Abstract The automatic seizure detection and classification are significant in both diagnosis of epilepsy and relieving heavy working load of doctors. In this paper we proposed a new seizure detection method based on multifeatures of longterm intracranial EEG. After wavelet and halfwave decomposition, differeutial variance, relative energy and relative fluctuation index were used to characterize seizure activity as three features. Then the feature vector was fed to Bayesian formulation which was used as a classifier. A sensitivity of 94.2%, average specificity of 95.6 % and a false detection rate of 1.16 per hour were achieved with longterm intracranial EEG from Freiburg dataset. The experimental results indicated that this method is able to detect epileptic seizures effectively and its low computational complexity made it suitable for realtime seizure detection.
［1］Khan YU, Gotman J. Waveletbased automatic seizure detection in intracerebral electroencephalogram［J］. Clinical Neurophysiology, 2003,114(5): 898-908.
［2］Gotman J, Gloor P. Automatic recognition and quantification of interictal epileptic activity in the human scalp EEG［J］. Electroencephalography and Clinical Neurophysiology, 1976, 41(5): 513-529.
［3］Gotman J. Automatic recognition of epileptic seizures in the EEG［J］. Electroencephalography and Clinical Neurophysiology, 1982, 54(5): 530-540.
［4］Pradhan N, Dutt D, Satyam S. A mimeticbased frequency domain technique for automatic generation of EEG reports［ J］. Computers in Biology and Medicine,1993, 23(1): 15-20.
［5］Sankar R, Natour J. Automatic computer analysis of transients in EEG［J］. Computers in Biology and Medicine, 1992, 22(6):407-422.
［6］Grewal S, Gotman J. An automatic warning system for epileptic seizures recorded on intracerebral EEGs［J］. Clinical Neurophysiology, 2005, 116(10): 2460-2472.
［7］Majumdar KK, Vardhan P. Automatic seizure detection in ECoG by differential operator and windowed variance［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2011, 19(4): 356-365.
［8］Saab M, Gotman J. A system to detect the onset of epileptic seizures in scalp EEG ［J］. Clinical Neurophysiology, 2005,116(2):427-442.
［9］Yuan Q, Zhou W, Liu Y, et al. Epileptic seizure detection with linear and nonlinear features［J］. Epilepsy and Behavior, 2012, 24: 415-421.
［10］蔡冬梅，周卫东，李淑芳，等．基于去趋势波动分析和支持向量机的癫痫脑电分类［J］．生物物理学报，2011，27(2)：175-182.
［11］Chua E, Patel K, Fitzsimons M, et al. Improved patient specic seizure detection during presurgical evaluation［J］. Clinical Neurophysiology, 2011, 122(4): 672-679.
［12］Raghunathan S, Jaitli A, Irazoqui PP. Multistage seizure detection techniques optimized for lowpower hardware platforms［J］. Epilepsy and Behavior, 2011,22:S61-S68.
