Zhang Yanli, Zhou Weidong, Yuan Qi, Wu Qi
School of Information Science and Engineering, Shandong University, Jinan 250100, China; School of Information and Electronics Engineering, Shandong Institute of Business and Technology, Yantai 264005, China; Suzhou Institute, Shandong University, Suzhou 215123, China.
School of Information Science and Engineering, Shandong University, Jinan 250100, China; Suzhou Institute, Shandong University, Suzhou 215123, China.
Epilepsy Res. 2014 Oct;108(8):1357-66. doi: 10.1016/j.eplepsyres.2014.06.007. Epub 2014 Jul 7.
The dynamic changes of electroencephalograph (EEG) signals in the period prior to epileptic seizures play a major role in the seizure prediction. This paper proposes a low computation seizure prediction algorithm that combines a fractal dimension with a machine learning algorithm. The presented seizure prediction algorithm extracts the Higuchi fractal dimension (HFD) of EEG signals as features to classify the patient's preictal or interictal state with Bayesian linear discriminant analysis (BLDA) as a classifier. The outputs of BLDA are smoothed by a Kalman filter for reducing possible sporadic and isolated false alarms and then the final prediction results are produced using a thresholding procedure. The algorithm was evaluated on the intracranial EEG recordings of 21 patients in the Freiburg EEG database. For seizure occurrence period of 30 min and 50 min, our algorithm obtained an average sensitivity of 86.95% and 89.33%, an average false prediction rate of 0.20/h, and an average prediction time of 24.47 min and 39.39 min, respectively. The results confirm that the changes of HFD can serve as a precursor of ictal activities and be used for distinguishing between interictal and preictal epochs. Both HFD and BLDA classifier have a low computational complexity. All of these make the proposed algorithm suitable for real-time seizure prediction.
癫痫发作前脑电图（EEG）信号的动态变化在癫痫发作预测中起着重要作用。本文提出了一种结合分形维数和机器学习算法的低计算量癫痫发作预测算法。所提出的癫痫发作预测算法提取EEG信号的 Higuchi 分形维数（HFD）作为特征，以贝叶斯线性判别分析（BLDA）作为分类器对患者的发作前期或发作间期状态进行分类。BLDA 的输出通过卡尔曼滤波器进行平滑处理，以减少可能出现的零星和孤立的误报，然后使用阈值处理过程得出最终的预测结果。该算法在弗莱堡 EEG 数据库中 21 名患者的颅内 EEG 记录上进行了评估。对于 30 分钟和 50 分钟的癫痫发作期，我们的算法平均灵敏度分别为 86.95%和 89.33%，平均误预测率为 0.20/小时，平均预测时间分别为 24.47 分钟和 39.39 分钟。结果证实，HFD 的变化可作为发作期活动的先兆，并用于区分发作间期和发作前期。HFD 和 BLDA 分类器都具有较低的计算复杂度。所有这些使得所提出的算法适用于实时癫痫发作预测。
