Analysis of Nonlinear EEG Time Series Based on Local Support Vectors Machine Model
Analysis of Nonlinear EEG Time Series Based on Local Support Vectors Machine Model
复制标题
基于局部支持向量机模型的非线性脑电时间序列分析
DOI：
10.1007/978-3-642-31965-5_61
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
孙丽莎
中科院分区：
文献类型：
--
作者：
孙丽莎
The modeling of Electroencephalography (EEG) signals is an important issue in clinical diagnosis of brain functional diseases. The proposed method using support vectors machine (SVM) with the structure risk minimization provides us an effective way of learning machine and modeling. The problem of solving the quadratic programming becomes a bottle-neck of training the SVM due to the long time of SVM training. In this paper, a local-SVM algorithm is proposed for modeling EEG time series. The local model is developed for improving the prediction of EEG signals. Furthermore, the presented model is used to detect the epilepsy from EEG signals in which dynamical characteristics are difference between normal and epilepsy EEG signals. Several experimental results were given to show that the training of the local-SVM provides a good behavior. Finally, the local SVM approach significantly improves the prediction and detection precision.
登录
查看更多内容
DOI：
10.5555/299094
发表时间：
1999-02
期刊：
--
影响因子：
--
作者：
B. Scholkopf;C. Burges;Alex Smola
通讯作者：
B. Scholkopf;C. Burges;Alex Smola
影响因子：
2.9
作者：
Keerthi, SS;Shevade, SK;Murthy, KRK
通讯作者：
Murthy, KRK
影响因子：
4.8
作者：
Burges, CJC
通讯作者：
Burges, CJC
DOI：
--
发表时间：
2000
期刊：
--
影响因子：
--
作者：
C. Campbell
通讯作者：
C. Campbell
DOI：
10.17877/de290r-14262
发表时间：
1998
期刊：
Technical reports
影响因子：
--
作者：
T. Joachims
通讯作者：
T. Joachims