标题:Automatic Seizure Detection Using Wavelet Transform and SVM in Long-Term Intracranial EEG
作者:Liu, Y.;Zhou, W.;Yuan, Q.;Chen, S.
作者机构:[Liu, Y] School of Information Science and Engineering, Shandong University, Jinan 250100, China;[ Zhou, W] School of Information Science and Engineer 更多
通讯作者:Liu, Y
通讯作者地址:[Liu, YX]Shandong Univ, Sch Informat Sci & Engn, Jinan 250100, Peoples R China.
来源:IEEE transactions on neural systems and rehabilitation engineering: a publication of the IEEE Engineering in Medicine and Biology Society
出版年:2012
卷:20
期:6
页码:749-755
DOI:10.1109/TNSRE.2012.2206054
关键词:Electroencephalogram (EEG);seizure detection;support vector machine (SVM);wavelet transform
摘要:Automatic seizure detection is of great significance for epilepsy long-term monitoring, diagnosis, and rehabilitation, and it is the key to closed-loop brain stimulation. This paper presents a novel wavelet-based automatic seizure detection method with high sensitivity. The proposed method first conducts wavelet decomposition of multi-channel intracranial EEG (iEEG) with five scales, and selects three frequency bands of them for subsequent processing. Effective features are extracted, such as relative energy, relative amplitude, coefficient of variation and fluctuation index at the selected scales, and then these features are sent into the support vector machine for training and classification. Afterwards a postprocessing is applied on the raw classification results to obtain more accurate and stable results. Postprocessing includes smoothing, multi-channel decision fusion and collar technique. Its performance is evaluated on a large dataset of 509 h from 21 epileptic patients. Experiments show that the proposed method could achieve a sensitivity of 94.46% and a specificity of 95.26% with a false detection rate of 0.58/h for seizure detection in long-term iEEG.
收录类别:EI;SCOPUS;SCIE
WOS核心被引频次:58
Scopus被引频次:91
资源类型:期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-84869393301&doi=10.1109%2fTNSRE.2012.2206054&partnerID=40&md5=ca8fa0d541a5b0e334f0aa022ba21a17
TOP