Automated Detection of Epileptic Seizure Using Artificial Neural Network
The embedding dimension of electroencephalogram (EEG) time series is used as the input feature of artificial neural network for detecting epileptic seizure automatedly. Caos method is applied for computing the embedding dimension of normal and epileptic EEG time series. The probabilistic neural networks (PNN) is used in this paper for the automated detection of epilepsy. The results show that the overall accuracy as high as 100％ can be achieved by using the method proposed in this paper. An interesting phenomenon is also found by Caos method that normal EEG time series is of randomness, whereas epileptic EEG time series is of some degree of determinacy, which means that epileptic EEG time series can be predicted well.
Embedding dimension electroencephalogram (EEG) epilepsy Caos method PNN artificial neural network seizure
Ye Yuan Yue Li Dongyan Yu Danilo P. Mandic
College of Communication Engineering Jilin University Changchun, China Department of Electrical and Electronic Engineering Imperial College London, UK
国际会议
上海
英文
1959-1962
2008-05-16（万方平台首次上网日期，不代表论文的发表时间）