Novel Automatic Epilepsy Detection Method Multi-weight Transition Network.
Journal:
Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
Published Date:
Jul 1, 2019
Abstract
The automatic diagnosis of epilepsy using Electroencephalogram (EEG) signals had always been an important research direction. A novel automatic epilepsy detection method based on multi-weight transition network was proposed in this paper. The epileptic EEG signal was first transformed into complex network according to our proposed multi-weight transition network algorithm. Then, based on the statistical characteristics of the multi-weight transition network, the degree of network and the local entropy of network were extracted as features. Finally, the extracted features and support vector machines (SVM) were combined to classify epileptic seizure and non-seizure signals, and the classification performance was evaluated by k-fold cross validation. Seven different experimental cases were tested. The experimental results indicate that the algorithm had high classification accuracy for all cases.