Classification of Multi-Types of EEG Time Series Based on Embedding Dimension Characteristic Parameter

We have studied the detection of epileptic seizure by EEG signals based on embedding dimension as the input characteristic parameter of artificial neural networks has been studied in the research before. The results of the experiments showed that the overall accuracy as high as 100% can be achieved for distinguishing normal and epileptic EEG time series. In this paper, classification of multi-types of EEG time series based on embedding dimension as input characteristic parameter of artificial neural network will be studied, and the probabilistic neural network (PNN) will be also employed as the classifier for comparing the results with those obtained before. Cao’s method is also applied for computing the embedding dimension of normal and epileptic EEG time series. The results show that different types of EEG time series can be classified using the embedding dimension of EEG time series as characteristic parameter when the number of feature points exceed some value, however, the accuracy were not satisfied up to now, some work need to be done to improve the classification accuracy.