Department of Systems and Informatics, University of Florence, Florence 50139, Italy.
IEEE Trans Biomed Eng. 2010 May;57(5):1124-32. doi: 10.1109/TBME.2009.2038990. Epub 2010 Feb 17.
This paper addresses the prediction of epileptic seizures from the online analysis of EEG data. This problem is of paramount importance for the realization of monitoring/control units to be implanted on drug-resistant epileptic patients. The proposed solution relies in a novel way on autoregressive modeling of the EEG time series and combines a least-squares parameter estimator for EEG feature extraction along with a support vector machine (SVM) for binary classification between preictal/ictal and interictal states. This choice is characterized by low computational requirements compatible with a real-time implementation of the overall system. Moreover, experimental results on the Freiburg dataset exhibited correct prediction of all seizures (100 % sensitivity) and, due to a novel regularization of the SVM classifier based on the Kalman filter, also a low false alarm rate.
本文针对从 EEG 数据的在线分析中预测癫痫发作这一问题展开研究。对于为耐药性癫痫患者植入的监测/控制单元的实现，这一问题至关重要。本文提出的解决方案依赖于 EEG 时间序列的自回归建模，并结合最小二乘参数估计器用于 EEG 特征提取，同时采用支持向量机（SVM）进行癫痫发作前/发作期和发作间期的二分类。这种选择的特点是计算要求低，与整个系统的实时实现兼容。此外，在弗莱堡数据集上的实验结果表明，所有癫痫发作都得到了正确预测（敏感性为 100%），并且由于基于卡尔曼滤波器的 SVM 分类器的新正则化，假警报率也很低。
