于类别:	[資訊管理學系所] 會議論文

文件中的档案:

档案	大小	格式	浏览次数
index.html	0Kb	HTML	418	检视/开启

在THUIR中所有的数据项都受到原著作权保护.